Smartphone-Acquired Anterior Segment Images for Deep Learning Prediction of Anterior Chamber Depth: A Proof-of-Concept Study

Chaoxu Qian; Yixing Jiang; Zhi Da Soh; Ganesan Sakthi Selvam; Shuyuan Xiao; Yih-Chung Tham; Xinxing Xu; Yong Liu; Jun Li; Hua Zhong; Ching-Yu Cheng

doi:10.3389/fmed.2022.912214

Smartphone-Acquired Anterior Segment Images for Deep Learning Prediction of Anterior Chamber Depth: A Proof-of-Concept Study

Front Med (Lausanne). 2022 Jun 23:9:912214. doi: 10.3389/fmed.2022.912214. eCollection 2022.

Authors

Chaoxu Qian^{1

2}, Yixing Jiang³, Zhi Da Soh^{1

4}, Ganesan Sakthi Selvam³, Shuyuan Xiao², Yih-Chung Tham^{1

4

5}, Xinxing Xu³, Yong Liu³, Jun Li⁶, Hua Zhong², Ching-Yu Cheng^{1

4

5}

Affiliations

¹ Singapore Eye Research Institute, Singapore National Eye Centre, Singapore, Singapore.
² Department of Ophthalmology, The First Affiliated Hospital of Kunming Medical University, Kunming, China.
³ Institute of High Performance Computing, Agency for Science, Technology and Research (AStar), Singapore, Singapore.
⁴ Department of Ophthalmology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
⁵ Ophthalmology and Visual Sciences Academic Clinical Program (Eye ACP), Duke-NUS Medical School, Singapore, Singapore.
⁶ Department of Ophthalmology, The Second People's Hospital of Yunnan Province, Kunming, China.

Abstract

Purpose: To develop a deep learning (DL) algorithm for predicting anterior chamber depth (ACD) from smartphone-acquired anterior segment photographs.

Methods: For algorithm development, we included 4,157 eyes from 2,084 Chinese primary school students (aged 11-15 years) from Mojiang Myopia Progression Study (MMPS). All participants had with ACD measurement measured with Lenstar (LS 900) and anterior segment photographs acquired from a smartphone (iPhone Xs), which was mounted on slit lamp and under diffuses lighting. The anterior segment photographs were randomly selected by person into training (80%, no. of eyes = 3,326) and testing (20%, no. of eyes = 831) dataset. We excluded participants with intraocular surgery history or pronounced corneal haze. A convolutional neural network was developed to predict ACD based on these anterior segment photographs. To determine the accuracy of our algorithm, we measured the mean absolute error (MAE) and coefficient of determination (R ²) were evaluated. Bland Altman plot was used to illustrate the agreement between DL-predicted and measured ACD values.

Results: In the test set of 831 eyes, the mean measured ACD was 3.06 ± 0.25 mm, and the mean DL-predicted ACD was 3.10 ± 0.20 mm. The MAE was 0.16 ± 0.13 mm, and R ² was 0.40 between the predicted and measured ACD. The overall mean difference was -0.04 ± 0.20 mm, with 95% limits of agreement ranging between -0.43 and 0.34 mm. The generated saliency maps showed that the algorithm mainly utilized central corneal region (i.e., the site where ACD is clinically measured typically) in making its prediction, providing further plausibility to the algorithm's prediction.

Conclusions: We developed a DL algorithm to estimate ACD based on smartphone-acquired anterior segment photographs. Upon further validation, our algorithm may be further refined for use as a ACD screening tool in rural localities where means of assessing ocular biometry is not readily available. This is particularly important in China where the risk of primary angle closure disease is high and often undetected.

Keywords: anterior chamber depth; deep learning; glaucoma; primary angle-closure glaucoma; smartphone.