Research Areas:
Artificial Intelligence in Healthcare
An open-source toolbox for enhancing the assessment of muscle activation patterns during cyclical movements
Authors:
Gregorio Dotti, Marco Ghislieri, Cristina Castagneri, Valentina Agostini, Marco Knaflitz, Gabriella Balestra and Samanta RosatiJournal:
IOP Physiological MeasurementDOI:
10.1088/1361-6579/ad814fYear:
2024Abstract:
Dynamic muscle activity can be quantitatively and non-invasively investigated during several cyclical movements by acquiring surface electromyographic (sEMG) signals. The accurate temporal analysis of muscle activations is of great importance in several research areas spanning from the assessment of altered muscle activation patterns in orthopaedic and neurological patients to the monitoring of their motor rehabilitation. Several studies have highlighted the challenge of understanding and interpreting muscle activation patterns due to the high cycle-by-cycle variability of the sEMG data. This makes it difficult to interpret results and to use sEMG signals in the clinical practice. To overcome this limitation, specific algorithms are needed to help scientists to easily characterize and assess muscle activation patterns during cyclical movements. In this perspective, CIMAP (Clustering for the Identification of Muscle Activation Patterns) is an open-source Python toolbox based on agglomerative hierarchical clustering that aims at characterizing muscle activation patterns during cyclical movements by grouping movement cycles showing similar muscle activity. From muscle activation intervals to the graphical representation of the agglomerative hierarchical clustering dendrograms, the proposed toolbox offers a complete analysis framework for enabling the assessment muscle activation pattern. The toolbox can be flexibly modified to comply with the necessities of the scientist. CIMAP is addressed to scientists of any programming skill level working in different research areas such as biomedical engineering, robotics, sports, clinics, biomechanics, and neuroscience. CIMAP is freely available on GitHub (https://github.com/Biolab-PoliTO/CIMAP).
Read moreCarotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans
Authors:
K. M. Meiburger, F. Marzola, G. Zahnd, F. Faita, C. P. Loizou, N. Lainé, C. Carvalho, D. A. Steinman, L. Gibello, R.M. Bruno, R. Clarenbach, M. Francesconi, A. N. Nicolaides, H. Liebgott, A. Campilho, R. Ghotbi, E. Kyriacou, N. Navab, M. Griffin, A. G. PaJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2022.105333Year:
2022Abstract:
After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on U-Net convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 μm vs. 160 ± 140 μm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 μm, 143 ± 118 μm and 139 ± 136 μm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis (https://doi.org/10.17632/m7ndn58sv6.1).
Read moreIntegration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images
Authors:
Massimo Salvi, Bruno De Santi, Bianca Pop, Martino Bosco, Valentina Giannini, Daniele Regge, Filippo Molinari, and Kristen M. MeiburgerJournal:
Journal of ImagingDOI:
https://doi.org/10.3390/jimaging8050133Year:
2022Abstract:
Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.
Read moreA hybrid deep learning approach for gland segmentation in prostate histopathological images
Authors:
Salvi, M., Bosco, M., Molinaro, L., Gambella, A., Papotti, M., Acharya, U. R., & Molinari, F.Journal:
Artificial Intelligence in MedicineDOI:
10.1016/j.artmed.2021.102076Year:
2021 Read moreDeep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment
Authors:
Francesco Marzola, Nens van Alfen, Jonne Doorduin, Kristen M. MeiburgerJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2021.104623Year:
2021Abstract:
Ultrasound imaging is a patient-friendly and robust technique for studying physiological and pathological muscles. An automatic deep learning (DL) system for the analysis of ultrasound images could be useful to support an expert operator, allowing the study of large datasets requiring less human interaction. The purpose of this study is to present a deep learning algorithm for the cross-sectional area (CSA) segmentation in transverse musculoskeletal ultrasound images, providing a quantitative grayscale analysis which is useful for studying muscles, and to validate the results in a large dataset. The dataset included 3917 images of biceps brachii, tibialis anterior and gastrocnemius medialis acquired on 1283 subjects (mean age 50 ± 21 years, 729 male). The algorithm was based on multiple deep-learning architectures, and its performance was compared to a manual expert segmentation. We compared the mean grayscale value inside the automatic and manual CSA using Bland-Altman plots and a correlation analysis. Classification in healthy and abnormal muscles between automatic and manual segmentation were compared using the grayscale value z-scores. In the test set, a Precision of 0.88 ± 0.12 and a Recall of 0.92 ± 0.09 was achieved. The network segmentation performance was slightly less in abnormal muscles, without a loss of discrimination between healthy and abnormal muscle images. Bland-Altman plots showed no clear trend in the error distribution and the two readings have a 0.99 Pearson’s correlation coefficient (p < 0.001, test set). The ICC(A, 1) calculated between the z-score readings was 0.99. The algorithm achieves robust CSA segmentation performance and gives mean grayscale level information comparable to a manual operator. This could provide a helpful tool for clinicians in neuromuscular disease diagnosis and follow-up. The entire dataset and code are made available for the research community.
Read moreImpact of stain normalization and patch selection on the performance of convolutional neural networks in histological breast and prostate cancer classification
Authors:
Salvi, M., Molinari, F., Acharya, U. R., Molinaro, L., & Meiburger, K. M.Journal:
Computer Methods and Programs in Biomedicine UpdateDOI:
10.1016/j.cmpbup.2021.100004Year:
2021 Read moreThe impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis
Authors:
Salvi, M., Acharya, U. R., Molinari, F., & Meiburger, K. M.Journal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2020.104129Year:
2021 Read moreThe Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks
Authors:
Federica Veronese, Francesco Branciforti, Elisa Zavattaro,Vanessa Tarantino,Valentina Romano, Kristen M. Meiburger, Massimo Salvi, Silvia Seoni, and Paola SavoiaJournal:
DiagnosticsDOI:
10.3390/diagnostics11030451Year:
2021 Read moreA Convolutional Neural Network based system for Colorectal cancer segmentation on MRI images
Authors:
J. Panic; A. Defeudis; S. Mazzetti; S. Rosati; G. Giannetto; L. Vassallo; D. Regge; G. Balestra; V. GianniniJournal:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)DOI:
10.1109/EMBC44109.2020.9175804Year:
2020Abstract:
The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.
Read moreAutomatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks
Authors:
Francesco Marzola; Nens van Alfen; Massimo Salvi; Bruno De Santi; Jonne Doorduin; Kristen M. MeiburgerJournal:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)DOI:
10.1109/EMBC44109.2020.9176343Year:
2020 Read moreComparison of different classifiers to recognize active bone marrow from CT images
Authors:
Rosati, S., Franco, P., Fiandra, C., Arcadipane, F., Silvetti, P., Gallio, E., Panic, J., Ricardi, U., Balestra, G.Journal:
IEEE Medical Measurements and Applications, MeMeA 2020 - Conference ProceedingsDOI:
10.1109/MeMeA49120.2020.9137173Year:
2020 Read moreRadiomics predicts response of individual HER2-amplified colorectal cancer liver metastases in patients treated with HER2-targeted therapy
Authors:
V. Giannini, S. Rosati, A. Defeudis, G. Balestra, L. Vassallo, G. Cappello, S. Mazzetti, C. De Mattia, F. Rizzetto, A. Torresin, A. Sartore-Bianchi, S. Siena, A. Vanzulli, F. Leone, V. Zagonel, S. MarsonJournal:
International journal of cancerDOI:
10.1002/ijc.33271Year:
2020Abstract:
The aim of our study was to develop and validate a machine learning algorithm to predict response of individual HER2-amplified colorectal cancer liver metastases (lmCRC) undergoing dual HER2-targeted therapy. Twenty-four radiomics features were extracted after 3D manual segmentation of 141 lmCRC on pretreatment portal CT scans of a cohort including 38 HER2-amplified patients; feature selection was then performed using genetic algorithms. lmCRC were classified as nonresponders (R-), if their largest diameter increased more than 10% at a CT scan performed after 3 months of treatment, responders (R+) otherwise. Sensitivity, specificity, negative (NPV) and positive (PPV) predictive values in correctly classifying individual lesion and overall patient response were assessed on a training dataset and then validated on a second dataset using a Gaussian naïve Bayesian classifier. Per-lesion sensitivity, specificity, NPV and PPV were 89%, 85%, 93%, 78% and 90%, 42%, 73%, 71% respectively in the testing and validation datasets. Per-patient sensitivity and specificity were 92% and 86%. Heterogeneous response was observed in 9 of 38 patients (24%). Five of nine patients were carriers of nonresponder lesions correctly classified as such by our radiomics signature, including four of seven harboring only one nonresponder lesion. The developed method has been proven effective in predicting behavior of individual metastases to targeted treatment in a cohort of HER2 amplified patients. The model accurately detects responder lesions and identifies nonresponder lesions in patients with heterogeneous response, potentially paving the way to multimodal treatment in selected patients. Further validation will be needed to confirm our findings.
Read moreCascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals
Authors:
N. Michielli, U. R. Acharya, F. MolinariJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2019.01.013Year:
2019 Read moreRadiomics for Identification of Active Bone Marrow from CT: An Exploratory Study
Authors:
S. Rosati; G. Balestra; P. Franco; C. Fiandra; F. Arcadipane; P. Silvetti; U. Ricardi; E. GallioJournal:
2018 IEEE Life Sciences Conference (LSC)DOI:
10.1109/LSC.2018.8572154Year:
2018Abstract:
The radiation dose received by the pelvic Bone Marrow (BM) is a predictive factor for Hematologic Toxicity (HT) occurrence in the treatment of anal cancer. For this reason it is important to avoid BM during radiotherapy. In particular, the standard strategy in these cases consists in the identification of hematopoietically active BM (actBM), i.e. the part of BM in charge of blood cells generation, on 18 FDG-PET, FLT-PET or MRI, but no approached have been developed for identifying actBM from CT images. This exploratory study aims to use radiomics for detecting actBM on CT sequences. Our approach is based on the extraction of 36 first-order and texture (second-order) features for each CT slice. These features are used as input of a Decision Tree (DT) classifier able to discriminate between active and inactive BM regions on the images. This method was applied to five patients affected by carcinoma of the anal canal and the obtained actBM segmentation was compared with the standard actBM identification from 18 FDG-PET (reference standard, RS). Our results show that actBM identification in lumbosacral and iliac structures using radiomics overlaps the RS for more than 75% in 4 out of 5 patients.
Read moreRadiomics to predict response to neoadjuvant chemotherapy in rectal cancer: Influence of simultaneous feature selection and classifier optimization
Authors:
Rosati, S., Gianfreda, C.M., Balestra, G., Giannini, V., Mazzetti, S., Regge, D.Journal:
IEEE Life Sciences Conference, LSC 2018DOI:
10.1109/LSC.2018.8572194Year:
2018 Read moreBiomedical Signal And Data Processing
A comparative study of muscle activity and synergies during walking in baboons and humans
Authors:
Francois Druelle*, Marco Ghislieri*, Pablo Molina-Vila, Brigitte Rimbaud, Valentina Agostini, Gilles BerillonJournal:
Journal of Human EvolutionDOI:
10.1016/j.jhevol.2024.103513Year:
2024Abstract:
Bipedal locomotion was a major functional change during hominin evolution, yet, our understanding of this gradual and complex process remains strongly debated. Based on fossil discoveries, it is possible to address functional hypotheses related to bipedal anatomy, however, motor control remains intangible with this approach. Using comparative models which occasionally walk bipedally has proved to be relevant to shed light on the evolutionary transition toward habitual bipedalism. Here, we explored the organization of the neuromuscular control using surface electromyography (sEMG) for six extrinsic muscles in two baboon individuals when they walk quadrupedally and bipedally on the ground. We compared their muscular coordination to five human subjects walking bipedally. We extracted muscle synergies from the sEMG envelopes using the nonnegative matrix factorization algorithm which allows decomposing the sEMG data in the linear combination of two non-negative matrixes (muscle weight vectors and activation coefficients). We calculated different parameters to estimate the complexity of the sEMG signals, the duration of the activation of the synergies, and the generalizability of the muscle synergy model across species and walking conditions. We found that the motor control strategy is less complex in baboons when they walk bipedally, with an increased muscular activity and muscle coactivation. When comparing the baboon bipedal and quadrupedal pattern of walking to human bipedalism, we observed that the baboon bipedal pattern of walking is closer to human bipedalism for both baboons, although substantial differences remain. Overall, our findings show that the muscle activity of a nonadapted biped effectively fulfills the basic mechanical requirements (propulsion and balance) for walking bipedally, but substantial refinements are possible to optimize the efficiency of bipedal locomotion. In the evolutionary context of an expanding reliance on bipedal behaviors, even minor morphological alterations, reducing muscle coactivation, could have faced strong selection pressure, ultimately driving bipedal evolution in hominins.
Read moreA Statistical Approach for Functional Reach-to-Grasp Segmentation Using a Single Inertial Measurement Unit
Authors:
Gregorio Dotti, Marco Caruso, Daniele Fortunato, Marco Knaflitz, Andrea Cereatti and Marco GhislieriJournal:
SensorsDOI:
10.3390/s24186119Year:
2024Abstract:
The aim of this contribution is to present a segmentation method for the identification of voluntary movements from inertial data acquired through a single inertial measurement unit placed on the subject’s wrist. Inertial data were recorded from 25 healthy subjects while performing 75 consecutive reach-to-grasp movements. The approach herein presented, called DynAMoS, is based on an adaptive thresholding step on the angular velocity norm, followed by a statistics-based post-processing on the movement duration distribution. Post-processing aims at reducing the number of erroneous transitions in the movement segmentation. We assessed the segmentation quality of this method using a stereophotogrammetric system as the gold standard. Two popular methods already presented in the literature were compared to DynAMoS in terms of the number of movements identified, onset and offset mean absolute errors, and movement duration. Moreover, we analyzed the sub-phase durations of the drinking movement to further characterize the task. The results show that the proposed method performs significantly better than the two state-of-the-art approaches (i.e., percentage of erroneous movements = 3%; onset and offset mean absolute error < 0.08 s), suggesting that DynAMoS could make more effective home monitoring applications for assessing the motion improvements of patients following domicile rehabilitation protocols.
Read moreAn open-source toolbox for enhancing the assessment of muscle activation patterns during cyclical movements
Authors:
Gregorio Dotti, Marco Ghislieri, Cristina Castagneri, Valentina Agostini, Marco Knaflitz, Gabriella Balestra and Samanta RosatiJournal:
IOP Physiological MeasurementDOI:
10.1088/1361-6579/ad814fYear:
2024Abstract:
Dynamic muscle activity can be quantitatively and non-invasively investigated during several cyclical movements by acquiring surface electromyographic (sEMG) signals. The accurate temporal analysis of muscle activations is of great importance in several research areas spanning from the assessment of altered muscle activation patterns in orthopaedic and neurological patients to the monitoring of their motor rehabilitation. Several studies have highlighted the challenge of understanding and interpreting muscle activation patterns due to the high cycle-by-cycle variability of the sEMG data. This makes it difficult to interpret results and to use sEMG signals in the clinical practice. To overcome this limitation, specific algorithms are needed to help scientists to easily characterize and assess muscle activation patterns during cyclical movements. In this perspective, CIMAP (Clustering for the Identification of Muscle Activation Patterns) is an open-source Python toolbox based on agglomerative hierarchical clustering that aims at characterizing muscle activation patterns during cyclical movements by grouping movement cycles showing similar muscle activity. From muscle activation intervals to the graphical representation of the agglomerative hierarchical clustering dendrograms, the proposed toolbox offers a complete analysis framework for enabling the assessment muscle activation pattern. The toolbox can be flexibly modified to comply with the necessities of the scientist. CIMAP is addressed to scientists of any programming skill level working in different research areas such as biomedical engineering, robotics, sports, clinics, biomechanics, and neuroscience. CIMAP is freely available on GitHub (https://github.com/Biolab-PoliTO/CIMAP).
