Visualization for Histopathology Images using Graph Convolutional Neural Networks

TL;DR

This paper introduces a graph convolutional neural network framework with visualization techniques for histopathology images, enabling interpretable diagnosis by highlighting cellular contributions in tissue samples.

Contribution

It presents a novel GCN-based approach with attention and occlusion mechanisms to visualize and interpret cellular features in histology images for disease diagnosis.

Findings

Generated visual maps align with expert diagnostic features.

Effectively distinguished between invasive and in-situ breast cancers.

Differentiated Gleason 3 and 4 prostate cancers using interpretability methods.

Abstract

With the increase in the use of deep learning for computer-aided diagnosis in medical images, the criticism of the black-box nature of the deep learning models is also on the rise. The medical community needs interpretable models for both due diligence and advancing the understanding of disease and treatment mechanisms. In histology, in particular, while there is rich detail available at the cellular level and that of spatial relationships between cells, it is difficult to modify convolutional neural networks to point out the relevant visual features. We adopt an approach to model histology tissue as a graph of nuclei and develop a graph convolutional network framework based on attention mechanism and node occlusion for disease diagnosis. The proposed method highlights the relative contribution of each cell nucleus in the whole-slide image. Our visualization of such networks trained to distinguish between invasive and in-situ breast cancers, and Gleason 3 and 4 prostate cancers generate interpretable visual maps that correspond well with our understanding of the structures that are important to experts for their diagnosis.