CIMIL-CRC: A clinically-informed multiple instance learning framework for patient-level colorectal cancer molecular subtypes classification from H&E stained images.

Journal: Computer methods and programs in biomedicine
PMID:

Abstract

BACKGROUND AND OBJECTIVE: Treatment approaches for colorectal cancer (CRC) are highly dependent on the molecular subtype, as immunotherapy has shown efficacy in cases with microsatellite instability (MSI) but is ineffective for the microsatellite stable (MSS) subtype. There is promising potential in utilizing deep neural networks (DNNs) to automate the differentiation of CRC subtypes by analyzing hematoxylin and eosin (H&E) stained whole-slide images (WSIs). Due to the extensive size of WSIs, multiple instance learning (MIL) techniques are typically explored. However, existing MIL methods focus on identifying the most representative image patches for classification, which may result in the loss of critical information. Additionally, these methods often overlook clinically relevant information, like the tendency for MSI class tumors to predominantly occur on the proximal (right side) colon.

Authors

  • Hadar Hezi
    Faculty of Biomedical Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  • Matan Gelber
    Faculty of Electrical and Computer Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  • Alexander Balabanov
    Faculty of Electrical and Computer Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  • Yosef E Maruvka
    Faculty of Biotechnology and Food Engineering, Technion - Israel Institute of Technology, Haifa, Israel.
  • Moti Freiman
    Philips Medical Systems Technologies Ltd., Advanced Technologies Center, Haifa, 3100202, Israel.