Read moreFoot–Floor Contact Sequences: A Metric for Gait Assessment in Parkinson’s Disease after Deep Brain Stimulation
Authors:
Marco Ghislieri, Valentina Agostini, Laura Rizzi, Chiara Fronda, Marco Knaflitz, Michele LanotteJournal:
SensorsDOI:
10.3390/s24206593Year:
2024Abstract:
Digital gait monitoring is increasingly used to assess locomotion and fall risk. The aim of this work is to analyze the changes in the foot–floor contact sequences of Parkinson’s Disease (PD) patients in the year following the implantation of Deep Brain Stimulation (DBS). During their best-ON condition, 30 PD patients underwent gait analysis at baseline (T0), at 3 months after subthalamic nucleus DBS neurosurgery (T1), and at 12 months (T2) after subthalamic nucleus DBS neurosurgery. Thirty age-matched controls underwent gait analysis once. Each subject was equipped with bilateral foot-switches and a 5 min walk was recorded, including both straight-line and turnings. The walking speed, turning time, stride time variability, percentage of atypical gait cycles, stance, swing, and double support duration were estimated. Overall, the gait performance of PD patients improved after DBS, as also confirmed by the decrease in their UPDRS-III scores from 19.4 ± 1.8 to 10.2 ± 1.0 (T0 vs.T2) (p < 0.001). In straight-line walking, the percentages of atypical cycles of PD on the more affected side were 11.1 ± 1.5% (at T0), 3.1 ± 1.5% (at T1), and 5.1 ± 2.4% (at T2), while in controls it was 3.1 ± 1.3% (p < 0.0005). In turnings, this percentage was 13.7 ± 1.1% (at T0), 7.8 ± 1.1% (at T1), and 10.9 ± 1.8% (at T2), while in controls it was 8.1 ± 1.0% (p < 0.001). Therefore, in straight-line walking, the atypical cycles decreased by 72% at T1, and by 54% at T2 (with respect to baseline), while, in turnings, atypical cycles decreased by 43% at T1, and by 20% at T2. The percentage of atypical gait cycles proved an informative digital biomarker for quantifying PD gait changes after DBS, both in straight-line paths and turnings.
Read moreBalance and Muscle Synergies during a Single-Limb Stance Task in Individuals with Chronic Ankle Instability
Authors:
M. Ghislieri, L. Labanca, M. Mosca, L. Bragonzoni, M. Kanflitz & V. AgostiniJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2023.3328933Year:
2023Abstract:
The aim of this study was to investigate balance performance and muscle synergies during a Single-Limb Stance (SLS) task in individuals with Chronic Ankle Instability (CAI) and a group of healthy controls. Twenty individuals with CAI and twenty healthy controls were asked to perform a 30-second SLS task in Open-Eyes (OE) and Closed-Eyes (CE) conditions while standing on a force platform with the injured or the dominant limb, respectively. The activation of 13 muscles of the lower limb, hip, and back was recorded by means of surface electromyography. Balance performance was assessed by identifying the number and the duration of SLS epochs, and the Root-Mean-Square (RMS) in Antero-Posterior (AP) and Medio-Lateral (ML) directions of the body-weight normalized ground reaction forces. The optimal number of synergies, weight vectors, and activation coefficients were also analyzed. CAI group showed a higher number and a shorter duration of SLS epochs and augmented ground reaction force RMS in both AP and ML directions compared to controls. Both groups showed an increase in the RMS in AP and ML forces in CE compared to OE. Both groups showed 4 optimal synergies in CE, while controls showed 5 synergies in OE. CAI showed a significantly higher weight of knee flexor muscles in both OE and CE. In conclusion, muscle synergies analysis provided an in–depth knowledge of motor control mechanisms in CAI individuals. They showed worse balance performance, a lower number of muscle synergies in a CE condition and abnormal knee flexor muscle activation compared to healthy controls.
Read moreMuscle synergies in Parkinson’s disease before and after the deep brain stimulation of the bilateral subthalamic nucleus
Authors:
Marco Ghislieri, Michele Lanotte, Marco Knaflitz, Laura Rizzi, and Valentina AgostiniJournal:
Scientific ReportsDOI:
10.1038/s41598-023-34151-6Year:
2023Abstract:
The aim of this study is to quantitatively assess motor control changes in Parkinson’s disease (PD) patients after bilateral deep brain stimulation of the subthalamic nucleus (STN-DBS), based on a novel muscle synergy evaluation approach. A group of 20 PD patients evaluated at baseline (before surgery, T0), at 3 months (T1), and at 12 months (T2) after STN-DBS surgery, as well as a group of 20 age-matched healthy control subjects, underwent an instrumented gait analysis, including surface electromyography recordings from 12 muscles. A smaller number of muscle synergies was found in PD patients (4 muscle synergies, at each time point) compared to control subjects (5 muscle synergies). The neuromuscular robustness of PD patients—that at T0 was smaller with respect to controls (PD T0: 69.3 ± 2.2% vs. Controls: 77.6 ± 1.8%, p = 0.004)—increased at T1 (75.8 ± 1.8%), becoming not different from that of controls at T2 (77.5 ± 1.9%). The muscle synergies analysis may offer clinicians new knowledge on the neuromuscular structure underlying PD motor types of behavior and how they can improve after electroceutical STN-DBS therapy.
Read moreWearable Inertial Sensors to Assess Standing Balance: A Systematic Review
Authors:
M. Ghislieri, L. Gastaldi, S. Pastorelli, S. Tadano, and V. AgostiniJournal:
SensorsDOI:
10.3390/s19194075Year:
2019Abstract:
Wearable sensors are de facto revolutionizing the assessment of standing balance. The aim of this work is to review the state-of-the-art literature that adopts this new posturographic paradigm, i.e., to analyse human postural sway through inertial sensors directly worn on the subject body. After a systematic search on PubMed and Scopus databases, two raters evaluated the quality of 73 full-text articles, selecting 47 high-quality contributions. A good inter-rater reliability was obtained (Cohen’s kappa = 0.79). This selection of papers was used to summarize the available knowledge on the types of sensors used and their positioning, the data acquisition protocols and the main applications in this field (e.g., “active aging”, biofeedback-based rehabilitation for fall prevention, and the management of Parkinson’s disease and other balance-related pathologies), as well as the most adopted outcome measures. A critical discussion on the validation of wearable systems against gold standards is also presented.
Read moreAutomated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications
Authors:
N. Giordano, S. Rosati, and M. KnaflitzJournal:
SensorsDOI:
10.3390/s21217246Year:
2021Abstract:
The signal quality limits the applicability of phonocardiography at the patients’ domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.
Read moreEvaluation of Muscle Function by Means of a Muscle-Specific and a Global Index
Authors:
S. Rosati, M. Ghislieri, G. Dotti, D. Fortunato, V. Agostini, M.Knaflitz, and G. BalestraJournal:
SensorsDOI:
10.3390/s21217186Year:
2021Abstract:
Gait analysis applications in clinics are still uncommon, for three main reasons: (1) the considerable time needed to prepare the subject for the examination; (2) the lack of user-independent tools; (3) the large variability of muscle activation patterns observed in healthy and pathological subjects. Numerical indices quantifying the muscle coordination of a subject could enable clinicians to identify patterns that deviate from those of a reference population and to follow the progress of the subject after surgery or completing a rehabilitation program. In this work, we present two user-independent indices. First, a muscle-specific index (MFI) that quantifies the similarity of the activation pattern of a muscle of a specific subject with that of a reference population. Second, a global index (GFI) that provides a score of the overall activation of a muscle set. These two indices were tested on two groups of healthy and pathological children with encouraging results. Hence, the two indices will allow clinicians to assess the muscle activation, identifying muscles showing an abnormal activation pattern, and associate a functional score to every single muscle as well as to the entire muscle set. These opportunities could contribute to facilitating the diffusion of surface EMG analysis in clinics
Read moreLong short-term memory (LSTM) recurrent neural network for muscle activity detection
Authors:
M. Ghislieri, G. L. Cerone, M. Knaflitz, & V. AgostiniJournal:
Journal of NeuroEngineering and RehabilitationDOI:
10.1186/s12984-021-00945-wYear:
2021Abstract:
Background
The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.
Methods
First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager–Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis.
Results
The proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR.
Conclusions
The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.
Read moreMuscle synergies for the control of single-limb stance with and without visual information in young individuals
Authors:
L. Labanca, M. Ghislieri, M. Knaflitz, G. Barone, L. Bragonzoni, V. Agostini & M. G. BenedettiJournal:
BMC Sports Science, Medicine and RehabilitationDOI:
10.1186/s13102-021-00392-zYear:
2021Abstract:
Purpose
Single-limb stance is a demanding postural task featuring a high number of daily living and sporting activities. Thus, it is widely used for training and rehabilitation, as well as for balance assessment. Muscle activations around single joints have been previously described, however, it is not known which are the muscle synergies used to control posture and how they change between conditions of normal and lack of visual information.
Methods
Twenty-two healthy young participants were asked to perform a 30 s single-limb stance task in open-eyes and closed-eyes condition while standing on a force platform with the dominant limb. Muscle synergies were extracted from the electromyographical recordings of 13 muscles of the lower limb, hip, and back. The optimal number of synergies, together with the average recruitment level and balance control strategies were analyzed and compared between the open- and the closed-eyes condition.
Results
Four major muscle synergies, two ankle-dominant synergies, one knee-dominant synergy, and one hip/back-dominant synergy were found. No differences between open- and closed-eyes conditions were found for the recruitment level, except for the hip/back synergy, which significantly decreased (p = 0.02) in the closed-eyes compared to the open-eyes condition. A significant increase (p = 0.03) of the ankle balance strategy was found in the closed-eyes compared to the open-eyes condition.
Conclusion
In healthy young individuals, single-limb stance is featured by four major synergies, both in open- and closed-eyes condition. Future studies should investigate muscle synergies in participants with other age groups, as well as pathological conditions.
Read moreStatistical Gait Analysis Based on Surface Electromyography
Authors:
Agostini, V., Ghislieri, M., Rosati, S., Balestra, B., Dotti, G., & Knaflitz, M.Journal:
Medicine-Based Informatics and EngineeringDOI:
10.1007/978-3-030-87845-0_2Year:
2021Abstract:
To help neurologists, physicians, and physical therapists in the management of patients with altered locomotion patterns, it is of the uttermost importance relying on accurate measurements of gait. Gait analysis becomes even more informative if the electrical activity of muscles is recorded, non-invasively, during the dynamic task of walking, through surface electromyography (sEMG) probes. However, sEMG signals must be processed through advanced techniques to obtain reliable results, easily interpretable by healthcare practitioners. Indeed, the study of how muscles are activated during natural walking (in unconstrained environments) is complex for several reasons, including a high stride-to-stride variability, even more pronounced in pathological subjects. On the other hand, it is crucial to provide clinicians with aggregated information relying on validated parameters and easily usable representations that can be effectively included in clinical reports. This chapter is aimed at introducing: (1) Statistical Gait Analysis (SGA) to automatically analyze hundreds of gait cycles collected during a physiological or pathological walk lasting several minutes, (2) the extraction of principal and secondary muscle activations to obtain consistent clinical indexes, (3) the extraction of “muscle synergies” to quantitatively study motor control strategies. Each of these techniques are based on state-of-the-art processing algorithms of the sEMG signal. A brief review of the recent literature published in this field will be presented and discussed.
Read moreAutomatic Dynamic Range Estimation for Ultrasound Image Visualization and Processing
Authors:
Kristen M. Meiburger, Silvia Seoni, Giulia MatroneJournal:
2020 IEEE International Ultrasonics Symposium (IUS)DOI:
10.1109/IUS46767.2020.9251470Year:
2020 Read moreNon-Invasive Analysis of Actinic Keratosis before and after Topical Treatment Using a Cold Stimulation and Near-Infrared Spectroscopy
Authors:
Silvia Seoni, Paola Savoia,Federica Veronese,Elisa Zavattaro,Vanessa Tarantino, and Kristen M. MeiburgerJournal:
MedicinaDOI:
10.3390/medicina56090482Year:
2020 Read moreRobustness Analysis of Texture Features with Different Beamforming Techniques
Authors:
Silvia Seoni, Giulia Matrone, Kristen M. MeiburgerJournal:
2020 IEEE International Ultrasonics Symposium (IUS)DOI:
10.1109/IUS46767.2020.9251737Year:
2020 Read moreA novel method for measuring the timing of heart sound components through digital phonocardiography
Authors:
N. Giordano and M. KnaflitzJournal:
SensorsDOI:
10.3390/s19081868Year:
2019 Read moreAsymmetry Index in Muscle Activations
Authors:
Castagneri, C., Agostini, V., Rosati, S., Balestra, G., Knaflitz, M.Journal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2019.2903687Year:
2019 Read moreCascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals
Authors:
N. Michielli, U. R. Acharya, F. MolinariJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2019.01.013Year:
2019 Read moreLifestyle analysis of a female group of university workers: Do they reach recommended levels of physical activity?
Authors:
S. Rosati, G. Balestra, D. Fortunato, and Marco KnaflitzJournal:
2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT)DOI:
10.1109/ISCE.2019.8900992Year:
2019Abstract:
–
Read moreMulti-source signal processing in phonocardiography: comparison among signal selection and signal enhancement techniques
Authors:
N. Giordano and M. KnaflitzJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856725Year:
2019 Read moreNon-invasive analysis of actinic keratosis using a cold stimulation and near-infrared spectroscopy
Authors:
Silvia Seoni, Federica Veronese, Vanessa Tarantino, Elisa Zavattaro, Massimo Salvi, Nicola Michielli, Bruno De Santi, Filippo Molinari, Paola Savoia, Kristen M. MeiburgerJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8857279Year:
2019 Read moreMuscle activation patterns during gait: A hierarchical clustering analysis
Authors:
Rosati, S., Agostini, V., Knaflitz, M., Balestra, G.Journal:
Biomedical Signal Processing and ControlDOI:
10.1016/j.bspc.2016.09.017Year:
2017 Read moreDoes texting while walking really affect gait in young adults?
Authors:
V. Agostini, F. Lo Fermo, G. Massazza and M. KnaflitzJournal:
Journal of NeuroEngineering and RehabilitationDOI:
10.1186/s12984-015-0079-4Year:
2015Abstract:
Background: Texting on a smartphone while walking has become a customary task among young adults. In recent literature many safety concerns on distracted walking have been raised. It is often hypothesized that the allocation of attentional resources toward a secondary task can influence dynamic stability. In the double task of walking and texting it was found that gait speed is reduced, but there is scarce evidence of a modified motor control strategy compromising stability. The aim of this study is twofold: 1) to comprehensively examine the gait modifications occurring when texting while walking, including the study of the lower limb muscle activation patterns, 2) to specifically assess the co-contraction of ankle antagonist muscles. We hypothesized that texting while walking increases co-contractions of ankle antagonist muscles when the body weight is transferred from one lower limb to the other, to improve the distal motor control and joint stabilization.
Methods: From the gait data collected during an instrumented walk lasting 3 min, we calculated the spatio-temporal parameters, the ankle and knee kinematics, the muscle activation patterns of tibialis anterior, gastrocnemius lateralis, peroneus longus, rectus femoris, and lateral hamstrings, and the co-contraction (occurrence and duration) of the ankle antagonist muscles (tibialis anterior and gastrocnemius lateralis), bilaterally.
Results: Young adults showed, overall, small gait modifications that could be mainly ascribable to gait speed reduction and a modified body posture due to phone handling. We found no significant alterations of ankle and knee kinematics and a slightly delayed activation onset of the left gastrocnemius lateralis. However, we found an increased co-contraction of tibialis anterior and gastrocnemius lateralis, especially during mid-stance. Conversely, we found a reduced co-contraction during terminal stance.
