A Survey on Graph-Based Deep Learning for Computational Histopathology

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.

arXiv commentPreprint submitted to Computerized Medical Imaging and Graphics

References in corpus (31)

• A Survey on Deep Learning in Medical Image Analysis
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Simplifying Graph Convolutional Networks
• Representation Learning on Graphs with Jumping Knowledge Networks
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Deep neural network models for computational histopathology: A survey
• BACH: Grand Challenge on Breast Cancer Histology Images
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Modern hierarchical, agglomerative clustering algorithms
• Learning Deep Generative Models of Graphs
• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use
• Benchmarking Graph Neural Networks
• Parameterized Explainer for Graph Neural Network
• SIGN: Scalable Inception Graph Neural Networks
• Artificial Intelligence Assistance Significantly Improves Gleason Grading of Prostate Biopsies by Pathologists
• Going Deeper through the Gleason Scoring Scale: An Automatic end-to-end System for Histology Prostate Grading and Cribriform Pattern Detection
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• NuCLS: A scalable crowdsourcing, deep learning approach and dataset for nucleus classification, localization and segmentation
• On Explainability of Graph Neural Networks via Subgraph Explorations
• Spherical CNNs on Unstructured Grids
• Towards Explainable Graph Representations in Digital Pathology
• Explaining Deep Learning Models - A Bayesian Non-parametric Approach
• Temporal Graph Modeling for Skeleton-based Action Recognition
• Some New Layer Architectures for Graph CNN

Cited by in corpus (10)

• Artificial Intelligence for Digital and Computational Pathology
• Graph Representation Learning in Biomedicine
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• Nuclei & Glands Instance Segmentation in Histology Images: A Narrative Review
• Efficient Parameter Optimisation for Quantum Kernel Alignment: A Sub-sampling Approach in Variational Training
• Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
• Predicting Feynman periods in ${\varphi }^4$-theory
• Automated Coronary Arteries Labeling Via Geometric Deep Learning