Development and validation of a deep learning system to classify aetiology and predict anatomical outcomes of macular hole.

Yu Xiao Yijun HuWuxiu QuanYahan YangWeiyi LaiXun WangXiayin ZhangBin ZhangYuqing WuQiaowei WuBaoyi LiuXiaomin ZengZhanjie LinYing FangYu HuSongfu FengLing YuanHongmin CaiTao Li Haotian Lin Honghua Yu

Published in: The British journal of ophthalmology (2021)

Our DL-based models can accurately classify the MH aetiology and predict the MH status after VILMP. These models would help ophthalmologists in diagnosis and surgical planning of MH.

Keyphrases

deep learning
optical coherence tomography
diabetic retinopathy
artificial intelligence
type diabetes
metabolic syndrome
cone beam computed tomography