Conclusions: Our results suggest that, in young adults, there is an adjustment of the motor control strategy aimed at increasing ankle joint stability in a specific and “critical” phase of the gait cycle, when the body weight is transferred from one leg to the other.
Read moreInstrumented Gait Analysis for an Objective Pre-/Postassessment of Tap Test in Normal Pressure Hydrocephalus
Authors:
V. Agostini, M. Lanotte, M. Carlone, M. Campagnoli, I. Azzolin, R. Scarafia, G. Massazza, M. KnaflitzJournal:
Archives of Physical Medicine and RehabilitationDOI:
10.1016/j.apmr.2015.02.014Year:
2015Abstract:
Objective
To present an objective method to evaluate gait improvements after a tap test in idiopathic normal pressure hydrocephalus (INPH).
Design
Retrospective analysis of gait data.
Setting
Public tertiary care center, day hospital. The gait analysis was performed before and 2 to 4 hours after the tap test.
Participants
Participants included patients with INPH (n=60) and age- and sex-matched controls (n=50; used to obtain reference intervals). From an initial referred sample of 79 patients (N=79), we excluded those unable to walk without walking aids (n=9) and those with incomplete (pre-/posttap test) gait data (n=10). Thirteen out of 60 patients were shunted and then reappraised after 6 months.
Interventions
Not applicable.
Main Outcome Measures
Mahalanobis distance from controls, before and after the tap test. Eleven gait parameters were combined in a single quantitative score. Walking velocity was also evaluated because it is frequently used in tap test assessment.
Results
Patients were classified into 2 groups: tap test responders (n=22, 9 of them were shunted) and not suitable for shunt (n=38, 4 of them were shunted). In the tap test responders group, 9 out of 9 patients improved after shunt. In the not suitable for shunt group, 3 out of 4 patients did not improve. Gait velocity increased after the tap test in 53% of responders and in 37% of patients not suitable for shunt.
Conclusions
The new method is applicable to clinical practice and allows for selecting tap test responders in an objective way, quantifying the improvements. Our results suggest that gait velocity alone is not sufficient to reliably assess tap test effects.
Clinical Process Modelling
Agent-Based Modeling and Simulation of Care Delivery for Patients with Thrombotic and Bleeding Disorders
Authors:
N. Giordano, S. Rosati, F. Valeri, A. Borchiellini, G. BalestraJournal:
STUDIES IN HEALTH TECHNOLOGY AND INFORMATICS, MIE 2020DOI:
10.3233/SHTI200358Year:
2020Abstract:
The quality of patients care delivery is thought to be strongly affected by the physicians’ workload. In this study we present an Agent-Based model of the processes during a typical working day. We simulated the current scenario and a possible scenario concerning the introduction of a second ambulatory as a potential improvement in the center organization. Our results validated the reliability of the model and showed that the introduction of a second ambulatory averagely reduces the daily physician’ workload.
Read moreAn Approach Based on Process Modeling for Implementing a Health Information Technology in Clinical Practice
Authors:
G.M. Zaccaria; S. Rosati; M. Zema; V. Agostini; G. BalestraJournal:
Journal of Medical Imaging and Health InformaticsDOI:
10.1166/jmihi.2018.2353Year:
2018Abstract:
The introduction of a new Health Information Technology (HIT) in a healthcare context is a very complex process. The aim of this study is to propose a completely original approach for the implementation a new HIT in a healthcare facility or department. This novel approach is made of four steps and based on process modeling. The first step is the identification of all the stakeholders involved. The second step consists in performing a detailed description of all clinical and administrative processes that will use the new HIT in order to understand how people, resources and documents interact among them. The third step allows the analysis of the HIT functionalities in order to highlight potential problems or risks that could emerge during its daily usage and guarantee its interoperability with other software. The fourth step concerns the construction of an adoption plan, in order to avoiding sharp transitions. A set of tools were associated to each step to guarantee a correct design and implementation. An application concerning the implementation of a new commercial HIT for Computerized Provider Order Entry (CPOE) in the oncology department of a large Italian hospital is reported as an example of the proposed approach. Furthermore, the user satisfaction about the introduction of the new CPOE in the oncology department was evaluated by means of a set of questionnaires. A positive evaluation of the process emerged from this analysis, confirming the goodness of the proposed approach. Moreover, the questionnaires results showed a high level of user satisfaction.
Read moreCharacterization of Physicians Workload in a Reference Center for the Treatment of Thrombotic and Bleeding Disorders
Authors:
S. Rosati; F. Valeri; A. Borchiellini; C. M. Gianfreda; G. BalestraJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856820Year:
2019Abstract:
Heavy workloads in healthcare have been often associated to adverse clinical outcomes. To reduce workloads, an optimal scheduling of clinical staff resources is not enough, but particular attention must be payed to work organization and task characteristics. Moreover, interruptions during the clinical practice contribute to increase perceived workloads. In this study we analyzed and characterized the physicians’ workload in an Italian center for the treatment of thrombotic and bleeding disorders. First, all clinical and administrative processes performed in the center were analyzed by means of two process modelling tools. Then, the quantification of the physicians’ workload and the characterization of interruptions during practice were conducted. From our results it emerged that the task that mainly impacts on the workload is ambulatory care (42% of total workload) while interruptions produce a delay of almost 15 minutes per day and mainly occur during visits. Including all activities, the total daily workload per physician was 8 hours on average. In this time breaks were not taken into account. Concluding, from our analysis it is evident that the physicians’ workload in the analyzed center is heavy and interruptions represent a source of delay in the workflow, that impact the physicians’ workload.
Read moreDeveloping medical device software in compliance with regulations
Authors:
M. Zema; S. Rosati; V. Gioia; M. Knaflitz; G. BalestraJournal:
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2015.7318614Year:
2015Abstract:
In the last decade, the use of information technology (IT) in healthcare has taken a growing role. In fact, the adoption of an increasing number of computer tools has led to several benefits related to the process of patient care and allowed easier access to social and health care resources. At the same time this trend gave rise to new challenges related to the implementation of these new technologies. Software used in healthcare can be classified as medical devices depending on the way they are used and on their functional characteristics. If they are classified as medical devices they must satisfy specific regulations. The aim of this work is to present a software development framework that can allow the production of safe and high quality medical device software and to highlight the correspondence between each software development phase and the appropriate standard and/or regulation.
Read moreModelling and analysis of four telemedicine Italian experiences
Authors:
S. Rosati; M. Zema; C. Castagneri; F. Marchetti; G. BalestraJournal:
2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2017.8037398Year:
2017Abstract:
In the last 10 years the European population aged 65 years and over grew of 2.3%, with Italy having the highest share of elderly persons in the total population. OPLON (OPportunities for active and healthy LONgevity) is a project supported by the Italian Ministry of Education, Universities, and Research aiming to identify and prevent frailty and to improve the life quality of elderly subjects. The main goal of OPLON is to develop a “Care&Cure” model for the management of subjects with different morbidities and co-morbidities, adaptable to the subject’s risk level and to the regional contexts. In this study we analyzed four Italian telemedicine experiences addressed to chronic, geriatric or partially self-sufficient subjects. Each of them was exhaustively described by means of three process modelling tools (synopsis, workflow and swimlane activity diagrams). Starting from this analysis, we defined a general model of tele-monitoring and tele-assistance of frail and pre-frail people with different needs and pathologies. The proposed model was characterized by three macro processes (enrollment, assessment and assistance) and four groups of actors (patient, general practitioner/specialist physician, multidisciplinary team, and healthcare professionals). Combining this model with a detailed analysis of regulations and legislations in force both at local and national level, it will be possible to design the complete and efficient “Care&Cure” model.
Read moreModels of care processes: Process modeling methods and applications
Authors:
S. Rosati; M. Zema; B. BalestraJournal:
E-Health - Medicina Digitale (Book chapter)DOI:
-Year:
2017 Read moreDesign of Biomedical Instrumentation
Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications
Authors:
N. Giordano, S. Rosati, and M. KnaflitzJournal:
SensorsDOI:
10.3390/s21217246Year:
2021Abstract:
The signal quality limits the applicability of phonocardiography at the patients’ domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.
Read moreA Method for the Estimation of the Timing of Heart Sound Components Through Blind Source Separation in Multi-Source Phonocardiography
Authors:
N. Giordano and M. KnaflitzJournal:
2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA)DOI:
10.1109/MeMeA49120.2020.9137315Year:
2020 Read moreA novel method for measuring the timing of heart sound components through digital phonocardiography
Authors:
N. Giordano and M. KnaflitzJournal:
SensorsDOI:
10.3390/s19081868Year:
2019 Read moreA wearable device to assess postural sway
Authors:
V. Agostini, E. Aiello, D. Fortunato, M. Knaflitz, and L. GastaldiJournal:
2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT)DOI:
10.1109/ISCE.2019.8901019Year:
2019Abstract:
The maintenance of balance in upright stance is traditionally evaluated using heavy and expensive force platforms. The aim of this work is to prove the usefulness of a low-cost wearable sensor (an actigraph) to assess postural sway. We compared the performance of the device to a gold standard force platform. We analyzed measurements of postural sway in four conditions differently challenging the subject: with eyes open or closed, while keeping a small or large base of support. We estimated the main postural parameters (ellipse area, mediolateral and antero-posterior root-mean square, eccentricity, sway path length) considering: 1) acceleration data recorded by the actigraph, and 2) traditional COP data obtained from the force platform. We found that it is possible to clearly distinguish the differences among the postural parameters, obtained in the various balance conditions, also using acceleration data. Our results show that the wearable device allows for obtaining information similar to those achievable by the force platform. This support the use of wearable devices to assess postural balance, in a handy and cheap manner.
Read moreLifestyle analysis of a female group of university workers: Do they reach recommended levels of physical activity?
Authors:
S. Rosati, G. Balestra, D. Fortunato, and Marco KnaflitzJournal:
2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT)DOI:
10.1109/ISCE.2019.8900992Year:
2019Abstract:
–
Read moreMulti-source signal processing in phonocardiography: comparison among signal selection and signal enhancement techniques
Authors:
N. Giordano and M. KnaflitzJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856725Year:
2019 Read moreHuman Motion Analysis
A comparative study of muscle activity and synergies during walking in baboons and humans
Authors:
Francois Druelle*, Marco Ghislieri*, Pablo Molina-Vila, Brigitte Rimbaud, Valentina Agostini, Gilles BerillonJournal:
Journal of Human EvolutionDOI:
10.1016/j.jhevol.2024.103513Year:
2024Abstract:
Bipedal locomotion was a major functional change during hominin evolution, yet, our understanding of this gradual and complex process remains strongly debated. Based on fossil discoveries, it is possible to address functional hypotheses related to bipedal anatomy, however, motor control remains intangible with this approach. Using comparative models which occasionally walk bipedally has proved to be relevant to shed light on the evolutionary transition toward habitual bipedalism. Here, we explored the organization of the neuromuscular control using surface electromyography (sEMG) for six extrinsic muscles in two baboon individuals when they walk quadrupedally and bipedally on the ground. We compared their muscular coordination to five human subjects walking bipedally. We extracted muscle synergies from the sEMG envelopes using the nonnegative matrix factorization algorithm which allows decomposing the sEMG data in the linear combination of two non-negative matrixes (muscle weight vectors and activation coefficients). We calculated different parameters to estimate the complexity of the sEMG signals, the duration of the activation of the synergies, and the generalizability of the muscle synergy model across species and walking conditions. We found that the motor control strategy is less complex in baboons when they walk bipedally, with an increased muscular activity and muscle coactivation. When comparing the baboon bipedal and quadrupedal pattern of walking to human bipedalism, we observed that the baboon bipedal pattern of walking is closer to human bipedalism for both baboons, although substantial differences remain. Overall, our findings show that the muscle activity of a nonadapted biped effectively fulfills the basic mechanical requirements (propulsion and balance) for walking bipedally, but substantial refinements are possible to optimize the efficiency of bipedal locomotion. In the evolutionary context of an expanding reliance on bipedal behaviors, even minor morphological alterations, reducing muscle coactivation, could have faced strong selection pressure, ultimately driving bipedal evolution in hominins.
Read moreA Statistical Approach for Functional Reach-to-Grasp Segmentation Using a Single Inertial Measurement Unit
Authors:
Gregorio Dotti, Marco Caruso, Daniele Fortunato, Marco Knaflitz, Andrea Cereatti and Marco GhislieriJournal:
SensorsDOI:
10.3390/s24186119Year:
2024Abstract:
The aim of this contribution is to present a segmentation method for the identification of voluntary movements from inertial data acquired through a single inertial measurement unit placed on the subject’s wrist. Inertial data were recorded from 25 healthy subjects while performing 75 consecutive reach-to-grasp movements. The approach herein presented, called DynAMoS, is based on an adaptive thresholding step on the angular velocity norm, followed by a statistics-based post-processing on the movement duration distribution. Post-processing aims at reducing the number of erroneous transitions in the movement segmentation. We assessed the segmentation quality of this method using a stereophotogrammetric system as the gold standard. Two popular methods already presented in the literature were compared to DynAMoS in terms of the number of movements identified, onset and offset mean absolute errors, and movement duration. Moreover, we analyzed the sub-phase durations of the drinking movement to further characterize the task. The results show that the proposed method performs significantly better than the two state-of-the-art approaches (i.e., percentage of erroneous movements = 3%; onset and offset mean absolute error < 0.08 s), suggesting that DynAMoS could make more effective home monitoring applications for assessing the motion improvements of patients following domicile rehabilitation protocols.
Read moreAn open-source toolbox for enhancing the assessment of muscle activation patterns during cyclical movements
Authors:
Gregorio Dotti, Marco Ghislieri, Cristina Castagneri, Valentina Agostini, Marco Knaflitz, Gabriella Balestra and Samanta RosatiJournal:
IOP Physiological MeasurementDOI:
10.1088/1361-6579/ad814fYear:
2024Abstract:
Dynamic muscle activity can be quantitatively and non-invasively investigated during several cyclical movements by acquiring surface electromyographic (sEMG) signals. The accurate temporal analysis of muscle activations is of great importance in several research areas spanning from the assessment of altered muscle activation patterns in orthopaedic and neurological patients to the monitoring of their motor rehabilitation. Several studies have highlighted the challenge of understanding and interpreting muscle activation patterns due to the high cycle-by-cycle variability of the sEMG data. This makes it difficult to interpret results and to use sEMG signals in the clinical practice. To overcome this limitation, specific algorithms are needed to help scientists to easily characterize and assess muscle activation patterns during cyclical movements. In this perspective, CIMAP (Clustering for the Identification of Muscle Activation Patterns) is an open-source Python toolbox based on agglomerative hierarchical clustering that aims at characterizing muscle activation patterns during cyclical movements by grouping movement cycles showing similar muscle activity. From muscle activation intervals to the graphical representation of the agglomerative hierarchical clustering dendrograms, the proposed toolbox offers a complete analysis framework for enabling the assessment muscle activation pattern. The toolbox can be flexibly modified to comply with the necessities of the scientist. CIMAP is addressed to scientists of any programming skill level working in different research areas such as biomedical engineering, robotics, sports, clinics, biomechanics, and neuroscience. CIMAP is freely available on GitHub (https://github.com/Biolab-PoliTO/CIMAP).
