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

Hao，Luoying1,6; Hu，Yan1; Xu，Yanwu2; Fu，Huazhu3; Miao，Hanpei1; Zheng，Ce5; Liu，Jiang1,4

2022-12-01

10.1186/s40662-022-00314-1

Eye and Vision   Impact Factor & Quartile

2326-0254

Background: 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. Methods: 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. Results: 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/svs. 5.256 mm/s; 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). Conclusions: 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.

Angle-closure AS-OCT videos Deep learning Glaucoma Iris change

SCI

English

First ; Corresponding

Guangdong Provincial Key Laboratory of Urology[2020B121201001];National Outstanding Youth Science Fund Project of National Natural Science Foundation of China[8210072776];

WOS:000879007600001

2-s2.0-85141401945

Scopus

1.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.Intelligent Healthcare Unit,Beijing,Baidu,China
3.Institute of High Performance Computing,Agency for Science,Technology and Research,Singapore,Singapore
4.School of Ophthalmology and Optometry,School of Biomedical Engineering,Wenzhou Medical University,Wenzhou,China
5.Department of Ophthalmology,Xinhua Hospital,Shanghai Jiaotong University School of Medicine,Shanghai,China
6.School of Computer Science,University of Birmingham,Birmingham,United Kingdom

Hao，Luoying,Hu，Yan,Xu，Yanwu,et al. Dynamic analysis of iris changes and a deep learning system for automated angle-closure classification based on AS-OCT videos[J]. Eye and Vision,2022,9(1).

Hao，Luoying.,Hu，Yan.,Xu，Yanwu.,Fu，Huazhu.,Miao，Hanpei.,...&Liu，Jiang.(2022).Dynamic analysis of iris changes and a deep learning system for automated angle-closure classification based on AS-OCT videos.Eye and Vision,9(1).

Hao，Luoying,et al."Dynamic analysis of iris changes and a deep learning system for automated angle-closure classification based on AS-OCT videos".Eye and Vision 9.1(2022).