A Survey on Graph-Based Deep Learning for Computational Histopathology

TL;DR

This survey reviews how graph-based deep learning methods enhance digital pathology analysis by capturing tissue structure and interactions, addressing limitations of traditional CNN approaches.

Contribution

It provides a comprehensive overview of graph analytics in digital pathology, including construction, architectures, applications, limitations, and future directions.

Findings

Graph methods improve tumor localization and classification.

Graph-based models enhance survival prediction accuracy.

Current techniques face limitations in scalability and interpretability.

Abstract

With the remarkable success of representation learning for prediction problems, we have witnessed a rapid expansion of the use of machine learning and deep learning for the analysis of digital pathology and biopsy image patches. However, learning over patch-wise features using convolutional neural networks limits the ability of the model to capture global contextual information and comprehensively model tissue composition. The phenotypical and topological distribution of constituent histological entities play a critical role in tissue diagnosis. As such, graph data representations and deep learning have attracted significant attention for encoding tissue representations, and capturing intra- and inter- entity level interactions. In this review, we provide a conceptual grounding for graph analytics in digital pathology, including entity-graph construction and graph architectures, and present their current success for tumor localization and classification, tumor invasion and staging, image retrieval, and survival prediction. We provide an overview of these methods in a systematic manner organized by the graph representation of the input image, scale, and organ on which they operate. We also outline the limitations of existing techniques, and suggest potential future research directions in this domain.