Read moreFoot–Floor Contact Sequences: A Metric for Gait Assessment in Parkinson’s Disease after Deep Brain Stimulation
Authors:
Marco Ghislieri, Valentina Agostini, Laura Rizzi, Chiara Fronda, Marco Knaflitz, Michele LanotteJournal:
SensorsDOI:
10.3390/s24206593Year:
2024Abstract:
Digital gait monitoring is increasingly used to assess locomotion and fall risk. The aim of this work is to analyze the changes in the foot–floor contact sequences of Parkinson’s Disease (PD) patients in the year following the implantation of Deep Brain Stimulation (DBS). During their best-ON condition, 30 PD patients underwent gait analysis at baseline (T0), at 3 months after subthalamic nucleus DBS neurosurgery (T1), and at 12 months (T2) after subthalamic nucleus DBS neurosurgery. Thirty age-matched controls underwent gait analysis once. Each subject was equipped with bilateral foot-switches and a 5 min walk was recorded, including both straight-line and turnings. The walking speed, turning time, stride time variability, percentage of atypical gait cycles, stance, swing, and double support duration were estimated. Overall, the gait performance of PD patients improved after DBS, as also confirmed by the decrease in their UPDRS-III scores from 19.4 ± 1.8 to 10.2 ± 1.0 (T0 vs.T2) (p < 0.001). In straight-line walking, the percentages of atypical cycles of PD on the more affected side were 11.1 ± 1.5% (at T0), 3.1 ± 1.5% (at T1), and 5.1 ± 2.4% (at T2), while in controls it was 3.1 ± 1.3% (p < 0.0005). In turnings, this percentage was 13.7 ± 1.1% (at T0), 7.8 ± 1.1% (at T1), and 10.9 ± 1.8% (at T2), while in controls it was 8.1 ± 1.0% (p < 0.001). Therefore, in straight-line walking, the atypical cycles decreased by 72% at T1, and by 54% at T2 (with respect to baseline), while, in turnings, atypical cycles decreased by 43% at T1, and by 20% at T2. The percentage of atypical gait cycles proved an informative digital biomarker for quantifying PD gait changes after DBS, both in straight-line paths and turnings.
Read moreBalance and Muscle Synergies during a Single-Limb Stance Task in Individuals with Chronic Ankle Instability
Authors:
M. Ghislieri, L. Labanca, M. Mosca, L. Bragonzoni, M. Kanflitz & V. AgostiniJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2023.3328933Year:
2023Abstract:
The aim of this study was to investigate balance performance and muscle synergies during a Single-Limb Stance (SLS) task in individuals with Chronic Ankle Instability (CAI) and a group of healthy controls. Twenty individuals with CAI and twenty healthy controls were asked to perform a 30-second SLS task in Open-Eyes (OE) and Closed-Eyes (CE) conditions while standing on a force platform with the injured or the dominant limb, respectively. The activation of 13 muscles of the lower limb, hip, and back was recorded by means of surface electromyography. Balance performance was assessed by identifying the number and the duration of SLS epochs, and the Root-Mean-Square (RMS) in Antero-Posterior (AP) and Medio-Lateral (ML) directions of the body-weight normalized ground reaction forces. The optimal number of synergies, weight vectors, and activation coefficients were also analyzed. CAI group showed a higher number and a shorter duration of SLS epochs and augmented ground reaction force RMS in both AP and ML directions compared to controls. Both groups showed an increase in the RMS in AP and ML forces in CE compared to OE. Both groups showed 4 optimal synergies in CE, while controls showed 5 synergies in OE. CAI showed a significantly higher weight of knee flexor muscles in both OE and CE. In conclusion, muscle synergies analysis provided an in–depth knowledge of motor control mechanisms in CAI individuals. They showed worse balance performance, a lower number of muscle synergies in a CE condition and abnormal knee flexor muscle activation compared to healthy controls.
Read moreMuscle synergies in Parkinson’s disease before and after the deep brain stimulation of the bilateral subthalamic nucleus
Authors:
Marco Ghislieri, Michele Lanotte, Marco Knaflitz, Laura Rizzi, and Valentina AgostiniJournal:
Scientific ReportsDOI:
10.1038/s41598-023-34151-6Year:
2023Abstract:
The aim of this study is to quantitatively assess motor control changes in Parkinson’s disease (PD) patients after bilateral deep brain stimulation of the subthalamic nucleus (STN-DBS), based on a novel muscle synergy evaluation approach. A group of 20 PD patients evaluated at baseline (before surgery, T0), at 3 months (T1), and at 12 months (T2) after STN-DBS surgery, as well as a group of 20 age-matched healthy control subjects, underwent an instrumented gait analysis, including surface electromyography recordings from 12 muscles. A smaller number of muscle synergies was found in PD patients (4 muscle synergies, at each time point) compared to control subjects (5 muscle synergies). The neuromuscular robustness of PD patients—that at T0 was smaller with respect to controls (PD T0: 69.3 ± 2.2% vs. Controls: 77.6 ± 1.8%, p = 0.004)—increased at T1 (75.8 ± 1.8%), becoming not different from that of controls at T2 (77.5 ± 1.9%). The muscle synergies analysis may offer clinicians new knowledge on the neuromuscular structure underlying PD motor types of behavior and how they can improve after electroceutical STN-DBS therapy.
Read moreWearable Inertial Sensors to Assess Standing Balance: A Systematic Review
Authors:
M. Ghislieri, L. Gastaldi, S. Pastorelli, S. Tadano, and V. AgostiniJournal:
SensorsDOI:
10.3390/s19194075Year:
2019Abstract:
Wearable sensors are de facto revolutionizing the assessment of standing balance. The aim of this work is to review the state-of-the-art literature that adopts this new posturographic paradigm, i.e., to analyse human postural sway through inertial sensors directly worn on the subject body. After a systematic search on PubMed and Scopus databases, two raters evaluated the quality of 73 full-text articles, selecting 47 high-quality contributions. A good inter-rater reliability was obtained (Cohen’s kappa = 0.79). This selection of papers was used to summarize the available knowledge on the types of sensors used and their positioning, the data acquisition protocols and the main applications in this field (e.g., “active aging”, biofeedback-based rehabilitation for fall prevention, and the management of Parkinson’s disease and other balance-related pathologies), as well as the most adopted outcome measures. A critical discussion on the validation of wearable systems against gold standards is also presented.
Read moreAn Algorithm for Choosing the Optimal Number of Muscle Synergies during Walking
Authors:
R. Ballarini, M. Ghislieri, M. Knaflitz and V. AgostiniJournal:
SensorsDOI:
10.3390/s21103311Year:
2021Abstract:
In motor control studies, the 90% thresholding of variance accounted for (VAF) is the classical way of selecting the number of muscle synergies expressed during a motor task. However, the adoption of an arbitrary cut-off has evident drawbacks. The aim of this work is to describe and validate an algorithm for choosing the optimal number of muscle synergies (ChoOSyn), which can overcome the limitations of VAF-based methods. The proposed algorithm is built considering the following principles: (1) muscle synergies should be highly consistent during the various motor task epochs (i.e., remaining stable in time), (2) muscle synergies should constitute a base with low intra-level similarity (i.e., to obtain information-rich synergies, avoiding redundancy). The algorithm performances were evaluated against traditional approaches (threshold-VAF at 90% and 95%, elbow-VAF and plateau-VAF), using both a simulated dataset and a real dataset of 20 subjects. The performance evaluation was carried out by analyzing muscle synergies extracted from surface electromyographic (sEMG) signals collected during walking tasks lasting 5 min. On the simulated dataset, ChoOSyn showed comparable performances compared to VAF-based methods, while, in the real dataset, it clearly outperformed the other methods, in terms of the fraction of correct classifications, mean error (ME), and root mean square error (RMSE). The proposed approach may be beneficial to standardize the selection of the number of muscle synergies between different research laboratories, independent of arbitrary thresholds
Read moreAtypical Gait Cycles in Parkinson’s Disease
Authors:
M. Ghislieri, V. Agostini, L. Rizzi, M. Knaflitz, and M. LanotteJournal:
SensorsDOI:
10.3390/s21155079Year:
2021Abstract:
It is important to find objective biomarkers for evaluating gait in Parkinson’s Disease (PD), especially related to the foot and lower leg segments. Foot-switch signals, analyzed through Statistical Gait Analysis (SGA), allow the foot-floor contact sequence to be characterized during a walking session lasting five-minutes, which includes turnings. Gait parameters were compared between 20 PD patients and 20 age-matched controls. PDs showed similar straight-line speed, cadence, and double-support compared to controls, as well as typical gait-phase durations, except for a small decrease in the flat-foot contact duration (−4% of the gait cycle, p = 0.04). However, they showed a significant increase in atypical gait cycles (+42%, p = 0.006), during both walking straight and turning. A forefoot strike, instead of a “normal” heel strike, characterized the large majority of PD’s atypical cycles, whose total percentage was 25.4% on the most-affected and 15.5% on the least-affected side. Moreover, we found a strong correlation between the atypical cycles and the motor clinical score UPDRS-III (r = 0.91, p = 0.002), in the subset of PD patients showing an abnormal number of atypical cycles, while we found a moderate correlation (r = 0.60, p = 0.005), considering the whole PD population. Atypical cycles have proved to be a valid biomarker to quantify subtle gait dysfunctions in PD patients
Read moreEvaluation of Muscle Function by Means of a Muscle-Specific and a Global Index
Authors:
S. Rosati, M. Ghislieri, G. Dotti, D. Fortunato, V. Agostini, M.Knaflitz, and G. BalestraJournal:
SensorsDOI:
10.3390/s21217186Year:
2021Abstract:
Gait analysis applications in clinics are still uncommon, for three main reasons: (1) the considerable time needed to prepare the subject for the examination; (2) the lack of user-independent tools; (3) the large variability of muscle activation patterns observed in healthy and pathological subjects. Numerical indices quantifying the muscle coordination of a subject could enable clinicians to identify patterns that deviate from those of a reference population and to follow the progress of the subject after surgery or completing a rehabilitation program. In this work, we present two user-independent indices. First, a muscle-specific index (MFI) that quantifies the similarity of the activation pattern of a muscle of a specific subject with that of a reference population. Second, a global index (GFI) that provides a score of the overall activation of a muscle set. These two indices were tested on two groups of healthy and pathological children with encouraging results. Hence, the two indices will allow clinicians to assess the muscle activation, identifying muscles showing an abnormal activation pattern, and associate a functional score to every single muscle as well as to the entire muscle set. These opportunities could contribute to facilitating the diffusion of surface EMG analysis in clinics
Read moreLong short-term memory (LSTM) recurrent neural network for muscle activity detection
Authors:
M. Ghislieri, G. L. Cerone, M. Knaflitz, & V. AgostiniJournal:
Journal of NeuroEngineering and RehabilitationDOI:
10.1186/s12984-021-00945-wYear:
2021Abstract:
Background
The accurate temporal analysis of muscle activation is of great interest in many research areas, spanning from neurorobotic systems to the assessment of altered locomotion patterns in orthopedic and neurological patients and the monitoring of their motor rehabilitation. The performance of the existing muscle activity detectors is strongly affected by both the SNR of the surface electromyography (sEMG) signals and the set of features used to detect the activation intervals. This work aims at introducing and validating a powerful approach to detect muscle activation intervals from sEMG signals, based on long short-term memory (LSTM) recurrent neural networks.
Methods
First, the applicability of the proposed LSTM-based muscle activity detector (LSTM-MAD) is studied through simulated sEMG signals, comparing the LSTM-MAD performance against other two widely used approaches, i.e., the standard approach based on Teager–Kaiser Energy Operator (TKEO) and the traditional approach, used in clinical gait analysis, based on a double-threshold statistical detector (Stat). Second, the effect of the Signal-to-Noise Ratio (SNR) on the performance of the LSTM-MAD is assessed considering simulated signals with nine different SNR values. Finally, the newly introduced approach is validated on real sEMG signals, acquired during both physiological and pathological gait. Electromyography recordings from a total of 20 subjects (8 healthy individuals, 6 orthopedic patients, and 6 neurological patients) were included in the analysis.
Results
The proposed algorithm overcomes the main limitations of the other tested approaches and it works directly on sEMG signals, without the need for background-noise and SNR estimation (as in Stat). Results demonstrate that LSTM-MAD outperforms the other approaches, revealing higher values of F1-score (F1-score > 0.91) and Jaccard similarity index (Jaccard > 0.85), and lower values of onset/offset bias (average absolute bias < 6 ms), both on simulated and real sEMG signals. Moreover, the advantages of using the LSTM-MAD algorithm are particularly evident for signals featuring a low to medium SNR.
Conclusions
The presented approach LSTM-MAD revealed excellent performances against TKEO and Stat. The validation carried out both on simulated and real signals, considering normal as well as pathological motor function during locomotion, demonstrated that it can be considered a powerful tool in the accurate and effective recognition/distinction of muscle activity from background noise in sEMG signals.
Read moreMuscle activations during functional tasks in individuals with chronic ankle instability: a systematic review of electromyographical studies
Authors:
L. Labanca, M. Mosca, M. Ghislieri, V. Agostini, M. Knaflitz, & M. G. BenedettiJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2021.09.182Year:
2021Abstract:
Background
It has been reported that individuals with chronic ankle instability (CAI) show motor control abnormalities. The study of muscle activations by means of surface electromyography (sEMG) plays a key role in understanding some of the features of movement abnormalities.
Research question
Do common sEMG activation abnormalities and strategies exists across different functional movements?
Methods
Literature review was conducted on PubMed, Web-of-Science and Cochrane databases. Studies published between 2000 and 2020 that assessed muscle activations by means of sEMG during any type of functional task in individuals with CAI, and used healthy individuals as controls, were included. Methodological quality was assessed using the modified Downs&Black checklist. Since the methodologies of different studies were heterogeneous, no meta-analysis was conducted.
Results
A total of 63 articles investigating muscle activations during gait, running, responses to perturbations, landing and hopping, cutting and turning; single-limb stance, star excursion balance task, forward lunges, ball-kicking, y-balance test and single-limb squatting were considered. Individuals with CAI showed a delayed activation of the peroneus longus in response to sudden inversion perturbations, in transitions between double- and single-limb stance, and in landing on unstable surfaces. Apparently, while walking on ground there are no differences between CAI and controls, walking on a treadmill increases the variability of muscles activations, probably as a “safety strategy” to avoid ankle inversion. An abnormal activation of the tibialis anterior was observed during a number of tasks. Finally, hip/spine muscles were activated before ankle muscles in CAI compared to controls.
Conclusion
Though the methodology of the studies herein considered is heterogeneous, this review shows that the peroneal and tibialis anterior muscles have an abnormal activation in CAI individuals. These individuals also show a proximal muscle activation strategy during the performance of balance challenging tasks. Future studies should investigate whole-body muscle activation abnormalities in CAI individuals.
Muscle synergies for the control of single-limb stance with and without visual information in young individuals
Authors:
L. Labanca, M. Ghislieri, M. Knaflitz, G. Barone, L. Bragonzoni, V. Agostini & M. G. BenedettiJournal:
BMC Sports Science, Medicine and RehabilitationDOI:
10.1186/s13102-021-00392-zYear:
2021Abstract:
Purpose
Single-limb stance is a demanding postural task featuring a high number of daily living and sporting activities. Thus, it is widely used for training and rehabilitation, as well as for balance assessment. Muscle activations around single joints have been previously described, however, it is not known which are the muscle synergies used to control posture and how they change between conditions of normal and lack of visual information.
Methods
Twenty-two healthy young participants were asked to perform a 30 s single-limb stance task in open-eyes and closed-eyes condition while standing on a force platform with the dominant limb. Muscle synergies were extracted from the electromyographical recordings of 13 muscles of the lower limb, hip, and back. The optimal number of synergies, together with the average recruitment level and balance control strategies were analyzed and compared between the open- and the closed-eyes condition.
Results
Four major muscle synergies, two ankle-dominant synergies, one knee-dominant synergy, and one hip/back-dominant synergy were found. No differences between open- and closed-eyes conditions were found for the recruitment level, except for the hip/back synergy, which significantly decreased (p = 0.02) in the closed-eyes compared to the open-eyes condition. A significant increase (p = 0.03) of the ankle balance strategy was found in the closed-eyes compared to the open-eyes condition.
