A Lesion-aware Edge-based Graph Neural Network for Predicting Language Ability in Patients with Post-stroke Aphasia

TL;DR

This paper introduces LEGNet, a lesion-aware graph neural network that predicts language ability in post-stroke aphasia patients from rs-fMRI data, outperforming baseline methods and demonstrating strong generalization.

Contribution

The study presents a novel lesion-aware GNN model that integrates functional connectivity, lesion information, and subgraph learning for improved language ability prediction.

Findings

LEGNet outperforms baseline deep learning models in accuracy.

LEGNet shows superior generalization on different neuroimaging protocols.

The model effectively captures relationships between rs-fMRI connectivity and language ability.

Abstract

We propose a lesion-aware graph neural network (LEGNet) to predict language ability from resting-state fMRI (rs-fMRI) connectivity in patients with post-stroke aphasia. Our model integrates three components: an edge-based learning module that encodes functional connectivity between brain regions, a lesion encoding module, and a subgraph learning module that leverages functional similarities for prediction. We use synthetic data derived from the Human Connectome Project (HCP) for hyperparameter tuning and model pretraining. We then evaluate the performance using repeated 10-fold cross-validation on an in-house neuroimaging dataset of post-stroke aphasia. Our results demonstrate that LEGNet outperforms baseline deep learning methods in predicting language ability. LEGNet also exhibits superior generalization ability when tested on a second in-house dataset that was acquired under a slightly different neuroimaging protocol. Taken together, the results of this study highlight the potential of LEGNet in effectively learning the relationships between rs-fMRI connectivity and language ability in a patient cohort with brain lesions for improved post-stroke aphasia evaluation.