Radiomics 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. Gallio
Journal:
2018 IEEE Life Sciences Conference (LSC)
DOI:
10.1109/LSC.2018.8572154
Year:
2018
Abstract:

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 more