Conclusion
In healthy young individuals, single-limb stance is featured by four major synergies, both in open- and closed-eyes condition. Future studies should investigate muscle synergies in participants with other age groups, as well as pathological conditions.
Read moreStatistical Gait Analysis Based on Surface Electromyography
Authors:
Agostini, V., Ghislieri, M., Rosati, S., Balestra, B., Dotti, G., & Knaflitz, M.Journal:
Medicine-Based Informatics and EngineeringDOI:
10.1007/978-3-030-87845-0_2Year:
2021Abstract:
To help neurologists, physicians, and physical therapists in the management of patients with altered locomotion patterns, it is of the uttermost importance relying on accurate measurements of gait. Gait analysis becomes even more informative if the electrical activity of muscles is recorded, non-invasively, during the dynamic task of walking, through surface electromyography (sEMG) probes. However, sEMG signals must be processed through advanced techniques to obtain reliable results, easily interpretable by healthcare practitioners. Indeed, the study of how muscles are activated during natural walking (in unconstrained environments) is complex for several reasons, including a high stride-to-stride variability, even more pronounced in pathological subjects. On the other hand, it is crucial to provide clinicians with aggregated information relying on validated parameters and easily usable representations that can be effectively included in clinical reports. This chapter is aimed at introducing: (1) Statistical Gait Analysis (SGA) to automatically analyze hundreds of gait cycles collected during a physiological or pathological walk lasting several minutes, (2) the extraction of principal and secondary muscle activations to obtain consistent clinical indexes, (3) the extraction of “muscle synergies” to quantitatively study motor control strategies. Each of these techniques are based on state-of-the-art processing algorithms of the sEMG signal. A brief review of the recent literature published in this field will be presented and discussed.
Read moreMuscle synergies extracted using principal activations: improvement of robustness and interpretability
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2020.2965179Year:
2020Abstract:
The muscle synergy theory has been widely used to assess the modular organization of the central nervous system (CNS) during human locomotion. The pre-processing approach applied to the surface electromyographic (sEMG) signals influences the extraction of muscle synergies. The aim of this contribution is to assess the improvements in muscle synergy extraction obtained by using an innovative pre-processing approach. We evaluate the improvement in terms of the possible variation in the number of muscle synergies, of the intra-subject consistency, of the robustness, and of the interpretability of the results. The pre-processing approach presented in this paper is based on the extraction of the muscle principal activations (muscle activations strictly necessary to accomplish a specific biomechanical task) from the original sEMG signals, to then obtain muscle synergies using principal activations only. The results herein presented show that the application of this novel approach for the extraction of the muscle synergies provides a more robust and easily interpretable description of the modular organization of the CNS with respect to the standard pre-processing approach.
Read moreMuscle Synergy Assessment During Single-Leg Stance
Authors:
M. Ghislieri, M. Knaflitz, L. Labanca, G. Barone, L. Bragonzoni, M. G. Benedetti, and V. AgostiniJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2020.3030847Year:
2020Abstract:
In the study of muscle synergies during the maintenance of single-leg stance there are several methodological issues that must be taken into account before muscle synergy extraction. In particular, it is important to distinguish between epochs of surface electromyography (sEMG) signals corresponding to “well-balanced” and “unbalanced” single-leg stance, since different motor control strategies could be used to maintain balance. The aim of this work is to present and define a robust procedure to distinguish between “well-balanced” and “unbalanced” single-leg stance to be chosen as input for the algorithm used to extract muscle synergies. Our results demonstrate that the proposed approach for the selection of sEMG epochs relative to “well-balanced” and “unbalanced” single-leg stance is robust with respect to the selection of the segmentation threshold, revealing a high consistency in the number of muscle synergies and high similarity among the weight vectors (correlation values range from 0.75 to 0.97). Moreover, differences in terms of average recruitment levels and balance control strategies were detected, suggesting a slightly different modular organization between “well-balanced” and “unbalanced” single-leg stance. In conclusion, this approach can be successfully used as a pre-processing step before muscle synergy extraction, allowing for a better assessment of motor control strategies during the single-leg stance task.
Read moreAsymmetry Index in Muscle Activations
Authors:
Castagneri, C., Agostini, V., Rosati, S., Balestra, G., Knaflitz, M.Journal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2019.2903687Year:
2019 Read moreHow to improve robustness in muscle synergy extraction
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856438Year:
2019Abstract:
The muscle synergy theory was widely used in literature to assess the modular organization of the central nervous system (CNS) during human locomotion. The extraction of muscle synergies may be strongly influenced by the preprocessing techniques applied to surface electromyographic (sEMG) signals. The aim of this contribution is to assess the robustness improvement in muscle synergy extraction obtained using an innovative pre-processing technique with respect to the standard procedure. The new pre-processing technique that we propose is based on the extraction of principal muscle activation intervals (necessary to accomplish a specific biomechanical task during gait) from the original sEMG signals, discarding the secondary muscle activation intervals (activations that occur only in some strides with auxiliary functions). Results suggest that the extraction of the principal activation intervals from sEMG provide a more consistent and stable description of the modular organization of the CNS with respect to the standard pre-processing procedure.
Read moreThe Effect of Signal-to-Noise Ratio on Muscle Synergy Extraction
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
2018 IEEE Life Sciences Conference (LSC)DOI:
10.1109/LSC.2018.8572075Year:
2018Abstract:
The modular organization of the central nervous system (CNS) during motor tasks was widely assessed by means of muscle synergies. The aim of this work was to assess the impact of the Signal-to-Noise Ratio (SNR) on muscle synergies extracted from synthetic surface electromyographic (sEMG) signals that simulate the muscle activity of the lower limb during walking. To evaluate the effect of the SNR, the similarity between the weights vectors and the activation coefficients extracted from real sEMG signals and from simulated sEMG signals at different values of SNR was computed. Results reveal that muscle synergy extraction is strongly dependent upon the quality of the sEMG signals simulated.
Read moreMuscle activation patterns during gait: A hierarchical clustering analysis
Authors:
S. Rosati, V. Agostini, M. Knaflitz and G. BalestraJournal:
Biomedical Signal Processing and ControlDOI:
10.1016/j.bspc.2016.09.017Year:
2017 Read moreMuscle activation patterns during gait: A hierarchical clustering analysis
Authors:
Rosati, S., Agostini, V., Knaflitz, M., Balestra, G.Journal:
Biomedical Signal Processing and ControlDOI:
10.1016/j.bspc.2016.09.017Year:
2017 Read moreThe role of central vision in posture: Postural sway adaptations in Stargardt patients
Authors:
V. Agostini, A. Sbrollini, C. Cavallini, A. Busso, G. Pignata and M. KnaflitzJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2015.10.003Year:
2016Abstract:
The role of central and peripheral vision in the maintenance of upright stance is debated in literature. Stargardt disease causes visual deficits affecting the central field, but leaving unaltered a patient’s peripheral vision. Hence, the study of this rare pathology gives the opportunity to selectively investigate the role of central vision in posture. Postural sway in quiet stance was analyzed in 10 Stargardt patients and 10 control subjects, in three different conditions: (1) eyes closed, (2) eyes open, gazing at a fixed target, and (3) eyes open, tracking a moving target. Stargardt patients outperformed controls in the condition with eyes closed, showing a reduced root mean square (RMS) of the medio-lateral COP displacement, while their performance was not significantly different from controls in the antero-posterior direction. There were no significant differences between patients and controls in open eyes conditions. These results suggest that Stargardt patients adapted to a different visual-somatosensory integration, relying less on vision, especially in the medio-lateral direction. Hence, the central vision seems to affect mostly the medio-lateral direction of postural sway. This finding supports the plausibility of the “functional sensitivity hypothesis”, that assigns complementary roles to central and peripheral vision in the control of posture.
Read moreDoes texting while walking really affect gait in young adults?
Authors:
V. Agostini, F. Lo Fermo, G. Massazza and M. KnaflitzJournal:
Journal of NeuroEngineering and RehabilitationDOI:
10.1186/s12984-015-0079-4Year:
2015Abstract:
Background: Texting on a smartphone while walking has become a customary task among young adults. In recent literature many safety concerns on distracted walking have been raised. It is often hypothesized that the allocation of attentional resources toward a secondary task can influence dynamic stability. In the double task of walking and texting it was found that gait speed is reduced, but there is scarce evidence of a modified motor control strategy compromising stability. The aim of this study is twofold: 1) to comprehensively examine the gait modifications occurring when texting while walking, including the study of the lower limb muscle activation patterns, 2) to specifically assess the co-contraction of ankle antagonist muscles. We hypothesized that texting while walking increases co-contractions of ankle antagonist muscles when the body weight is transferred from one lower limb to the other, to improve the distal motor control and joint stabilization.
Methods: From the gait data collected during an instrumented walk lasting 3 min, we calculated the spatio-temporal parameters, the ankle and knee kinematics, the muscle activation patterns of tibialis anterior, gastrocnemius lateralis, peroneus longus, rectus femoris, and lateral hamstrings, and the co-contraction (occurrence and duration) of the ankle antagonist muscles (tibialis anterior and gastrocnemius lateralis), bilaterally.
Results: Young adults showed, overall, small gait modifications that could be mainly ascribable to gait speed reduction and a modified body posture due to phone handling. We found no significant alterations of ankle and knee kinematics and a slightly delayed activation onset of the left gastrocnemius lateralis. However, we found an increased co-contraction of tibialis anterior and gastrocnemius lateralis, especially during mid-stance. Conversely, we found a reduced co-contraction during terminal stance.
Conclusions: Our results suggest that, in young adults, there is an adjustment of the motor control strategy aimed at increasing ankle joint stability in a specific and “critical” phase of the gait cycle, when the body weight is transferred from one leg to the other.
Read moreInstrumented Gait Analysis for an Objective Pre-/Postassessment of Tap Test in Normal Pressure Hydrocephalus
Authors:
V. Agostini, M. Lanotte, M. Carlone, M. Campagnoli, I. Azzolin, R. Scarafia, G. Massazza, M. KnaflitzJournal:
Archives of Physical Medicine and RehabilitationDOI:
10.1016/j.apmr.2015.02.014Year:
2015Abstract:
Objective
To present an objective method to evaluate gait improvements after a tap test in idiopathic normal pressure hydrocephalus (INPH).
Design
Retrospective analysis of gait data.
Setting
Public tertiary care center, day hospital. The gait analysis was performed before and 2 to 4 hours after the tap test.
Participants
Participants included patients with INPH (n=60) and age- and sex-matched controls (n=50; used to obtain reference intervals). From an initial referred sample of 79 patients (N=79), we excluded those unable to walk without walking aids (n=9) and those with incomplete (pre-/posttap test) gait data (n=10). Thirteen out of 60 patients were shunted and then reappraised after 6 months.
Interventions
Not applicable.
Main Outcome Measures
Mahalanobis distance from controls, before and after the tap test. Eleven gait parameters were combined in a single quantitative score. Walking velocity was also evaluated because it is frequently used in tap test assessment.
Results
Patients were classified into 2 groups: tap test responders (n=22, 9 of them were shunted) and not suitable for shunt (n=38, 4 of them were shunted). In the tap test responders group, 9 out of 9 patients improved after shunt. In the not suitable for shunt group, 3 out of 4 patients did not improve. Gait velocity increased after the tap test in 53% of responders and in 37% of patients not suitable for shunt.
Conclusions
The new method is applicable to clinical practice and allows for selecting tap test responders in an objective way, quantifying the improvements. Our results suggest that gait velocity alone is not sufficient to reliably assess tap test effects.
Gait parameters and muscle activation patterns at 3, 6 and 12 months after total hip arthroplasty
Authors:
V. Agostini, D. Ganio, K. Facchin, L. Cane, S. M. Carneiro and M. KnaflitzJournal:
The Journal of ArthroplastyDOI:
10.1016/j.arth.2013.12.018Year:
2014 Read morePostural sway in volleyball players
Authors:
V. Agostini, E. Chiaramello, L. Canavese, C. Bredariol and M. KnaflitzJournal:
Human Movement ScienceDOI:
10.1016/j.humov.2013.01.002Year:
2013Abstract:
The aim of this work was to analyze the postural sway of volleyball players in bipedal quiet stance. The center of pressure (CoP) was measured in 46 athletes and 42 non-athlete controls. Each subject was tested in 10 different conditions, 5 with their eyes open and 5 with their eyes closed. Volleyball players showed greater CoP ellipses, suggesting a different model of sensory integration in their postural stability. A multivariate approach to data analysis demonstrated that the postural sway of the two groups was different when the subjects kept their eyes open, but it was not with visual deprivation. This could partially be explained by the better ‘dynamic’ visual acuity of athletes, since possible (‘static’) refractive errors were corrected for both groups. Furthermore, we expected that national players, engaged in more intensive training programs, were more different from controls than regional ones, and that defensive players, whose role requires the quickest reaction times, were more different from controls than hitters. Our results confirmed these hypothesis. The protocol presented might be useful to assess the efficacy of intensive sport training programs and/or to select elite players with an aptitude for a specific playing position.
Read moreSegmentation and classification of gait cycles
Authors:
V. Agostini, G. Balestra, M. KnaflitzJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2013.2291907Year:
2013 Read morePostural control after traumatic brain injury in patients with neuro-ophthalmic deficits
Authors:
V. Agostini, E. Chiaramello, C. Bredariol, C. Cavallini and M. KnaflitzJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2011.05.008Year:
2011Abstract:
Postural instability is a common and devastating consequence of traumatic brain injury (TBI). The majority of TBI patients also suffer from neuro-ophthalmic deficits that can be an important contributing element to their sensation of vertigo and dizziness. Static posturography aims at the objective evaluation of patient balance impairment, but is usually affected by large inter- and intra-subject variability. Here we propose a protocol based on 10 randomized trials stimulating in different ways the visual and vestibular systems. Due to its completeness, our protocol highlights the specific residual difficulties of each patient in the various conditions. In this way, it was possible to evidence significant balance abnormalities in TBI patients with respect to controls. Moreover, by means of a multivariate analysis we were able to discriminate different levels of residual neuro-ophthalmic impairment.
Read moreNormative EMG activation patterns of school-age children during gait
Authors:
V. Agostini, A. Nascimbeni, A. Gaffuri, P. Imazio, M.G. Benedetti and M. KnaflitzJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2010.06.024Year:
2010 Read moreMedical Device Software
An Approach Based on Process Modeling for Implementing a Health Information Technology in Clinical Practice
Authors:
G.M. Zaccaria; S. Rosati; M. Zema; V. Agostini; G. BalestraJournal:
Journal of Medical Imaging and Health InformaticsDOI:
10.1166/jmihi.2018.2353Year:
2018Abstract:
The introduction of a new Health Information Technology (HIT) in a healthcare context is a very complex process. The aim of this study is to propose a completely original approach for the implementation a new HIT in a healthcare facility or department. This novel approach is made of four steps and based on process modeling. The first step is the identification of all the stakeholders involved. The second step consists in performing a detailed description of all clinical and administrative processes that will use the new HIT in order to understand how people, resources and documents interact among them. The third step allows the analysis of the HIT functionalities in order to highlight potential problems or risks that could emerge during its daily usage and guarantee its interoperability with other software. The fourth step concerns the construction of an adoption plan, in order to avoiding sharp transitions. A set of tools were associated to each step to guarantee a correct design and implementation. An application concerning the implementation of a new commercial HIT for Computerized Provider Order Entry (CPOE) in the oncology department of a large Italian hospital is reported as an example of the proposed approach. Furthermore, the user satisfaction about the introduction of the new CPOE in the oncology department was evaluated by means of a set of questionnaires. A positive evaluation of the process emerged from this analysis, confirming the goodness of the proposed approach. Moreover, the questionnaires results showed a high level of user satisfaction.
