Home  | Publications | WBL+25

From Pixels to Histopathology: A Graph-Based Framework for Interpretable Whole Slide Image Analysis

MCML Authors

Link to Profile Peter Schüffler

Peter Schüffler

Prof. Dr.

Associate

Computational Pathology

Abstract

The histopathological classification of whole-slide images (WSIs) is a fundamental task in digital pathology; yet it requires extensive time and expertise from specialists. While deep learning methods show promising results, they typically process WSIs by dividing them into artificial patches, which inherently prevents a network from learning from the entire image context, disregards natural tissue structures and compromises interpretability. Our method overcomes this limitation through a novel graph-based framework that constructs WSI graph representations. The WSI-graph efficiently captures essential histopathological information in a compact form. We build tissue representations (nodes) that follow biological boundaries rather than arbitrary patches all while providing interpretable features for explainability. Through adaptive graph coarsening guided by learned embeddings, we progressively merge regions while maintaining discriminative local features and enabling efficient global information exchange. In our method's final step, we solve the diagnostic task through a graph attention network. We empirically demonstrate strong performance on multiple challenging tasks such as cancer stage classification and survival prediction, while also identifying predictive factors using Integrated Gradients.

misc

Preprint

Mar. 2025

Authors

A. Weers • A. H. Berger • L. Lux • P. J. Schüffler • D. Rückert • J. C. Paetzold

Links

arXiv GitHub

Research Area

 C1 | Medicine

BibTeXKey: WBL+25

Back to Top