Dataset Information

Dynamic changes of anterior segment in patients with different stages of primary angle-closure in both eyes and normal subjects.

ABSTRACT: To compare changes in anterior segment parameters under light and dark (light-to-dark) conditions among eyes with chronic primary angle-closure glaucoma (CPACG), fellow eyes with confirmed or suspect primary angle-closure (PAC or PACS), and age-matched healthy eyes.Consecutive patients with CPACG in one eye and PAC/PACS in the fellow eye, as well as age-matched healthy subjects were recruited. Anterior segment optical coherence tomography measurements were conducted under light and dark conditions, and anterior chamber, lens, and iris parameters compared. Demographic and biometric factors associated with light-to-dark change in iris area were analyzed by linear regression.Fifty-seven patients (mean age 59.6±8.9 years) and 30 normal subjects matched for age (60.6±9.3 years) and sex ratio were recruited. In regards to differences under light-to-dark conditions, angle opening distance at 500 ?m (AOD500?m) and iris area during light-to-dark transition were smaller in CPACG eyes than fellow PACS/PAC eyes and normal eyes (P<0.017). Pupil diameter change was largest in normal eyes, and larger in PACS/PAC eyes than CPACG eyes (P<0.017). There was an average reduction of 0.145 mm2 in iris area for each millimeter of pupil diameter increase in CPACG eyes, 0.161 mm2 in fellow PAC/PACS eyes, and 0.165 mm2 in normal eyes. Larger iris curvature in the dark and diagnosis of PACG were significantly associated with less light-to-dark iris area changes.Dynamic changes in iris parameters with light-to-dark transition differed significantly among CPACG eyes, fellow PAC/PACS eyes, and normal eyes. Greater iris curvature under dark conditions was correlated with reduced light-to-dark change in iris area and pupil diameter, which may contribute to disease progression.

SUBMITTER: Lin J

PROVIDER: S-EPMC5436810 | biostudies-literature | 2017

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Dynamic changes of anterior segment in patients with different stages of primary angle-closure in both eyes and normal subjects.

Lin Jialiu J Wang Zhonghao Z Chung Chuchen C Xu Jianan J Dai Miaomiao M Huang Jingjing J

PloS one 20170518 5

<h4>Purpose</h4>To compare changes in anterior segment parameters under light and dark (light-to-dark) conditions among eyes with chronic primary angle-closure glaucoma (CPACG), fellow eyes with confirmed or suspect primary angle-closure (PAC or PACS), and age-matched healthy eyes.<h4>Methods</h4>Consecutive patients with CPACG in one eye and PAC/PACS in the fellow eye, as well as age-matched healthy subjects were recruited. Anterior segment optical coherence tomography measurements were conduct ...[more]

PMID: 28542344

Similar Datasets

Project description:PURPOSE:To develop and test deep learning classifiers that detect gonioscopic angle closure and primary angle closure disease (PACD) based on fully automated analysis of anterior segment OCT (AS-OCT) images. METHODS:Subjects were recruited as part of the Chinese-American Eye Study (CHES), a population-based study of Chinese Americans in Los Angeles, California, USA. Each subject underwent a complete ocular examination including gonioscopy and AS-OCT imaging in each quadrant of the anterior chamber angle (ACA). Deep learning methods were used to develop 3 competing multi-class convolutional neural network (CNN) classifiers for modified Shaffer grades 0, 1, 2, 3, and 4. Binary probabilities for closed (grades 0 and 1) and open (grades 2, 3, and 4) angles were calculated by summing over the corresponding grades. Classifier performance was evaluated by 5-fold cross-validation and on an independent test dataset. Outcome measures included area under the receiver operating characteristic curve (AUC) for detecting gonioscopic angle closure and PACD, defined as either 2 or 3 quadrants of gonioscopic angle closure per eye. RESULTS:A total of 4036 AS-OCT images with corresponding gonioscopy grades (1943 open, 2093 closed) were obtained from 791 CHES subjects. Three competing CNN classifiers were developed with a cross-validation dataset of 3396 images (1632 open, 1764 closed) from 664 subjects. The remaining 640 images (311 open, 329 closed) from 127 subjects were segregated into a test dataset. The best-performing classifier was developed by applying transfer learning to the ResNet-18 architecture. For detecting gonioscopic angle closure, this classifier achieved an AUC of 0.933 (95% confidence interval, 0.925-0.941) on the cross-validation dataset and 0.928 on the test dataset. For detecting PACD based on 2- and 3-quadrant definitions, the ResNet-18 classifier achieved AUCs of 0.964 and 0.952, respectively, on the test dataset. CONCLUSION:Deep learning classifiers effectively detect gonioscopic angle closure and PACD based on automated analysis of AS-OCT images. These methods could be used to automate clinical evaluations of the ACA and improve access to eye care in high-risk populations.

Dataset Information

Dynamic changes of anterior segment in patients with different stages of primary angle-closure in both eyes and normal subjects.

Publications

Dynamic changes of anterior segment in patients with different stages of primary angle-closure in both eyes and normal subjects.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets