Hierarchical graph representations in digital pathology.
Details
Download: 34781160.pdf (7677.17 [Ko])
State: Public
Version: Final published version
License: CC BY-NC-ND 4.0
State: Public
Version: Final published version
License: CC BY-NC-ND 4.0
Serval ID
serval:BIB_2E5E57FF556F
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Hierarchical graph representations in digital pathology.
Journal
Medical image analysis
ISSN
1361-8423 (Electronic)
ISSN-L
1361-8415
Publication state
Published
Issued date
01/2022
Peer-reviewed
Oui
Volume
75
Pages
102264
Language
english
Notes
Publication types: Journal Article
Publication Status: ppublish
Publication Status: ppublish
Abstract
Cancer diagnosis, prognosis, and therapy response predictions from tissue specimens highly depend on the phenotype and topological distribution of constituting histological entities. Thus, adequate tissue representations for encoding histological entities is imperative for computer aided cancer patient care. To this end, several approaches have leveraged cell-graphs, capturing the cell-microenvironment, to depict the tissue. These allow for utilizing graph theory and machine learning to map the tissue representation to tissue functionality, and quantify their relationship. Though cellular information is crucial, it is incomplete alone to comprehensively characterize complex tissue structure. We herein treat the tissue as a hierarchical composition of multiple types of histological entities from fine to coarse level, capturing multivariate tissue information at multiple levels. We propose a novel multi-level hierarchical entity-graph representation of tissue specimens to model the hierarchical compositions that encode histological entities as well as their intra- and inter-entity level interactions. Subsequently, a hierarchical graph neural network is proposed to operate on the hierarchical entity-graph and map the tissue structure to tissue functionality. Specifically, for input histology images, we utilize well-defined cells and tissue regions to build HierArchical Cell-to-Tissue (HACT) graph representations, and devise HACT-Net, a message passing graph neural network, to classify the HACT representations. As part of this work, we introduce the BReAst Carcinoma Subtyping (BRACS) dataset, a large cohort of Haematoxylin & Eosin stained breast tumor regions-of-interest, to evaluate and benchmark our proposed methodology against pathologists and state-of-the-art computer-aided diagnostic approaches. Through comparative assessment and ablation studies, our proposed method is demonstrated to yield superior classification results compared to alternative methods as well as individual pathologists. The code, data, and models can be accessed at https://github.com/histocartography/hact-net.
Keywords
Benchmarking, Histological Techniques, Humans, Neural Networks, Computer, Prognosis, Breast cancer classification, Breast cancer dataset, Cell graph representation, Digital pathology, Hierarchical graph neural network, Hierarchical tissue representation, Tissue graph representation
Pubmed
Web of science
Open Access
Yes
Create date
17/11/2021 12:50
Last modification date
16/09/2023 6:09