A survey on graph-based deep learning for computational histopathology. (January 2022)

• Record Type: Journal Article
• Authors: Ahmedt-Aristizabal, David; Armin, Mohammad Ali; Denman, Simon; Fookes, Clinton; Petersson, Lars
• Is Part Of: Computerized medical imaging and graphics. Volume 95(2022)
• Publication Date: 2022-01
• Subjects: Digital pathology -- Cancer classification -- Cell-graph -- Tissue-graph -- Hierarchical graph representation -- Graph Convolutional Networks -- Deep learning; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2021.102027
• Languages: English
• ISSNs: 0895-6111

Abstract

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. Highlights: A rapidly growing field of representation learning for digital pathology is reviewed. Graph-based models can efficiently encode cellular and tissue interactions. Pathology-specific interpretability and human-machine co-learning enabled by graphs. Graph representation has resulted in superior performance for diverse cancers.