Generalizable automated ischaemic stroke lesion segmentation with vision transformers

TL;DR

This paper introduces a vision transformer-based tool for automated ischemic stroke lesion segmentation in DWI images, addressing variability and limited data challenges, and proposes a new evaluation framework emphasizing fairness and robustness.

Contribution

It presents a novel high-performance segmentation model using vision transformers, integrating extensive multi-site data, and introduces a comprehensive evaluation framework for clinical applicability.

Findings

Achieved state-of-the-art segmentation accuracy.

Demonstrated robustness across diverse datasets and demographics.

Enhanced model fairness and clinical relevance.

Abstract

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.