Read moreDeveloping medical device software in compliance with regulations
Authors:
M. Zema; S. Rosati; V. Gioia; M. Knaflitz; G. BalestraJournal:
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2015.7318614Year:
2015Abstract:
In the last decade, the use of information technology (IT) in healthcare has taken a growing role. In fact, the adoption of an increasing number of computer tools has led to several benefits related to the process of patient care and allowed easier access to social and health care resources. At the same time this trend gave rise to new challenges related to the implementation of these new technologies. Software used in healthcare can be classified as medical devices depending on the way they are used and on their functional characteristics. If they are classified as medical devices they must satisfy specific regulations. The aim of this work is to present a software development framework that can allow the production of safe and high quality medical device software and to highlight the correspondence between each software development phase and the appropriate standard and/or regulation.
Read moreModelling and analysis of four telemedicine Italian experiences
Authors:
S. Rosati; M. Zema; C. Castagneri; F. Marchetti; G. BalestraJournal:
2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2017.8037398Year:
2017Abstract:
In the last 10 years the European population aged 65 years and over grew of 2.3%, with Italy having the highest share of elderly persons in the total population. OPLON (OPportunities for active and healthy LONgevity) is a project supported by the Italian Ministry of Education, Universities, and Research aiming to identify and prevent frailty and to improve the life quality of elderly subjects. The main goal of OPLON is to develop a “Care&Cure” model for the management of subjects with different morbidities and co-morbidities, adaptable to the subject’s risk level and to the regional contexts. In this study we analyzed four Italian telemedicine experiences addressed to chronic, geriatric or partially self-sufficient subjects. Each of them was exhaustively described by means of three process modelling tools (synopsis, workflow and swimlane activity diagrams). Starting from this analysis, we defined a general model of tele-monitoring and tele-assistance of frail and pre-frail people with different needs and pathologies. The proposed model was characterized by three macro processes (enrollment, assessment and assistance) and four groups of actors (patient, general practitioner/specialist physician, multidisciplinary team, and healthcare professionals). Combining this model with a detailed analysis of regulations and legislations in force both at local and national level, it will be possible to design the complete and efficient “Care&Cure” model.
Read moreModels of care processes: Process modeling methods and applications
Authors:
S. Rosati; M. Zema; B. BalestraJournal:
E-Health - Medicina Digitale (Book chapter)DOI:
-Year:
2017 Read moreMedical Image Analysis Using Innovative Intelligent Systems
Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans
Authors:
K. M. Meiburger, F. Marzola, G. Zahnd, F. Faita, C. P. Loizou, N. Lainé, C. Carvalho, D. A. Steinman, L. Gibello, R.M. Bruno, R. Clarenbach, M. Francesconi, A. N. Nicolaides, H. Liebgott, A. Campilho, R. Ghotbi, E. Kyriacou, N. Navab, M. Griffin, A. G. PaJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2022.105333Year:
2022Abstract:
After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on U-Net convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 μm vs. 160 ± 140 μm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 μm, 143 ± 118 μm and 139 ± 136 μm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis (https://doi.org/10.17632/m7ndn58sv6.1).
Read moreIntegration of Deep Learning and Active Shape Models for More Accurate Prostate Segmentation in 3D MR Images
Authors:
Massimo Salvi, Bruno De Santi, Bianca Pop, Martino Bosco, Valentina Giannini, Daniele Regge, Filippo Molinari, and Kristen M. MeiburgerJournal:
Journal of ImagingDOI:
https://doi.org/10.3390/jimaging8050133Year:
2022Abstract:
Magnetic resonance imaging (MRI) has a growing role in the clinical workup of prostate cancer. However, manual three-dimensional (3D) segmentation of the prostate is a laborious and time-consuming task. In this scenario, the use of automated algorithms for prostate segmentation allows us to bypass the huge workload of physicians. In this work, we propose a fully automated hybrid approach for prostate gland segmentation in MR images using an initial segmentation of prostate volumes using a custom-made 3D deep network (VNet-T2), followed by refinement using an Active Shape Model (ASM). While the deep network focuses on three-dimensional spatial coherence of the shape, the ASM relies on local image information and this joint effort allows for improved segmentation of the organ contours. Our method is developed and tested on a dataset composed of T2-weighted (T2w) MRI prostatic volumes of 60 male patients. In the test set, the proposed method shows excellent segmentation performance, achieving a mean dice score and Hausdorff distance of 0.851 and 7.55 mm, respectively. In the future, this algorithm could serve as an enabling technology for the development of computer-aided systems for prostate cancer characterization in MR imaging.
Read moreA hybrid deep learning approach for gland segmentation in prostate histopathological images
Authors:
Salvi, M., Bosco, M., Molinaro, L., Gambella, A., Papotti, M., Acharya, U. R., & Molinari, F.Journal:
Artificial Intelligence in MedicineDOI:
10.1016/j.artmed.2021.102076Year:
2021 Read moreAutomatic Segmentation and Classification Methods Using Optical Coherence Tomography Angiography (OCTA): A Review and Handbook
Authors:
Kristen M. Meiburger, Massimo Salvi, Giulia Rotunno, Wolfgang Drexler and Mengyang LiuJournal:
Applied SciencesDOI:
10.3390/app11209734Year:
2021Abstract:
Carotid Ultrasound Boundary Study (CUBS): An Open Multicenter Analysis of Computerized Intima–Media Thickness Measurement Systems and Their Clinical Impact
Authors:
Kristen M.Meiburger, Guillaume Zahnd, Francesco Faita, Christos P. Loizou, Catarina Carvalho, David A. Steinman, Lorenzo Gibello, Rosa Maria Bruno, Francesco Marzola, Ricarda Clarenbach, Martina Francesconi, Andrew N. Nicolaides, Aurelio Campilho, Reza GhJournal:
Ultrasound in Medicine and BiologyDOI:
10.1016/j.ultrasmedbio.2021.03.022Year:
2021Abstract:
Common carotid intima–media thickness (CIMT) is a commonly used marker for atherosclerosis and is often computed in carotid ultrasound images. An analysis of different computerized techniques for CIMT measurement and their clinical impacts on the same patient data set is lacking. Here we compared and assessed five computerized CIMT algorithms against three expert analysts’ manual measurements on a data set of 1088 patients from two centers. Inter- and intra-observer variability was assessed, and the computerized CIMT values were compared with those manually obtained. The CIMT measurements were used to assess the correlation with clinical parameters, cardiovascular event prediction through a generalized linear model and the Kaplan–Meier hazard ratio. CIMT measurements obtained with a skilled analyst’s segmentation and the computerized segmentation were comparable in statistical analyses, suggesting they can be used interchangeably for CIMT quantification and clinical outcome investigation. To facilitate future studies, the entire data set used is made publicly available for the community at http://dx.doi.org/10.17632/fpv535fss7.1.
Read moreChanges in supramaximal M-wave amplitude at different regions of biceps brachii following eccentric exercise of the elbow flexors
Authors:
Hélio V. Cabral, Kristen M. Meiburger, Liliam F. de Oliveira, Taian M. VieiraJournal:
European Journal of Applied PhysiologyDOI:
https://doi.org/10.1007/s00421-020-04520-4Year:
2021 Read moreDeep learning segmentation of transverse musculoskeletal ultrasound images for neuromuscular disease assessment
Authors:
Francesco Marzola, Nens van Alfen, Jonne Doorduin, Kristen M. MeiburgerJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2021.104623Year:
2021Abstract:
Ultrasound imaging is a patient-friendly and robust technique for studying physiological and pathological muscles. An automatic deep learning (DL) system for the analysis of ultrasound images could be useful to support an expert operator, allowing the study of large datasets requiring less human interaction. The purpose of this study is to present a deep learning algorithm for the cross-sectional area (CSA) segmentation in transverse musculoskeletal ultrasound images, providing a quantitative grayscale analysis which is useful for studying muscles, and to validate the results in a large dataset. The dataset included 3917 images of biceps brachii, tibialis anterior and gastrocnemius medialis acquired on 1283 subjects (mean age 50 ± 21 years, 729 male). The algorithm was based on multiple deep-learning architectures, and its performance was compared to a manual expert segmentation. We compared the mean grayscale value inside the automatic and manual CSA using Bland-Altman plots and a correlation analysis. Classification in healthy and abnormal muscles between automatic and manual segmentation were compared using the grayscale value z-scores. In the test set, a Precision of 0.88 ± 0.12 and a Recall of 0.92 ± 0.09 was achieved. The network segmentation performance was slightly less in abnormal muscles, without a loss of discrimination between healthy and abnormal muscle images. Bland-Altman plots showed no clear trend in the error distribution and the two readings have a 0.99 Pearson’s correlation coefficient (p < 0.001, test set). The ICC(A, 1) calculated between the z-score readings was 0.99. The algorithm achieves robust CSA segmentation performance and gives mean grayscale level information comparable to a manual operator. This could provide a helpful tool for clinicians in neuromuscular disease diagnosis and follow-up. The entire dataset and code are made available for the research community.
Read moreDiagnostic Value of Conventional PET Parameters and Radiomic Features Extracted from 18F-FDG-PET/CT for Histologic Subtype Classification and Characterization of Lung Neuroendocrine Neoplasms
Authors:
Philippe Thuillier,Virginia Liberini,Osvaldo Rampado, Elena Gallio,Bruno De Santi, Francesco Ceci, Jasna Metovic, Mauro Papotti, Marco Volante, Filippo Molinari, Désirée DeandreisJournal:
BiomedicinesDOI:
10.3390/biomedicines9030281Year:
2021 Read moreHistopathological classification of canine cutaneous round cell tumors using deep learning: a multi-center study
Authors:
Salvi, M., Molinari, F., Iussich, S., Muscatello, L. V., Pazzini, L., Benali, S., Banco, B., Abramo, F., De Maria, R., & Aresu, L.Journal:
Frontiers in Veterinary ScienceDOI:
10.3389/fvets.2021.640944Year:
2021 Read moreImpact of segmentation and discretization on radiomic features in 68Ga-DOTA-TOC PET/CT images of neuroendocrine tumor
Authors:
Virginia Liberini, Bruno De Santi, Osvaldo Rampado, Elena Gallio, Beatrice Dionisi, Francesco Ceci, Giulia Polverari, Philippe Thuillier, Filippo Molinari & Désirée DeandreisJournal:
European Journal of Nuclear Medicine and Molecular Imaging PhysicsDOI:
10.1186/s40658-021-00367-6Year:
2021 Read moreImpact of stain normalization and patch selection on the performance of convolutional neural networks in histological breast and prostate cancer classification
Authors:
Salvi, M., Molinari, F., Acharya, U. R., Molinaro, L., & Meiburger, K. M.Journal:
Computer Methods and Programs in Biomedicine UpdateDOI:
10.1016/j.cmpbup.2021.100004Year:
2021 Read moreThe impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis
Authors:
Salvi, M., Acharya, U. R., Molinari, F., & Meiburger, K. M.Journal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2020.104129Year:
2021 Read moreThe Role in Teledermoscopy of an Inexpensive and Easy-to-Use Smartphone Device for the Classification of Three Types of Skin Lesions Using Convolutional Neural Networks
Authors:
Federica Veronese, Francesco Branciforti, Elisa Zavattaro,Vanessa Tarantino,Valentina Romano, Kristen M. Meiburger, Massimo Salvi, Silvia Seoni, and Paola SavoiaJournal:
DiagnosticsDOI:
10.3390/diagnostics11030451Year:
2021 Read moreA Convolutional Neural Network based system for Colorectal cancer segmentation on MRI images
Authors:
J. Panic; A. Defeudis; S. Mazzetti; S. Rosati; G. Giannetto; L. Vassallo; D. Regge; G. Balestra; V. GianniniJournal:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)DOI:
10.1109/EMBC44109.2020.9175804Year:
2020Abstract:
The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.
Read moreAutomatic Dynamic Range Estimation for Ultrasound Image Visualization and Processing
Authors:
Kristen M. Meiburger, Silvia Seoni, Giulia MatroneJournal:
2020 IEEE International Ultrasonics Symposium (IUS)DOI:
10.1109/IUS46767.2020.9251470Year:
2020 Read moreAutomatic Optic Nerve Measurement: A New Tool to Standardize Optic Nerve Assessment in Ultrasound B-Mode Images
Authors:
Kristen M. Meiburger, Andrea Naldi, Nicola Michielli, Lorenzo Coppo,, Klaus Fassbender, Filippo Molinari, Piergiorgio LochnerJournal:
Ultrasound in Medicine & BiologyDOI:
10.1016/j.ultrasmedbio.2020.01.034Year:
2020 Read moreAutomatic segmentation of ultrasound images of gastrocnemius medialis with different echogenicity levels using convolutional neural networks
Authors:
Francesco Marzola; Nens van Alfen; Massimo Salvi; Bruno De Santi; Jonne Doorduin; Kristen M. MeiburgerJournal:
2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)DOI:
10.1109/EMBC44109.2020.9176343Year:
2020 Read moreComparison of different classifiers to recognize active bone marrow from CT images
Authors:
Rosati, S., Franco, P., Fiandra, C., Arcadipane, F., Silvetti, P., Gallio, E., Panic, J., Ricardi, U., Balestra, G.Journal:
IEEE Medical Measurements and Applications, MeMeA 2020 - Conference ProceedingsDOI:
10.1109/MeMeA49120.2020.9137173Year:
2020 Read moreKarpinski Score under Digital Investigation: A Fully Automated Segmentation Algorithm to Identify Vascular and Stromal Injury of Donors’ Kidneys
Authors:
Salvi, M., Mogetta, A., Meiburger, K. M., Gambella, A., Molinaro, L., Barreca, A., Papotti M., & Molinari, F.Journal:
ElectronicsDOI:
10.3390/electronics9101644Year:
2020 Read moreRadiomics predicts response of individual HER2-amplified colorectal cancer liver metastases in patients treated with HER2-targeted therapy
Authors:
V. Giannini, S. Rosati, A. Defeudis, G. Balestra, L. Vassallo, G. Cappello, S. Mazzetti, C. De Mattia, F. Rizzetto, A. Torresin, A. Sartore-Bianchi, S. Siena, A. Vanzulli, F. Leone, V. Zagonel, S. MarsonJournal:
International journal of cancerDOI:
10.1002/ijc.33271Year:
2020Abstract:
The aim of our study was to develop and validate a machine learning algorithm to predict response of individual HER2-amplified colorectal cancer liver metastases (lmCRC) undergoing dual HER2-targeted therapy. Twenty-four radiomics features were extracted after 3D manual segmentation of 141 lmCRC on pretreatment portal CT scans of a cohort including 38 HER2-amplified patients; feature selection was then performed using genetic algorithms. lmCRC were classified as nonresponders (R-), if their largest diameter increased more than 10% at a CT scan performed after 3 months of treatment, responders (R+) otherwise. Sensitivity, specificity, negative (NPV) and positive (PPV) predictive values in correctly classifying individual lesion and overall patient response were assessed on a training dataset and then validated on a second dataset using a Gaussian naïve Bayesian classifier. Per-lesion sensitivity, specificity, NPV and PPV were 89%, 85%, 93%, 78% and 90%, 42%, 73%, 71% respectively in the testing and validation datasets. Per-patient sensitivity and specificity were 92% and 86%. Heterogeneous response was observed in 9 of 38 patients (24%). Five of nine patients were carriers of nonresponder lesions correctly classified as such by our radiomics signature, including four of seven harboring only one nonresponder lesion. The developed method has been proven effective in predicting behavior of individual metastases to targeted treatment in a cohort of HER2 amplified patients. The model accurately detects responder lesions and identifies nonresponder lesions in patients with heterogeneous response, potentially paving the way to multimodal treatment in selected patients. Further validation will be needed to confirm our findings.
