虹膜变化动态分析和基于 AS-OCT 视频的自动闭角分类深度学习系统,Eye and Vision

当前位置： X-MOL 学术 › Eye and Vis. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

虹膜变化动态分析和基于 AS-OCT 视频的自动闭角分类深度学习系统
Eye and Vision ( IF 4.1 ) Pub Date : 2022-11-05 , DOI: 10.1186/s40662-022-00314-1
Luoying Hao _{1,

2} , Yan Hu ₁ , Yanwu Xu ₃ , Huazhu Fu ₄ , Hanpei Miao ₁ , Ce Zheng ₅ , Jiang Liu _{1,

6}

Affiliation

研究动态虹膜变化与原发性闭角疾病 (PACD) 与眼前节光学相干断层扫描 (AS-OCT) 视频之间的关联，并开发用于闭角筛查的自动深度学习系统并验证其性能。总共包括 369 个 AS-OCT 视频（19,940 帧）——159 个闭角受试者和 210 个正常对照（使用不同 AS-OCT 捕获设备的两个数据集）——被包括在内。在资深眼科医生的指导下，根据动态临床参数（瞳孔直径）分析虹膜变化（瞳孔收缩）与PACD的相关性。然后开发了一个时间网络来从视频中学习有区别的时间特征。将数据集随机分成训练集，并使用测试集和五重分层交叉验证来评估性能。对于动态临床参数评估，闭角眼的平均瞳孔收缩速度 (VPC) (0.470 mm/s) 显着低于正常眼 (0.571 mm/s) (P < 0.001)，其加速也是如此。瞳孔收缩（APC，3.512 mm/s2 vs. 5.256 mm/s2；P < 0.001）。对于我们的时间网络，使用 AS-OCT 图像、原始 AS-OCT 视频和对齐的 AS-OCT 视频的系统曲线下面积分别为 0.766（95% CI：0.610–0.923）与 0.820（95% CI： 0.680–0.961) vs. 0.905 (95% CI: 0.802–1.000) (对于 Casia 数据集) 和 0.767 (95% CI: 0.620–0.914) vs. 0.837 (95% CI: 0.713–0.961) vs. 0.919 (95% CI：0.831–1.000）（对于蔡司数据集）。结果显示，相对而言，闭角眼的虹膜对光照的反应比正常眼的虹膜伸展更少。此外，

"点击查看英文标题和摘要"

Dynamic analysis of iris changes and a deep learning system for automated angle-closure classification based on AS-OCT videos

To study the association between dynamic iris change and primary angle-closure disease (PACD) with anterior segment optical coherence tomography (AS-OCT) videos and develop an automated deep learning system for angle-closure screening as well as validate its performance. A total of 369 AS-OCT videos (19,940 frames)—159 angle-closure subjects and 210 normal controls (two datasets using different AS-OCT capturing devices)—were included. The correlation between iris changes (pupil constriction) and PACD was analyzed based on dynamic clinical parameters (pupil diameter) under the guidance of a senior ophthalmologist. A temporal network was then developed to learn discriminative temporal features from the videos. The datasets were randomly split into training, and test sets and fivefold stratified cross-validation were used to evaluate the performance. For dynamic clinical parameter evaluation, the mean velocity of pupil constriction (VPC) was significantly lower in angle-closure eyes (0.470 mm/s) than in normal eyes (0.571 mm/s) (P < 0.001), as was the acceleration of pupil constriction (APC, 3.512 mm/s2 vs. 5.256 mm/s2; P < 0.001). For our temporal network, the areas under the curve of the system using AS-OCT images, original AS-OCT videos, and aligned AS-OCT videos were 0.766 (95% CI: 0.610–0.923) vs. 0.820 (95% CI: 0.680–0.961) vs. 0.905 (95% CI: 0.802–1.000) (for Casia dataset) and 0.767 (95% CI: 0.620–0.914) vs. 0.837 (95% CI: 0.713–0.961) vs. 0.919 (95% CI: 0.831–1.000) (for Zeiss dataset). The results showed, comparatively, that the iris of angle-closure eyes stretches less in response to illumination than in normal eyes. Furthermore, the dynamic feature of iris motion could assist in angle-closure classification.

更新日期：2022-11-05

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文