Dataset Information

From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning.

ABSTRACT: Anterior chamber depth (ACD) is a major risk factor of angle closure disease, and has been used in angle closure screening in various populations. However, ACD is measured from ocular biometer or anterior segment optical coherence tomography (AS-OCT), which are costly and may not be readily available in primary care and community settings. Thus, this proof-of-concept study aims to predict ACD from low-cost anterior segment photographs (ASPs) using deep-learning (DL). We included 2,311 pairs of ASPs and ACD measurements for algorithm development and validation, and 380 pairs for algorithm testing. We captured ASPs with a digital camera mounted on a slit-lamp biomicroscope. Anterior chamber depth was measured with ocular biometer (IOLMaster700 or Lenstar LS9000) in data used for algorithm development and validation, and with AS-OCT (Visante) in data used for testing. The DL algorithm was modified from the ResNet-50 architecture, and assessed using mean absolute error (MAE), coefficient-of-determination (R2), Bland-Altman plot and intraclass correlation coefficients (ICC). In validation, our algorithm predicted ACD with a MAE (standard deviation) of 0.18 (0.14) mm; R2 = 0.63. The MAE of predicted ACD was 0.18 (0.14) mm in eyes with open angles and 0.19 (0.14) mm in eyes with angle closure. The ICC between actual and predicted ACD measurements was 0.81 (95% CI 0.77, 0.84). In testing, our algorithm predicted ACD with a MAE of 0.23 (0.18) mm; R2 = 0.37. Saliency maps highlighted the pupil and its margin as the main structures used in ACD prediction. This study demonstrates the possibility of predicting ACD from ASPs via DL. This algorithm mimics an ocular biometer in making its prediction, and provides a foundation to predict other quantitative measurements that are relevant to angle closure screening.

SUBMITTER: Soh ZD

PROVIDER: S-EPMC9931242 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning.

Soh Zhi Da ZD Jiang Yixing Y S/O Ganesan Sakthi Selvam SS Zhou Menghan M Nongiur Monisha M Majithia Shivani S Tham Yih Chung YC Rim Tyler Hyungtaek TH Qian Chaoxu C Koh Victor V Aung Tin T Wong Tien Yin TY Xu Xinxing X Liu Yong Y Cheng Ching-Yu CY

PLOS digital health 20230201 2

Anterior chamber depth (ACD) is a major risk factor of angle closure disease, and has been used in angle closure screening in various populations. However, ACD is measured from ocular biometer or anterior segment optical coherence tomography (AS-OCT), which are costly and may not be readily available in primary care and community settings. Thus, this proof-of-concept study aims to predict ACD from low-cost anterior segment photographs (ASPs) using deep-learning (DL). We included 2,311 pairs of A ...[more]

PMID: 36812642

Similar Datasets

Project description:PurposeTo develop a deep learning (DL) algorithm for predicting anterior chamber depth (ACD) from smartphone-acquired anterior segment photographs.MethodsFor 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.ResultsIn 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.ConclusionsWe 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.

Project description:PrcisCompared with normal subjects with similar shallow anterior chamber depth (ACD), patients with primary angle closure disease (PACD) had narrower angle structures measured by swept-source optical coherence tomography (SS-OCT) at 250 μm from scleral spur (very root of iris), especially along oblique and vertical axis.PurposeTo examine anterior segment structures in normal subjects whose ACD was shallow on slit-lamp examination but did not meet the diagnostic criteria of PACD, and to compare them with PACD patients with similar ACD.Materials and methodsPatients were recruited from glaucoma clinic at Zhongshan Ophthalmic Center. A total of 40 eyes from 29 PACD patients and 40 eyes from 34 normal subjects received full ophthalmic examination and CASIA SS-1000 OCT tests. PACD eyes and control eyes were 1:1 matched for ACD at 0 degree of scan. Generalized linear model that accounted for inter-eye correlation was used to compare differences between the 2 groups for intraocular pressure and SS-OCT parameters. P-values were adjusted for multiple comparisons using the Bonferroni method.ResultsThe PACD and control groups had similar age, but the PACD group had a significantly higher intraocular pressure (18.4 vs. 14.0 mm Hg, P=0.005). Angle parameters, representative of angle area, such as angle recess area and trabecular iris space area measured at 250 μm along axes of 90, 135, 225, and 315 degrees were significantly smaller in PACD group than those of control group (adjusted P<0.05), while most of angle parameters at 500 and 750 μm, volume parameters, and anterior chamber parameters, were similar (adjusted P>0.05).ConclusionsIn PACD patients compared with normal subjects with similar anterior chamber shallowing, OCT findings measured at the iris root 250 μm from the scleral spur, especially in the oblique and vertical axes, including angle recess area and trabecular iris space area, may match gonioscopic findings more closely and provide further insight into mechanisms of PACD.

Dataset Information

From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning.

Publications

From 2 dimensions to 3rd dimension: Quantitative prediction of anterior chamber depth from anterior segment photographs via deep-learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets