Hierarchical graph representations in digital pathology

Autor: Giosuè Scognamiglio, Daniel Riccio, Anna Maria Anniciello, Jean-Philippe Thiran, Pushpak Pati, Gerardo Botti, Nadia Brancati, Antonio Foncubierta-Rodríguez, Maria Gabrani, Florinda Feroce, Estelle Dubruc, Maryse Fiche, Maria Frucci, Orcun Goksel, Guillaume Jaume, Giuseppe De Pietro, Maurizio Di Bonito
Rok vydání: 2022
Předmět:
FOS: Computer and information sciences
Breast cancer datase
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
Health Informatics
Breast cancer dataset
ENCODE
image-analysis
Digital pathology
Breast cancer classification
Cell graph representation
Tissue graph representation
Hierarchical tissue representation
Hierarchical graph neural network
Encoding (memory)
Hi-erarchical tissue representation
Humans
dataset
Radiology
Nuclear Medicine and imaging
Representation (mathematics)
Hierarchical graph neuralnetwork
Radiological and Ultrasound Technology
business.industry
Histological Techniques
Medicinsk bildbehandling
Message passing
cancer statistics
Graph theory
Pattern recognition
Prognosis
Computer Graphics and Computer-Aided Design
Benchmarking
Medical Image Processing
network
Graph (abstract data type)
Neural Networks
Computer
Computer Vision and Pattern Recognition
Artificial intelligence
business
Zdroj: Medical Image Analysis, 75
Medical image analysis
75 (2022). doi:10.1016/j.media.2021.102264
info:cnr-pdr/source/autori:P. Pati, G. Jaume, A. Foncubierta, F. Feroce, A. M. Anniciello, G. Scognamiglio, N. Brancati, M.Fiche, E. Dubruc, D.Riccio, M. Di Bonito, G. De Pietro, G. Botti, J. P. Thiran, M. Frucci, O. Goksel, M. Gabrani/titolo:Hierarchical Graph Representations in Digital Pathology/doi:10.1016%2Fj.media.2021.102264/rivista:Medical image analysis (Print)/anno:2022/pagina_da:/pagina_a:/intervallo_pagine:/volume:75
ISSN: 1361-8415
1361-8423
DOI: 10.1016/j.media.2021.102264
Popis: 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.
Medical Image Analysis, 75
ISSN:1361-8415
ISSN:1361-8423
Databáze: OpenAIRE
Externí odkaz: