Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians

TL;DR

This paper introduces a method combining automated concept discovery and logic-based explanations to make graph neural networks in digital histopathology more interpretable for clinicians, using breast cancer data.

Contribution

It presents a novel framework integrating GCExplainer and Logic Explained Networks for global explanations of GNNs in medical imaging.

Findings

Effective explanation of GNN decisions in histopathology

Promising results on breast cancer H&E slide classification

Enhanced trustworthiness of AI tools for clinicians

Abstract

To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explained Networks to provide global explanations for Graph Neural Networks. We demonstrate this using a generally applicable graph construction and classification pipeline, involving panoptic segmentation with HoVer-Net and cancer prediction with Graph Convolution Networks. By training on H&E slides of breast cancer, we show promising results in offering explainable and trustworthy AI tools for clinicians.