Patient-Level Microsatellite Stability Assessment from Whole Slide Images by Combining Momentum Contrast Learning and Group Patch Embeddings.

Daniel Shats, Hadar Hezi, Guy Shani, Yosef E. Maruvka, Moti Freiman

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Assessing microsatellite stability status of a patient’s colorectal cancer is crucial in personalizing treatment regime. Recently, convolutional-neural-networks (CNN) combined with transfer-learning approaches were proposed to circumvent traditional laboratory testing for determining microsatellite status from hematoxylin and eosin stained biopsy whole slide images (WSI). However, the high resolution of WSI practically prevent direct classification of the entire WSI. Current approaches bypass the WSI high resolution by first classifying small patches extracted from the WSI, and then aggregating patch-level classification logits to deduce the patient-level status. Such approaches limit the capacity to capture important information which resides at the high resolution WSI data. We introduce an effective approach to leverage WSI high resolution information by momentum contrastive learning of patch embeddings along with training a patient-level classifier on groups of those embeddings. Our approach achieves up to 7.4% better accuracy compared to the straightforward patch-level classification and patient level aggregation approach with a higher stability (AUC, 0.91±0.01vs. 0.85±0.04 , p-value < 0.01). Our code can be found at https://github.com/TechnionComputationalMRILab/colorectal_cancer_ai.
Original languageEnglish
Title of host publication European Conference on Computer Vision ECCV Workshops (3)
EditorsLeonid Karlinsky, Tomer Michaeli, Ko Nishino
Place of PublicationCham
PublisherSpringer
Pages454-465
Number of pages12
ISBN (Electronic)978-3-031-25065-1
ISBN (Print)978-3-031-25065-1
DOIs
StatePublished - 18 Feb 2022
Externally publishedYes
Event17th European Conference on Computer Vision, ECCV 2022 - Tel Aviv, Israel
Duration: 23 Oct 202227 Oct 2022

Publication series

NameLecture Notes in Computer Science
Volume13803

Conference

Conference17th European Conference on Computer Vision, ECCV 2022
Country/TerritoryIsrael
CityTel Aviv
Period23/10/2227/10/22

Keywords

  • Digital pathology
  • Colorectal cancer
  • Momentum contrast learning
  • Self-supervised learning

Fingerprint

Dive into the research topics of 'Patient-Level Microsatellite Stability Assessment from Whole Slide Images by Combining Momentum Contrast Learning and Group Patch Embeddings.'. Together they form a unique fingerprint.

Cite this