xCG: Explainable Cell Graphs for Survival Prediction in Non-Small Cell Lung Cancer

TL;DR

This paper introduces xCG, an explainable graph neural network model that predicts survival in lung adenocarcinoma patients by analyzing tumor microenvironment cell graphs, providing interpretable risk attributions.

Contribution

The paper presents an explainable cell graph approach with a novel layer-wise relevance propagation method for survival prediction in lung cancer, integrating phenotypic cell information.

Findings

xCG achieves accurate survival predictions on IMC data.

Incorporating cancer stage improves risk estimation.

Model ensembling enhances prediction robustness.

Abstract

Understanding how deep learning models predict oncology patient risk can provide critical insights into disease progression, support clinical decision-making, and pave the way for trustworthy and data-driven precision medicine. Building on recent advances in the spatial modeling of the tumor microenvironment using graph neural networks, we present an explainable cell graph (xCG) approach for survival prediction. We validate our model on a public cohort of imaging mass cytometry (IMC) data for 416 cases of lung adenocarcinoma. We explain survival predictions in terms of known phenotypes on the cell level by computing risk attributions over cell graphs, for which we propose an efficient grid-based layer-wise relevance propagation (LRP) method. Our ablation studies highlight the importance of incorporating the cancer stage and model ensembling to improve the quality of risk estimates. Our xCG method, together with the IMC data, is made publicly available to support further research.