Read moreRobustness Analysis of Texture Features with Different Beamforming Techniques
Authors:
Silvia Seoni, Giulia Matrone, Kristen M. MeiburgerJournal:
2020 IEEE International Ultrasonics Symposium (IUS)DOI:
10.1109/IUS46767.2020.9251737Year:
2020 Read moreAutomated segmentation of brain cells for clonal analyses in fluorescence microscopy images
Authors:
Salvi, M., Cerrato, V., Buffo, A., & Molinari, F.Journal:
Journal of neuroscience methodsDOI:
10.1016/j.jneumeth.2019.10834810.1016/j.jneumeth.2019.108348Year:
2019 Read moreAutomated segmentation of fluorescence microscopy images for 3D cell detection in human-derived cardiospheres
Authors:
Salvi, M., Morbiducci, U., Amadeo, F., Santoro, R., Angelini, F., Chimenti, I., ... & Molinari, F.• Salvi, M., Morbiducci, U., Amadeo, F., Santoro, R., Angelini, F., Chimenti, I., ... & Molinari, F.Journal:
Scientific reportsDOI:
10.1038/s41598-019-43137-2Year:
2019 Read moreAutomatic Extraction of Dermatological Parameters from Nevi Using an Inexpensive Smartphone Microscope: A Proof of Concept
Authors:
Kristen M. Meiburger, Federica Veronese, Vanessa Tarantino, Massimo Salvi, Matteo Fadda, Silvia Seoni, Elisa Zavattaro, Bruno De Santi, Nicola Michielli, Paola Savoia, Filippo MolinariJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856720Year:
2019Abstract:
–
Read moreAutomatic skin lesion area determination of basal cell carcinoma using optical coherence tomography angiography and a skeletonization approach: Preliminary results
Authors:
Kristen M. Meiburger, Zhe Chen, Christoph Sinz, Erich Hoover, Michael Minneman, Jason Ensher, Harald Kittler, Rainer A. Leitgeb, Wolfgang Drexler, Mengyang LiuJournal:
Journal of BiophotonicsDOI:
10.1002/jbio.201900131Year:
2019 Read moreGeometry and strain sensing dictate YAP-dependent evolution of human cardiac stromal cells toward myofibroblasts in the cardiosphere organoid model
Authors:
Pesce, M., Amadeo, F., Salvi, M., Pagani, F., Angelini, F., Messina, E., Agrifoglio, M., Molinari, F., Chimenti, I., & Morbiducci, U.Journal:
European Heart Journal, 40(Supplement_1)DOI:
10.1093/eurheartj/ehz746.0342Year:
2019 Read moreTransverse Muscle Ultrasound Analysis (TRAMA): Robust and Accurate Segmentation of Muscle Cross-Sectional Area
Authors:
Massimo Salvi, Cristina Caresio, Kristen M. Meiburger, Bruno De Santi, Filippo Molinari, Marco Alessandro MinettoJournal:
Ultrasound in Medicine and BiologyDOI:
10.1016/j.ultrasmedbio.2018.11.012Year:
2019 Read moreAutomated localization and segmentation techniques for B-mode ultrasound images: A review
Authors:
Kristen M. Meiburger, U. Rajendra Acharya, Filippo MolinariJournal:
Computers in Biology and MedicineDOI:
10.1016/j.compbiomed.2017.11.018Year:
2018 Read moreQuantitative analysis of thyroid tumors vascularity: A comparison between 3‐D contrast‐enhanced ultrasound and 3‐D Power Doppler on benign and malignant thyroid nodules
Authors:
Cristina Caresio, Marco Caballo, Maurilio Deandrea, Roberto Garberoglio, Alberto Mormile, Ruth Rossetto, Paolo Limone, Filippo MolinariJournal:
Medical PhysicsDOI:
10.1002/mp.12971Year:
2018 Read moreRadiomics for Identification of Active Bone Marrow from CT: An Exploratory Study
Authors:
S. Rosati; G. Balestra; P. Franco; C. Fiandra; F. Arcadipane; P. Silvetti; U. Ricardi; E. GallioJournal:
2018 IEEE Life Sciences Conference (LSC)DOI:
10.1109/LSC.2018.8572154Year:
2018Abstract:
The radiation dose received by the pelvic Bone Marrow (BM) is a predictive factor for Hematologic Toxicity (HT) occurrence in the treatment of anal cancer. For this reason it is important to avoid BM during radiotherapy. In particular, the standard strategy in these cases consists in the identification of hematopoietically active BM (actBM), i.e. the part of BM in charge of blood cells generation, on 18 FDG-PET, FLT-PET or MRI, but no approached have been developed for identifying actBM from CT images. This exploratory study aims to use radiomics for detecting actBM on CT sequences. Our approach is based on the extraction of 36 first-order and texture (second-order) features for each CT slice. These features are used as input of a Decision Tree (DT) classifier able to discriminate between active and inactive BM regions on the images. This method was applied to five patients affected by carcinoma of the anal canal and the obtained actBM segmentation was compared with the standard actBM identification from 18 FDG-PET (reference standard, RS). Our results show that actBM identification in lumbosacral and iliac structures using radiomics overlaps the RS for more than 75% in 4 out of 5 patients.
Read moreRadiomics to predict response to neoadjuvant chemotherapy in rectal cancer: Influence of simultaneous feature selection and classifier optimization
Authors:
Rosati, S., Gianfreda, C.M., Balestra, G., Giannini, V., Mazzetti, S., Regge, D.Journal:
IEEE Life Sciences Conference, LSC 2018DOI:
10.1109/LSC.2018.8572194Year:
2018 Read moreFully Automated Muscle Ultrasound Analysis (MUSA): Robust and Accurate Muscle Thickness Measurement
Authors:
Cristina Caresio, Massimo Salvi, Filippo Molinari, Kristen M. Meiburger, Marco Alessandro MinettoJournal:
Ultrasound in Medicine and BiologyDOI:
10.1016/j.ultrasmedbio.2016.08.032Year:
2017 Read moreNon-invasive multimodal optical coherence and photoacoustic tomography for human skin imaging
Authors:
Zhe Chen, Elisabet Rank, Kristen M. Meiburger, Christoph Sinz, Andreas Hodul, Edward Zhang, Erich Hoover, Micheal Minneman, Jason Ensher, Paul C. Beard, Harald Kittler, Rainer A. Leitgeb, Wolfgang Drexler, Mengyang LiuJournal:
Scientific ReportsDOI:
10.1038/s41598-017-18331-9Year:
2017 Read moreCarotid wall measurement and assessment based on pixel-based and local texture descriptors
Authors:
Rosati, S., Meiburger, K.M., Balestra, G., Acharya, U.R., Molinari, F.Journal:
Journal of Mechanics in Medicine and BiologyDOI:
10.1142/S0219519416400066Year:
2016 Read moreSkeletonization algorithm-based blood vessel quantification using in vivo 3D photoacoustic imaging
Authors:
Kristen M. Meiburger, Seung Yun Nam, Eunna Chung, Laura J. Suggs5, Stanislav Y. Emelianov, Filippo MolinariJournal:
Physics in Medicine and BiologyDOI:
10.1088/0031-9155/61/22/7994Year:
2016 Read moreQuantitative Assessment of Cancer Vascular Architecture by Skeletonization of High-Resolution 3-D Contrast-Enhanced Ultrasound Images: Role of Liposomes and Microbubbles
Authors:
Filippo Molinari, Kristen M. Meiburger, Pierangela Giustetto, Silvia Rizzitelli, Cinzia Boffa, Mauro Castano, Enzo TerrenoJournal:
Technology in Cancer Research and TreatmentDOI:
10.7785/tcrtexpress.2013.600272Year:
2014 Read moreNeuroengineering
A comparative study of muscle activity and synergies during walking in baboons and humans
Authors:
Francois Druelle*, Marco Ghislieri*, Pablo Molina-Vila, Brigitte Rimbaud, Valentina Agostini, Gilles BerillonJournal:
Journal of Human EvolutionDOI:
10.1016/j.jhevol.2024.103513Year:
2024Abstract:
Bipedal locomotion was a major functional change during hominin evolution, yet, our understanding of this gradual and complex process remains strongly debated. Based on fossil discoveries, it is possible to address functional hypotheses related to bipedal anatomy, however, motor control remains intangible with this approach. Using comparative models which occasionally walk bipedally has proved to be relevant to shed light on the evolutionary transition toward habitual bipedalism. Here, we explored the organization of the neuromuscular control using surface electromyography (sEMG) for six extrinsic muscles in two baboon individuals when they walk quadrupedally and bipedally on the ground. We compared their muscular coordination to five human subjects walking bipedally. We extracted muscle synergies from the sEMG envelopes using the nonnegative matrix factorization algorithm which allows decomposing the sEMG data in the linear combination of two non-negative matrixes (muscle weight vectors and activation coefficients). We calculated different parameters to estimate the complexity of the sEMG signals, the duration of the activation of the synergies, and the generalizability of the muscle synergy model across species and walking conditions. We found that the motor control strategy is less complex in baboons when they walk bipedally, with an increased muscular activity and muscle coactivation. When comparing the baboon bipedal and quadrupedal pattern of walking to human bipedalism, we observed that the baboon bipedal pattern of walking is closer to human bipedalism for both baboons, although substantial differences remain. Overall, our findings show that the muscle activity of a nonadapted biped effectively fulfills the basic mechanical requirements (propulsion and balance) for walking bipedally, but substantial refinements are possible to optimize the efficiency of bipedal locomotion. In the evolutionary context of an expanding reliance on bipedal behaviors, even minor morphological alterations, reducing muscle coactivation, could have faced strong selection pressure, ultimately driving bipedal evolution in hominins.
Read moreAn Algorithm for Choosing the Optimal Number of Muscle Synergies during Walking
Authors:
R. Ballarini, M. Ghislieri, M. Knaflitz and V. AgostiniJournal:
SensorsDOI:
10.3390/s21103311Year:
2021Abstract:
In motor control studies, the 90% thresholding of variance accounted for (VAF) is the classical way of selecting the number of muscle synergies expressed during a motor task. However, the adoption of an arbitrary cut-off has evident drawbacks. The aim of this work is to describe and validate an algorithm for choosing the optimal number of muscle synergies (ChoOSyn), which can overcome the limitations of VAF-based methods. The proposed algorithm is built considering the following principles: (1) muscle synergies should be highly consistent during the various motor task epochs (i.e., remaining stable in time), (2) muscle synergies should constitute a base with low intra-level similarity (i.e., to obtain information-rich synergies, avoiding redundancy). The algorithm performances were evaluated against traditional approaches (threshold-VAF at 90% and 95%, elbow-VAF and plateau-VAF), using both a simulated dataset and a real dataset of 20 subjects. The performance evaluation was carried out by analyzing muscle synergies extracted from surface electromyographic (sEMG) signals collected during walking tasks lasting 5 min. On the simulated dataset, ChoOSyn showed comparable performances compared to VAF-based methods, while, in the real dataset, it clearly outperformed the other methods, in terms of the fraction of correct classifications, mean error (ME), and root mean square error (RMSE). The proposed approach may be beneficial to standardize the selection of the number of muscle synergies between different research laboratories, independent of arbitrary thresholds
Read moreAtypical Gait Cycles in Parkinson’s Disease
Authors:
M. Ghislieri, V. Agostini, L. Rizzi, M. Knaflitz, and M. LanotteJournal:
SensorsDOI:
10.3390/s21155079Year:
2021Abstract:
It is important to find objective biomarkers for evaluating gait in Parkinson’s Disease (PD), especially related to the foot and lower leg segments. Foot-switch signals, analyzed through Statistical Gait Analysis (SGA), allow the foot-floor contact sequence to be characterized during a walking session lasting five-minutes, which includes turnings. Gait parameters were compared between 20 PD patients and 20 age-matched controls. PDs showed similar straight-line speed, cadence, and double-support compared to controls, as well as typical gait-phase durations, except for a small decrease in the flat-foot contact duration (−4% of the gait cycle, p = 0.04). However, they showed a significant increase in atypical gait cycles (+42%, p = 0.006), during both walking straight and turning. A forefoot strike, instead of a “normal” heel strike, characterized the large majority of PD’s atypical cycles, whose total percentage was 25.4% on the most-affected and 15.5% on the least-affected side. Moreover, we found a strong correlation between the atypical cycles and the motor clinical score UPDRS-III (r = 0.91, p = 0.002), in the subset of PD patients showing an abnormal number of atypical cycles, while we found a moderate correlation (r = 0.60, p = 0.005), considering the whole PD population. Atypical cycles have proved to be a valid biomarker to quantify subtle gait dysfunctions in PD patients
Read moreBalance and Muscle Synergies during a Single-Limb Stance Task in Individuals with Chronic Ankle Instability
Authors:
M. Ghislieri, L. Labanca, M. Mosca, L. Bragonzoni, M. Kanflitz & V. AgostiniJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2023.3328933Year:
2023Abstract:
The aim of this study was to investigate balance performance and muscle synergies during a Single-Limb Stance (SLS) task in individuals with Chronic Ankle Instability (CAI) and a group of healthy controls. Twenty individuals with CAI and twenty healthy controls were asked to perform a 30-second SLS task in Open-Eyes (OE) and Closed-Eyes (CE) conditions while standing on a force platform with the injured or the dominant limb, respectively. The activation of 13 muscles of the lower limb, hip, and back was recorded by means of surface electromyography. Balance performance was assessed by identifying the number and the duration of SLS epochs, and the Root-Mean-Square (RMS) in Antero-Posterior (AP) and Medio-Lateral (ML) directions of the body-weight normalized ground reaction forces. The optimal number of synergies, weight vectors, and activation coefficients were also analyzed. CAI group showed a higher number and a shorter duration of SLS epochs and augmented ground reaction force RMS in both AP and ML directions compared to controls. Both groups showed an increase in the RMS in AP and ML forces in CE compared to OE. Both groups showed 4 optimal synergies in CE, while controls showed 5 synergies in OE. CAI showed a significantly higher weight of knee flexor muscles in both OE and CE. In conclusion, muscle synergies analysis provided an in–depth knowledge of motor control mechanisms in CAI individuals. They showed worse balance performance, a lower number of muscle synergies in a CE condition and abnormal knee flexor muscle activation compared to healthy controls.
Read moreFoot–Floor Contact Sequences: A Metric for Gait Assessment in Parkinson’s Disease after Deep Brain Stimulation
Authors:
Marco Ghislieri, Valentina Agostini, Laura Rizzi, Chiara Fronda, Marco Knaflitz, Michele LanotteJournal:
SensorsDOI:
10.3390/s24206593Year:
2024Abstract:
Digital gait monitoring is increasingly used to assess locomotion and fall risk. The aim of this work is to analyze the changes in the foot–floor contact sequences of Parkinson’s Disease (PD) patients in the year following the implantation of Deep Brain Stimulation (DBS). During their best-ON condition, 30 PD patients underwent gait analysis at baseline (T0), at 3 months after subthalamic nucleus DBS neurosurgery (T1), and at 12 months (T2) after subthalamic nucleus DBS neurosurgery. Thirty age-matched controls underwent gait analysis once. Each subject was equipped with bilateral foot-switches and a 5 min walk was recorded, including both straight-line and turnings. The walking speed, turning time, stride time variability, percentage of atypical gait cycles, stance, swing, and double support duration were estimated. Overall, the gait performance of PD patients improved after DBS, as also confirmed by the decrease in their UPDRS-III scores from 19.4 ± 1.8 to 10.2 ± 1.0 (T0 vs.T2) (p < 0.001). In straight-line walking, the percentages of atypical cycles of PD on the more affected side were 11.1 ± 1.5% (at T0), 3.1 ± 1.5% (at T1), and 5.1 ± 2.4% (at T2), while in controls it was 3.1 ± 1.3% (p < 0.0005). In turnings, this percentage was 13.7 ± 1.1% (at T0), 7.8 ± 1.1% (at T1), and 10.9 ± 1.8% (at T2), while in controls it was 8.1 ± 1.0% (p < 0.001). Therefore, in straight-line walking, the atypical cycles decreased by 72% at T1, and by 54% at T2 (with respect to baseline), while, in turnings, atypical cycles decreased by 43% at T1, and by 20% at T2. The percentage of atypical gait cycles proved an informative digital biomarker for quantifying PD gait changes after DBS, both in straight-line paths and turnings.
