Incorporating intratumoral heterogeneity into weakly-supervised deep learning models via variance pooling

TL;DR

This paper introduces a variance pooling method in deep learning models to explicitly incorporate intratumoral heterogeneity, improving cancer survival prediction from whole slide images.

Contribution

It presents a novel variance pooling architecture for MIL models to capture tumor heterogeneity, enhancing predictive accuracy in computational pathology.

Findings

Variance pooling improves survival prediction across five cancer types.

The model captures biologically relevant signals related to tumor heterogeneity.

Enhanced interpretability via patches reveals meaningful biological insights.

Abstract

Supervised learning tasks such as cancer survival prediction from gigapixel whole slide images (WSIs) are a critical challenge in computational pathology that requires modeling complex features of the tumor microenvironment. These learning tasks are often solved with deep multi-instance learning (MIL) models that do not explicitly capture intratumoral heterogeneity. We develop a novel variance pooling architecture that enables a MIL model to incorporate intratumoral heterogeneity into its predictions. Two interpretability tools based on representative patches are illustrated to probe the biological signals captured by these models. An empirical study with 4,479 gigapixel WSIs from the Cancer Genome Atlas shows that adding variance pooling onto MIL frameworks improves survival prediction performance for five cancer types.