Center for Genetics, National Research Institute for Family Planning, Beijing 100081, China
Key Laboratory of Intelligent Information Processing, Advanced Computer Research Center, State Key Laboratory of Computer Architecture, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China.
Biosci Rep. 2018 Dec 7;38(6). doi: 10.1042/BSR20180497. Print 2018 Dec 21.
There is a disparity between the increasing application of digital retinal imaging to neonatal ocular screening and slowly growing number of pediatric ophthalmologists. Assistant tools that can automatically detect ocular disorders may be needed. In present study, we develop a deep convolutional neural network (DCNN) for automated classification and grading of retinal hemorrhage. We used 48,996 digital fundus images from 3770 newborns with retinal hemorrhage of different severity (grade 1, 2 and 3) and normal controls from a large cross-sectional investigation in China. The DCNN was trained for automated grading of retinal hemorrhage (multiclass classification problem: hemorrhage-free and grades 1, 2 and 3) and then validated for its performance level. The DCNN yielded an accuracy of 97.85 to 99.96%, and the area under the receiver operating characteristic curve was 0.989-1.000 in the binary classification of neonatal retinal hemorrhage (i.e., one classification vs. the others). The overall accuracy with regard to the multiclass classification problem was 97.44%. This is the first study to show that a DCNN can detect and grade neonatal retinal hemorrhage at high performance levels. Artificial intelligence will play more positive roles in ocular healthcare of newborns and children.
数字视网膜成像在新生儿眼部筛查中的应用日益广泛，而儿科眼科医生的数量却在缓慢增长，两者之间存在差距。可能需要能够自动检测眼部疾病的辅助工具。在本研究中，我们开发了一种深度卷积神经网络（DCNN），用于自动分类和分级视网膜出血。我们使用了来自中国一项大型横断面研究的 3770 名患有不同严重程度（1 级、2 级和 3 级）视网膜出血和正常对照的新生儿的 48996 张眼底数字图像。DCNN 经过训练可自动分级视网膜出血（多类分类问题：无出血和 1 级、2 级和 3 级），然后验证其性能水平。DCNN 在新生儿视网膜出血的二分类（即一种分类与其他分类）中产生了 97.85%至 99.96%的准确率，并且接收器工作特征曲线下的面积为 0.989-1.000。多类分类问题的总体准确率为 97.44%。这是第一项表明 DCNN 可以以较高的性能水平检测和分级新生儿视网膜出血的研究。人工智能将在新生儿和儿童的眼部保健中发挥更加积极的作用。