Read moreHow to improve robustness in muscle synergy extraction
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)DOI:
10.1109/EMBC.2019.8856438Year:
2019Abstract:
The muscle synergy theory was widely used in literature to assess the modular organization of the central nervous system (CNS) during human locomotion. The extraction of muscle synergies may be strongly influenced by the preprocessing techniques applied to surface electromyographic (sEMG) signals. The aim of this contribution is to assess the robustness improvement in muscle synergy extraction obtained using an innovative pre-processing technique with respect to the standard procedure. The new pre-processing technique that we propose is based on the extraction of principal muscle activation intervals (necessary to accomplish a specific biomechanical task during gait) from the original sEMG signals, discarding the secondary muscle activation intervals (activations that occur only in some strides with auxiliary functions). Results suggest that the extraction of the principal activation intervals from sEMG provide a more consistent and stable description of the modular organization of the CNS with respect to the standard pre-processing procedure.
Read moreMuscle activations during functional tasks in individuals with chronic ankle instability: a systematic review of electromyographical studies
Authors:
L. Labanca, M. Mosca, M. Ghislieri, V. Agostini, M. Knaflitz, & M. G. BenedettiJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2021.09.182Year:
2021Abstract:
Background
It has been reported that individuals with chronic ankle instability (CAI) show motor control abnormalities. The study of muscle activations by means of surface electromyography (sEMG) plays a key role in understanding some of the features of movement abnormalities.
Research question
Do common sEMG activation abnormalities and strategies exists across different functional movements?
Methods
Literature review was conducted on PubMed, Web-of-Science and Cochrane databases. Studies published between 2000 and 2020 that assessed muscle activations by means of sEMG during any type of functional task in individuals with CAI, and used healthy individuals as controls, were included. Methodological quality was assessed using the modified Downs&Black checklist. Since the methodologies of different studies were heterogeneous, no meta-analysis was conducted.
Results
A total of 63 articles investigating muscle activations during gait, running, responses to perturbations, landing and hopping, cutting and turning; single-limb stance, star excursion balance task, forward lunges, ball-kicking, y-balance test and single-limb squatting were considered. Individuals with CAI showed a delayed activation of the peroneus longus in response to sudden inversion perturbations, in transitions between double- and single-limb stance, and in landing on unstable surfaces. Apparently, while walking on ground there are no differences between CAI and controls, walking on a treadmill increases the variability of muscles activations, probably as a “safety strategy” to avoid ankle inversion. An abnormal activation of the tibialis anterior was observed during a number of tasks. Finally, hip/spine muscles were activated before ankle muscles in CAI compared to controls.
Conclusion
Though the methodology of the studies herein considered is heterogeneous, this review shows that the peroneal and tibialis anterior muscles have an abnormal activation in CAI individuals. These individuals also show a proximal muscle activation strategy during the performance of balance challenging tasks. Future studies should investigate whole-body muscle activation abnormalities in CAI individuals.
Muscle synergies extracted using principal activations: improvement of robustness and interpretability
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2020.2965179Year:
2020Abstract:
The muscle synergy theory has been widely used to assess the modular organization of the central nervous system (CNS) during human locomotion. The pre-processing approach applied to the surface electromyographic (sEMG) signals influences the extraction of muscle synergies. The aim of this contribution is to assess the improvements in muscle synergy extraction obtained by using an innovative pre-processing approach. We evaluate the improvement in terms of the possible variation in the number of muscle synergies, of the intra-subject consistency, of the robustness, and of the interpretability of the results. The pre-processing approach presented in this paper is based on the extraction of the muscle principal activations (muscle activations strictly necessary to accomplish a specific biomechanical task) from the original sEMG signals, to then obtain muscle synergies using principal activations only. The results herein presented show that the application of this novel approach for the extraction of the muscle synergies provides a more robust and easily interpretable description of the modular organization of the CNS with respect to the standard pre-processing approach.
Read moreMuscle synergies for the control of single-limb stance with and without visual information in young individuals
Authors:
L. Labanca, M. Ghislieri, M. Knaflitz, G. Barone, L. Bragonzoni, V. Agostini & M. G. BenedettiJournal:
BMC Sports Science, Medicine and RehabilitationDOI:
10.1186/s13102-021-00392-zYear:
2021Abstract:
Purpose
Single-limb stance is a demanding postural task featuring a high number of daily living and sporting activities. Thus, it is widely used for training and rehabilitation, as well as for balance assessment. Muscle activations around single joints have been previously described, however, it is not known which are the muscle synergies used to control posture and how they change between conditions of normal and lack of visual information.
Methods
Twenty-two healthy young participants were asked to perform a 30 s single-limb stance task in open-eyes and closed-eyes condition while standing on a force platform with the dominant limb. Muscle synergies were extracted from the electromyographical recordings of 13 muscles of the lower limb, hip, and back. The optimal number of synergies, together with the average recruitment level and balance control strategies were analyzed and compared between the open- and the closed-eyes condition.
Results
Four major muscle synergies, two ankle-dominant synergies, one knee-dominant synergy, and one hip/back-dominant synergy were found. No differences between open- and closed-eyes conditions were found for the recruitment level, except for the hip/back synergy, which significantly decreased (p = 0.02) in the closed-eyes compared to the open-eyes condition. A significant increase (p = 0.03) of the ankle balance strategy was found in the closed-eyes compared to the open-eyes condition.
Conclusion
In healthy young individuals, single-limb stance is featured by four major synergies, both in open- and closed-eyes condition. Future studies should investigate muscle synergies in participants with other age groups, as well as pathological conditions.
Read moreMuscle synergies in Parkinson’s disease before and after the deep brain stimulation of the bilateral subthalamic nucleus
Authors:
Marco Ghislieri, Michele Lanotte, Marco Knaflitz, Laura Rizzi, and Valentina AgostiniJournal:
Scientific ReportsDOI:
10.1038/s41598-023-34151-6Year:
2023Abstract:
The aim of this study is to quantitatively assess motor control changes in Parkinson’s disease (PD) patients after bilateral deep brain stimulation of the subthalamic nucleus (STN-DBS), based on a novel muscle synergy evaluation approach. A group of 20 PD patients evaluated at baseline (before surgery, T0), at 3 months (T1), and at 12 months (T2) after STN-DBS surgery, as well as a group of 20 age-matched healthy control subjects, underwent an instrumented gait analysis, including surface electromyography recordings from 12 muscles. A smaller number of muscle synergies was found in PD patients (4 muscle synergies, at each time point) compared to control subjects (5 muscle synergies). The neuromuscular robustness of PD patients—that at T0 was smaller with respect to controls (PD T0: 69.3 ± 2.2% vs. Controls: 77.6 ± 1.8%, p = 0.004)—increased at T1 (75.8 ± 1.8%), becoming not different from that of controls at T2 (77.5 ± 1.9%). The muscle synergies analysis may offer clinicians new knowledge on the neuromuscular structure underlying PD motor types of behavior and how they can improve after electroceutical STN-DBS therapy.
Read moreMuscle Synergy Assessment During Single-Leg Stance
Authors:
M. Ghislieri, M. Knaflitz, L. Labanca, G. Barone, L. Bragonzoni, M. G. Benedetti, and V. AgostiniJournal:
IEEE Transactions on Neural Systems and Rehabilitation EngineeringDOI:
10.1109/TNSRE.2020.3030847Year:
2020Abstract:
In the study of muscle synergies during the maintenance of single-leg stance there are several methodological issues that must be taken into account before muscle synergy extraction. In particular, it is important to distinguish between epochs of surface electromyography (sEMG) signals corresponding to “well-balanced” and “unbalanced” single-leg stance, since different motor control strategies could be used to maintain balance. The aim of this work is to present and define a robust procedure to distinguish between “well-balanced” and “unbalanced” single-leg stance to be chosen as input for the algorithm used to extract muscle synergies. Our results demonstrate that the proposed approach for the selection of sEMG epochs relative to “well-balanced” and “unbalanced” single-leg stance is robust with respect to the selection of the segmentation threshold, revealing a high consistency in the number of muscle synergies and high similarity among the weight vectors (correlation values range from 0.75 to 0.97). Moreover, differences in terms of average recruitment levels and balance control strategies were detected, suggesting a slightly different modular organization between “well-balanced” and “unbalanced” single-leg stance. In conclusion, this approach can be successfully used as a pre-processing step before muscle synergy extraction, allowing for a better assessment of motor control strategies during the single-leg stance task.
Read morePostural control after traumatic brain injury in patients with neuro-ophthalmic deficits
Authors:
V. Agostini, E. Chiaramello, C. Bredariol, C. Cavallini and M. KnaflitzJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2011.05.008Year:
2011Abstract:
Postural instability is a common and devastating consequence of traumatic brain injury (TBI). The majority of TBI patients also suffer from neuro-ophthalmic deficits that can be an important contributing element to their sensation of vertigo and dizziness. Static posturography aims at the objective evaluation of patient balance impairment, but is usually affected by large inter- and intra-subject variability. Here we propose a protocol based on 10 randomized trials stimulating in different ways the visual and vestibular systems. Due to its completeness, our protocol highlights the specific residual difficulties of each patient in the various conditions. In this way, it was possible to evidence significant balance abnormalities in TBI patients with respect to controls. Moreover, by means of a multivariate analysis we were able to discriminate different levels of residual neuro-ophthalmic impairment.
Read morePostural sway in volleyball players
Authors:
V. Agostini, E. Chiaramello, L. Canavese, C. Bredariol and M. KnaflitzJournal:
Human Movement ScienceDOI:
10.1016/j.humov.2013.01.002Year:
2013Abstract:
The aim of this work was to analyze the postural sway of volleyball players in bipedal quiet stance. The center of pressure (CoP) was measured in 46 athletes and 42 non-athlete controls. Each subject was tested in 10 different conditions, 5 with their eyes open and 5 with their eyes closed. Volleyball players showed greater CoP ellipses, suggesting a different model of sensory integration in their postural stability. A multivariate approach to data analysis demonstrated that the postural sway of the two groups was different when the subjects kept their eyes open, but it was not with visual deprivation. This could partially be explained by the better ‘dynamic’ visual acuity of athletes, since possible (‘static’) refractive errors were corrected for both groups. Furthermore, we expected that national players, engaged in more intensive training programs, were more different from controls than regional ones, and that defensive players, whose role requires the quickest reaction times, were more different from controls than hitters. Our results confirmed these hypothesis. The protocol presented might be useful to assess the efficacy of intensive sport training programs and/or to select elite players with an aptitude for a specific playing position.
Read moreThe Effect of Signal-to-Noise Ratio on Muscle Synergy Extraction
Authors:
M. Ghislieri, V. Agostini, and M. KnaflitzJournal:
2018 IEEE Life Sciences Conference (LSC)DOI:
10.1109/LSC.2018.8572075Year:
2018Abstract:
The modular organization of the central nervous system (CNS) during motor tasks was widely assessed by means of muscle synergies. The aim of this work was to assess the impact of the Signal-to-Noise Ratio (SNR) on muscle synergies extracted from synthetic surface electromyographic (sEMG) signals that simulate the muscle activity of the lower limb during walking. To evaluate the effect of the SNR, the similarity between the weights vectors and the activation coefficients extracted from real sEMG signals and from simulated sEMG signals at different values of SNR was computed. Results reveal that muscle synergy extraction is strongly dependent upon the quality of the sEMG signals simulated.
Read moreThe role of central vision in posture: Postural sway adaptations in Stargardt patients
Authors:
V. Agostini, A. Sbrollini, C. Cavallini, A. Busso, G. Pignata and M. KnaflitzJournal:
Gait & PostureDOI:
10.1016/j.gaitpost.2015.10.003Year:
2016Abstract:
The role of central and peripheral vision in the maintenance of upright stance is debated in literature. Stargardt disease causes visual deficits affecting the central field, but leaving unaltered a patient’s peripheral vision. Hence, the study of this rare pathology gives the opportunity to selectively investigate the role of central vision in posture. Postural sway in quiet stance was analyzed in 10 Stargardt patients and 10 control subjects, in three different conditions: (1) eyes closed, (2) eyes open, gazing at a fixed target, and (3) eyes open, tracking a moving target. Stargardt patients outperformed controls in the condition with eyes closed, showing a reduced root mean square (RMS) of the medio-lateral COP displacement, while their performance was not significantly different from controls in the antero-posterior direction. There were no significant differences between patients and controls in open eyes conditions. These results suggest that Stargardt patients adapted to a different visual-somatosensory integration, relying less on vision, especially in the medio-lateral direction. Hence, the central vision seems to affect mostly the medio-lateral direction of postural sway. This finding supports the plausibility of the “functional sensitivity hypothesis”, that assigns complementary roles to central and peripheral vision in the control of posture.
Read moreTelemedicine
Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications
Authors:
N. Giordano, S. Rosati, and M. KnaflitzJournal:
SensorsDOI:
10.3390/s21217246Year:
2021Abstract:
The signal quality limits the applicability of phonocardiography at the patients’ domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.
Read moreA Method for the Estimation of the Timing of Heart Sound Components Through Blind Source Separation in Multi-Source Phonocardiography
Authors:
N. Giordano and M. KnaflitzJournal:
2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA)DOI:
10.1109/MeMeA49120.2020.9137315Year:
2020 Read moreA wearable device to assess postural sway
Authors:
V. Agostini, E. Aiello, D. Fortunato, M. Knaflitz, and L. GastaldiJournal:
2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT)DOI:
10.1109/ISCE.2019.8901019Year:
2019Abstract:
The maintenance of balance in upright stance is traditionally evaluated using heavy and expensive force platforms. The aim of this work is to prove the usefulness of a low-cost wearable sensor (an actigraph) to assess postural sway. We compared the performance of the device to a gold standard force platform. We analyzed measurements of postural sway in four conditions differently challenging the subject: with eyes open or closed, while keeping a small or large base of support. We estimated the main postural parameters (ellipse area, mediolateral and antero-posterior root-mean square, eccentricity, sway path length) considering: 1) acceleration data recorded by the actigraph, and 2) traditional COP data obtained from the force platform. We found that it is possible to clearly distinguish the differences among the postural parameters, obtained in the various balance conditions, also using acceleration data. Our results show that the wearable device allows for obtaining information similar to those achievable by the force platform. This support the use of wearable devices to assess postural balance, in a handy and cheap manner.
Read moreSEARCH
NEWS
- Fabrizio Sciscenti wins the “Vincenzo Tagliasco 2024” Award October 26, 2024
- Premi GNB 2024 – Gruppo Nazionale BioIngegneria May 1, 2024
- XXIV Congresso Nazionale SIAMOC 2024 April 23, 2024
- 9th International Summer School on Neuroengineering ‘Massimo Grattarola’ – Neuroengineering for health and disease: a multi-scale approach March 13, 2024
- XLII Annual School 2023 – Registration is open June 8, 2023
RECENT PUBLICATIONS
-
Foot–Floor Contact Sequences: A Metric for Gait Assessment in Parkinson’s Disease after Deep Brain StimulationOctober 13, 2024/0 Comments