Slide-based Graph Collaborative Training for Histopathology Whole Slide Image Analysis

TL;DR

This paper introduces SlideGCD, a slide-based graph collaborative training framework that incorporates inter-slide correlations into WSI analysis, enhancing performance across multiple pathology tasks.

Contribution

The proposed pipeline integrates inter-slide correlations into existing MIL frameworks, improving WSI analysis by leveraging tumor development knowledge in an end-to-end manner.

Findings

Improved accuracy in cancer subtyping, staging, survival, and mutation prediction.

Robust performance across four different pathology tasks.

Effective enhancement of existing MIL frameworks with slide inter-correlation modeling.

Abstract

The development of computational pathology lies in the consensus that pathological characteristics of tumors are significant guidance for cancer diagnostics. Most existing research focuses on the inner-contextual information within each WSI yet ignores the possible inter-correlations between slides. As the development of tumors is a continuous process involving a series of histological, morphological, and genetic changes that accumulate over time, the similarities and differences between WSIs across various stages, grades, locations and patients should potentially contribute to the representation of WSIs and deserve to be taken into account in WSI modeling. To verify the advancement of introducing the slide inter-correlations into the representation learning of WSIs, we proposed a generic WSI analysis pipeline SlideGCD that can be adapted to any existing Multiple Instance Learning (MIL) frameworks and improve their performance. With the new paradigm, the prior knowledge of cancer development can participate in the end-to-end workflow, which concurrently initializes and refines the slide representation, as a guide for message passing in the slide-based graph. Extensive comparisons and experiments are conducted to validate the effectiveness and robustness of the proposed pipeline across 4 different tasks, including cancer subtyping, cancer staging, survival prediction, and gene mutation prediction, with 7 representative SOTA WSI analysis frameworks as backbones.