Ischaemic stroke, a leading cause of death and disability, critically relies on neuroimaging for characterising the anatomical pattern of injury. Diffusion-weighted imaging (DWI) provides the highest expressivity in ischemic stroke but poses substantial challenges for automated lesion segmentation: susceptibility artefacts, morphological heterogeneity, age-related comorbidities, time-dependent signal dynamics, instrumental variability, and limited labelled data. Current U-Net-based models therefore underperform, a problem accentuated by inadequate evaluation metrics that focus on mean performance, neglecting anatomical, subpopulation, and acquisition-dependent variability. Here, we present a high-performance DWI lesion segmentation tool addressing these challenges through optimized vision transformer-based architectures, integration of 3563 annotated lesions from multi-site data, and algorithmic enhancements, achieving state-of-the-art results. We further propose a novel evaluative framework assessing model fidelity, equity (across demographics and lesion subtypes), anatomical precision, and robustness to instrumental variability, promoting clinical and research utility. This work advances stroke imaging by reconciling model expressivity with domain-specific challenges and redefining performance benchmarks to prioritize equity and generalizability, critical for personalized medicine and mechanistic research.
@article{arxiv.2502.06939,
title = {Generalizable automated ischaemic stroke lesion segmentation with vision transformers},
author = {Chris Foulon and Robert Gray and James K. Ruffle and Jonathan Best and Tianbo Xu and Henry Watkins and Jane Rondina and Guilherme Pombo and Dominic Giles and Paul Wright and Marcela Ovando-Tellez and H. Rolf Jäger and Jorge Cardoso and Sebastien Ourselin and Geraint Rees and Parashkev Nachev},
journal= {arXiv preprint arXiv:2502.06939},
year = {2025}
}