Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/26330
Title: MesoGraph: Automatic Profiling of Malignant Mesothelioma Subtypes from Histological Images
Authors: Eastwood, M
Sailem, H
Tudor, S
Gao, X
Offman, J
Karteris, E
Montero Fernandez, A
Jonigk, D
Cookson, W
Moffatt, M
Popat, S
Minhas, F
Lukas Robertus, J
Keywords: graph neural networks;multiple instance learning;mesothelioma;cancer subtyping;digital pathology
Issue Date: 23-Feb-2023
Publisher: Cornell University
Citation: Eastwood, M. et al. (2023) 'MesoGraph: Automatic Profiling of Malignant Mesothelioma Subtypes from Histological Images', arXiv:2302.12653v1 [cs.CV], pp. 1 - 20. doi: 10.48550/arXiv.2302.12653.
Abstract: Copright 2023 The Author(s). Malignant mesothelioma is classified into three histological subtypes, Epithelioid, Sarcomatoid, and Biphasic according to the relative proportions of epithelioid and sarcomatoid tumor cells present. Biphasic tumors display significant populations of both cell types. This subtyping is subjective and limited by current diagnostic guidelines and can differ even between expert thoracic pathologists when characterising the continuum of relative proportions of epithelioid and sarcomatoid components using a three class system. In this work, we develop a novel dual-task Graph Neural Network (GNN) architecture with ranking loss to learn a model capable of scoring regions of tissue down to cellular resolution. This allows quantitative profiling of a tumor sample according to the aggregate sarcomatoid association score of all the cells in the sample. The proposed approach uses only core-level labels and frames the prediction task as a dual multiple instance learning (MIL) problem. Tissue is represented by a cell graph with both cell-level morphological and regional features. We use an external multi-centric test set from Mesobank, on which we demonstrate the predictive performance of our model. We validate our model predictions through an analysis of the typical morphological features of cells according to their predicted score, finding that some of the morphological differences identified by our model match known differences used by pathologists. We further show that the model score is predictive of patient survival with a hazard ratio of 2.30. The code for the proposed approach, along with the dataset, is available at: https://github.com/measty/MesoGraph.
URI: https://bura.brunel.ac.uk/handle/2438/26330
DOI: https://doi.org/10.48550/arXiv.2302.12653
Other Identifiers: ORCID iD: Emmanouil Karteris https://orcid.org/0000-0003-3231-7267
arXiv:2302.12653v1
Appears in Collections:Dept of Life Sciences Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2023 The Author(s). This is an uncorrected, non peer reviewed article made available on arXiv under a Creative Commons (CC BY) Attribution license (https://creativecommons.org/licenses/by/4.0/).13.31 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons