Multi-Cohort Framework with Cohort-Aware Attention and Adversarial Mutual-Information Minimization for Whole Slide Image Classification

TL;DR

This paper presents a novel multi-cohort framework for whole slide image classification that leverages cohort-aware attention, adversarial mutual-information minimization, and hierarchical balancing to improve cross-tumor generalization and reduce biases.

Contribution

It introduces a cohort-aware attention module, adversarial cohort regularization, and a hierarchical balancing strategy for unbiased multi-cohort WSI analysis, addressing heterogeneity and cohort imbalance.

Findings

Significant improvement in cross-tumor generalization on multi-cancer dataset

Effective reduction of cohort-specific biases through mutual information minimization

Enhanced scalability for WSI classification across diverse cancer types

Abstract

Whole Slide Images (WSIs) are critical for various clinical applications, including histopathological analysis. However, current deep learning approaches in this field predominantly focus on individual tumor types, limiting model generalization and scalability. This relatively narrow focus ultimately stems from the inherent heterogeneity in histopathology and the diverse morphological and molecular characteristics of different tumors. To this end, we propose a novel approach for multi-cohort WSI analysis, designed to leverage the diversity of different tumor types. We introduce a Cohort-Aware Attention module, enabling the capture of both shared and tumor-specific pathological patterns, enhancing cross-tumor generalization. Furthermore, we construct an adversarial cohort regularization mechanism to minimize cohort-specific biases through mutual information minimization. Additionally, we develop a hierarchical sample balancing strategy to mitigate cohort imbalances and promote unbiased learning. Together, these form a cohesive framework for unbiased multi-cohort WSI analysis. Extensive experiments on a uniquely constructed multi-cancer dataset demonstrate significant improvements in generalization, providing a scalable solution for WSI classification across diverse cancer types. Our code for the experiments is publicly available at <link>.