MesoGraph: Automatic Profiling of Malignant Mesothelioma Subtypes from Histological Images

TL;DR

This paper introduces MesoGraph, a novel graph neural network approach for automatic, quantitative profiling of mesothelioma subtypes from histological images, improving diagnostic consistency and predicting patient survival.

Contribution

The work presents a dual-task GNN with ranking loss for cellular-level tumor profiling using only core-level labels, advancing automated histopathological analysis.

Findings

Model achieves high predictive performance on multi-centric test set.

Morphological features identified by the model align with known pathological differences.

Model score is predictive of patient survival with a hazard ratio of 2.30.

Abstract

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.