Lu Li, Ren Peifang, Lu Qianyi, Zhou Enliang, Yu Wangshu, Huang Jiani, He Xiaoying, Han Wei
Department of Ophthalmology, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China.
Department of Ophthalmology, The First Affiliated Hospital of University of Science and Technology of China, Hefei, China.
Ann Transl Med. 2021 Feb;9(3):226. doi: 10.21037/atm-20-3275.
This study aimed to establish and evaluate an artificial intelligence-based deep learning system (DLS) for automatic detection of diabetic retinopathy. This could be important in developing an advanced tele-screening system for diabetic retinopathy.
A DLS with a convolutional neural network was developed to recognize fundus images of referable diabetic retinopathy. A total data set of 41,866 color fundus images were obtained from 17 cities in the Yangtze River Delta Urban Agglomeration (YRDUA). Five experienced retinal specialists and 15 ophthalmologists were recruited to verify images. For training, 80% of the data set was used, and the other 20% served as the validation data set. To effectively understand the learning process, the DLS automatically superimposed a heatmap on the original image. The regions utilized by the DLS were highlighted for diagnosis.
Using the local validation data set, the DLS achieved an area under the curve of 0.9824. Based on the manual screening criteria, an operating point was set at about 0.9 sensitivity to evaluate the DLS. Specificity was recorded at 0.9609 and sensitivity was 0.9003. The DLSs showed excellent reliability, repeatability, and high efficiency. After analyzing the misclassification, it was found that 88.6% of the false-positives were mild non-proliferative diabetic retinopathy (NPDR) whereas, 81.6% of the false-negatives were intraretinal microvascular abnormalities.
The DLS efficiently detected fundus images from complex sources in the real world. Incorporating DLS technology in tele-screening will advance the current screening programs to offer a cost-effective and time-efficient solution for detecting diabetic retinopathy.
本研究旨在建立并评估一种基于人工智能的深度学习系统（DLS），用于自动检测糖尿病视网膜病变。这对于开发先进的糖尿病视网膜病变远程筛查系统可能具有重要意义。
开发了一种带有卷积神经网络的DLS，用于识别可转诊糖尿病视网膜病变的眼底图像。从长江三角洲城市群（YRDUA）的17个城市获取了总共41,866张彩色眼底图像的数据集。招募了5名经验丰富的视网膜专家和15名眼科医生来验证图像。对于训练，使用了80%的数据集，另外20%用作验证数据集。为了有效理解学习过程，DLS自动在原始图像上叠加一个热图。DLS用于诊断的区域被突出显示。
使用局部验证数据集，DLS的曲线下面积达到0.9824。根据人工筛查标准，设定了一个约0.9灵敏度的操作点来评估DLS。特异性记录为0.9609，灵敏度为0.9003。DLS显示出出色的可靠性、可重复性和高效率。在分析错误分类后，发现88.6%的假阳性是轻度非增殖性糖尿病视网膜病变（NPDR），而81.6%的假阴性是视网膜内微血管异常。
DLS有效地检测了来自现实世界复杂来源的眼底图像。将DLS技术纳入远程筛查将推动当前的筛查计划，为检测糖尿病视网膜病变提供一种经济高效且节省时间的解决方案。
