深度学习
冲程(发动机)
人工智能
医学
视网膜
学习迁移
物理医学与康复
急性中风
视网膜
计算机科学
计算机视觉
验光服务
神经科学
缺血性中风
眼电学
临床神经学
听力学
神经影像学
作者
Minyan Ge,Yuchun Wang,Shumao Xu
标识
DOI:10.1038/s41746-025-02021-2
摘要
Silent brain infarctions (SBIs), affecting 20% of adults and increasing stroke risk, evade routine MRI screening. While retinal scans offer a “window to the brain,” prior AI failed to simultaneously detect SBIs and predict strokes. DeepRETStroke overcomes this by analysing eye scans. Trained on ~900,000 images, it uses deep learning combining self-supervised pattern recognition from unlabeled images, semi-supervised SBI detection with limited MRI, and knowledge transfer refinement, transforming eye exams into affordable stroke screenings.
科研通智能强力驱动
Strongly Powered by AbleSci AI