Braided Vision Transformer for Stroke Detection in Multi-view Retinal Fundus Imaging

Researchers introduced the Braided Vision Transformer (BViT), the first vision transformer model for stroke detection using retinal fundus imaging, achieving an AUC score of 0.75 on their Stroke-Data dataset, outperforming regular vision transformers. The model analyzes macula-centric and optic nerve head-centric views from both eyes to capture inter-view relationships, offering a non-invasive, cost-effective screening alternative.

arXiv:2608.14722v1 Announce Type: new Abstract: Stroke remains a leading cause of mortality and morbidity worldwide, emphasizing the importance of its accurate and immediate assessment. Retinal fundus imaging has emerged as a promising modality for stroke assessment, as the retina reflects cerebrovascular and neurological risk factors. Contrary to conventional neuroimaging techniques, retinal fundus imaging offers a non-invasive, cost-effective, and portable alternative for rapid screening. This paper explores the feasibility of retinal fundus imaging for stroke and transient ischemic attack TIA detection using macula-centric and optic nerve head-centric views captured from both eyes. Our study introduces, to the best of our knowledge, the first vision transformer model for retinal fundus imaging in stroke assessment, offering a novel approach for capturing retinal patterns. Thereby, we propose the Braided Vision Transformer BViT model, which extracts representative features from the given multi-view images while simultaneously capturing inter-view relationships across both eyes, enabling a more informative understanding of retinal biomarkers associated with cerebrovascular events. Experiments conducted on our collected Stroke-Data dataset demonstrate that BViT achieves an AUC score of 0.75 for stroke detection, outperforming regular vision transformers.