Computational analysis of pathological image enables interpretable prediction for microsatellite instability

TL;DR

This paper develops interpretable deep learning methods using standard histopathology images to predict microsatellite instability, aiding clinical diagnosis and providing insights into key image features.

Contribution

The study introduces a novel, interpretable image analysis framework for MSI prediction that leverages common pathology images and offers both localization and feature importance insights.

Findings

Achieved decent MSI prediction performance on TCGA cohorts

Generated heat maps highlighting important image regions

Identified color and texture features as key predictors

Abstract

Microsatellite instability (MSI) is associated with several tumor types and its status has become increasingly vital in guiding patient treatment decisions. However, in clinical practice, distinguishing MSI from its counterpart is challenging since the diagnosis of MSI requires additional genetic or immunohistochemical tests. In this study, interpretable pathological image analysis strategies are established to help medical experts to automatically identify MSI. The strategies only require ubiquitous Haematoxylin and eosin-stained whole-slide images and can achieve decent performance in the three cohorts collected from The Cancer Genome Atlas. The strategies provide interpretability in two aspects. On the one hand, the image-level interpretability is achieved by generating localization heat maps of important regions based on the deep learning network; on the other hand, the feature-level interpretability is attained through feature importance and pathological feature interaction analysis. More interestingly, both from the image-level and feature-level interpretability, color features and texture characteristics are shown to contribute the most to the MSI predictions. Therefore, the classification models under the proposed strategies can not only serve as an efficient tool for predicting the MSI status of patients, but also provide more insights to pathologists with clinical understanding.