The analysis of histological slides is fundamental for cancer diagnosis and grading, typically performed by an expert pathologist, and this process is becoming more and more complex due to the rise in cancer incidence and patient-specific treatment options. Digital pathology (DP) is a sub-field of pathology that focuses on data management based on information generated from digitalized specimen slides. The field of DP is growing and has applications in diagnostic medicine, with the goal of achieving efficient and cheaper diagnoses, and prediction of diseases.

Recently, deep learning (DL) frameworks have rapidly become the main methodology for analyzing medical images. Due to their powerful learning ability and advantages in dealing with complex patterns, DL algorithms are ideal for image analysis challenges, particularly in the field of digital pathology. This research line is focused on the development of automated solutions for digital pathology image analysis. The variety of tasks performed in the context of DP includes classification (e.g., healthy vs. cancerous tissue), detection (e.g., lymphocytes and mitosis counting), segmentation (e.g., nuclei and glands segmentation) and correlation with clinical outcomes (e.g., treatment response).


  • Filippo Molinari (Full Professor)
  • Massimo Salvi (Research Assistant)
  • Nicola Michielli (Research Assistant)
  • Collaborators:

  • Prof. Mauro Papotti, Dr. Luca Molinaro, Dr. Alessandro Gambella – Department of Oncology – University of Turin
  • Dr. Martino Bosco, Dr. Natalia Dogliani - Department of Pathology, Ospedale San Lazzano
  • Prof. Luca Aresu, Dr. Raffaella De Maria, Dr. Selina Iussich - Department of Veterinary Sciences, University of Turin

  • Recent publications:

  • A hybrid deep learning approach for gland segmentation in prostate histopathological images
      Salvi, M., Bosco, M., Molinaro, L., Gambella, A., Papotti, M., Acharya, U. R., & Molinari, F.
      Artificial Intelligence in Medicine
  • Histopathological classification of canine cutaneous round cell tumors using deep learning: a multi-center study
      Salvi, M., Molinari, F., Iussich, S., Muscatello, L. V., Pazzini, L., Benali, S., Banco, B., Abramo, F., De Maria, R., & Aresu, L.
      Frontiers in Veterinary Science
  • Impact of stain normalization and patch selection on the performance of convolutional neural networks in histological breast and prostate cancer classification
      Salvi, M., Molinari, F., Acharya, U. R., Molinaro, L., & Meiburger, K. M.
      Computer Methods and Programs in Biomedicine Update
  • Karpinski Score under Digital Investigation: A Fully Automated Segmentation Algorithm to Identify Vascular and Stromal Injury of Donors’ Kidneys
      Salvi, M., Mogetta, A., Meiburger, K. M., Gambella, A., Molinaro, L., Barreca, A., Papotti M., & Molinari, F.
  • The impact of pre-and post-image processing techniques on deep learning frameworks: A comprehensive review for digital pathology image analysis
      Salvi, M., Acharya, U. R., Molinari, F., & Meiburger, K. M.
      Computers in Biology and Medicine