School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.
Department of Ophthalmology, The Affiliated Hospital of Southwest Medical University, Luzhou, China.
Ophthalmic Res. 2023;66(1):238-246. doi: 10.1159/000525929. Epub 2022 Sep 28.
Development and validation of a deep learning algorithm to automatically identify and locate epiretinal memberane (ERM) regions in OCT images.
OCT images of 468 eyes were retrospectively collected from a total of 404 ERM patients. One expert manually annotated the ERM regions for all images. A total of 422 images (90%) and the remainig 46 images (10%) were used as the training dataset and validation dataset for deep learning algorithm training and validation, respectively. One senior and one junior clinician read the images. The diagnostic results were compared.
The algorithm accurately segmented and located the ERM regions in OCT images. The image-level accuracy was 95.65%, and the ERM region-level accuracy was 90.14%, respectively. In comparison experiments, the accuracies of the junior clinician improved from 85.00% to 61.29% without the assistance of the algorithm to 100.00% and 90.32% with the assistance of the algorithm. The corresponding results of the senior clinician were 96.15%, 95.00% without the assistance of the algorithm, and 96.15%, 97.50% with the assistance of the algorithm.
The developed deep learning algorithm can accurately segment ERM regions in OCT images. This deep learning approach may help clinicians in clinical diagnosis with better accuracy and efficiency.
开发和验证一种深度学习算法，以自动识别和定位 OCT 图像中的视网膜内膜（ERM）区域。
回顾性收集了来自 404 名 ERM 患者的 468 只眼的 OCT 图像。一名专家对所有图像的 ERM 区域进行了手动注释。总共 422 张图像（90%）和剩下的 46 张图像（10%）被分别用于深度学习算法的训练数据集和验证数据集。一名高级医生和一名初级医生阅读图像。比较诊断结果。
该算法能够准确地对 OCT 图像中的 ERM 区域进行分割和定位。图像级别的准确率为 95.65%，ERM 区域级别的准确率为 90.14%。在对比实验中，初级医生的准确率从无算法辅助时的 85.00%提高到有算法辅助时的 100.00%和 90.32%，而高级医生的准确率分别为 96.15%和 97.50%。
开发的深度学习算法可以准确地分割 OCT 图像中的 ERM 区域。这种深度学习方法可能有助于提高临床医生的诊断准确性和效率。
