New Braided Vision Transformer detects stroke from retinal images

Researchers have developed a novel Braided Vision Transformer (BViT) model for detecting stroke using retinal fundus imaging. This approach leverages multi-view images from both eyes to capture subtle retinal patterns indicative of cerebrovascular events. In experiments on a custom dataset, the BViT model achieved an AUC score of 0.75 for stroke detection, outperforming standard vision transformers. AI

IMPACT This research could lead to more accessible and non-invasive stroke screening tools, potentially improving early detection and patient outcomes.

RANK_REASON The cluster contains a research paper introducing a novel model for a specific medical application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Braided Vision Transformer
• Hugging Face
• Stroke data banks
• vision transformer

• paper
• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →