Dataset Information

Automated classification of angle-closure mechanisms based on anterior segment optical coherence tomography images via deep learning.

ABSTRACT:

Purpose

To develop and validate deep learning algorithms that can identify and classify angle-closure (AC) mechanisms using anterior segment optical coherence tomography (AS-OCT) images.

Methods

This cross-sectional study included participants of the Handan Eye Study aged ≥35 years with AC detected via gonioscopy or on the AS-OCT images. These images were classified by human experts into the following to indicate the predominant AC mechanism (ground truth): pupillary block, plateau iris configuration, or thick peripheral iris roll. A deep learning architecture, known as comprehensive mechanism decision net (CMD-Net), was developed to simulate the identification of image-level AC mechanisms by human experts. Cross-validation was performed to optimize and evaluate the model. Human-machine comparisons were conducted using a held-out and separate test sets to establish generalizability.

Results

In total, 11,035 AS-OCT images of 1455 participants (2833 eyes) were included. Among these, 8828 and 2.207 images were included in the cross-validation and held-out test sets, respectively. A separate test was formed comprising 228 images of 35 consecutive patients with AC detected via gonioscopy at our eye center. In the classification of AC mechanisms, CMD-Net achieved a mean area under the receiver operating characteristic curve (AUC) of 0.980, 0.977, and 0.988 in the cross-validation, held-out, and separate test sets, respectively. The best-performing ophthalmologist achieved an AUC of 0.903 and 0.891 in the held-out and separate test sets, respectively. And CMD-Net outperformed glaucoma specialists, achieving an accuracy of 89.9 % and 93.0 % compared to 87.0 % and 86.8 % for the best-performing ophthalmologist in the held-out and separate test sets, respectively.

Conclusions

Our study suggests that CMD-Net has the potential to classify AC mechanisms using AS-OCT images, though further validation is needed.

SUBMITTER: Zhang Y

PROVIDER: S-EPMC11334645 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated classification of angle-closure mechanisms based on anterior segment optical coherence tomography images via deep learning.

Zhang Ye Y Zhang Xiaoyue X Zhang Qing Q Lv Bin B Hu Man M Lv Chuanfeng C Ni Yuan Y Xie Guotong G Li Shuning S Zebardast Nazlee N Shweikh Yusrah Y Wang Ningli N

Heliyon 20240726 15

<h4>Purpose</h4>To develop and validate deep learning algorithms that can identify and classify angle-closure (AC) mechanisms using anterior segment optical coherence tomography (AS-OCT) images.<h4>Methods</h4>This cross-sectional study included participants of the Handan Eye Study aged ≥35 years with AC detected via gonioscopy or on the AS-OCT images. These images were classified by human experts into the following to indicate the predominant AC mechanism (ground truth): pupillary block, platea ...[more]

PMID: 39166052

Similar Datasets

Project description:Fuchs uveitis (FU) is a chronic and often unilateral ocular inflammation and characteristic iris atrophic changes, other than heterochromia, are common in FU and are key to the correct diagnosis in many cases. With the advent of anterior segment optical coherence tomography (AS-OCT), some investigators attempted to quantitatively study these atrophic changes; mostly by introducing various methods to measure iris thickness in AS-OCT images. We aimed to present an automated method in an observational case series to measure the smoothness index (SI) of the iris surface in AS-OCT images. The ratio of the length of the straight line connecting the most peripheral and central points of the anterior iris border (in nasal and temporal sides) to the actual length of this border on AS-OCT images, was defined as SI. In a uveitis referral center, twenty-two eyes of 11 patients with unilateral Fuchs uveitis (FU) (7 female) and 22 eyes of 11 healthy control subjects underwent AS-OCT imaging. Image J and a newly developed MATLAB algorithm were used for manual and automated SI measurements, respectively. Agreement between manual and automated measurements was evaluated with Bland-Altman analysis and interclass correlation coefficient. The inter-eye difference of SI was compared between the FU group and the control group. Automated mean overall SI was 0.868 ± 0.037 and 0.840 ± 0.039 in FU and healthy fellow eyes, respectively (estimated mean difference = - 0.028, 95% CI [- 0.038, - 0.018], p < 0.001). Bland- Altman plots showed good agreement between two methods in both healthy and FU eyes. The interclass correlation coefficient between the manual and automated measurements in the FU and healthy fellow eyes was 0.958 and 0.964, respectively. The inter-eye difference of overall SI was 0.029 ± 0.015 and 0.012 ± 0.008 in FU group and control group, respectively (p = 0.01). We concluded that the automated algorithm can rapidly and conveniently measure SI with results comparable to the manual method.

Project description:PurposeTo 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.MethodsSubjects 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.ResultsA 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.ConclusionDeep 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.

Project description:BackgroundSemi-supervised learning algorithms can leverage an unlabeled dataset when labeling is limited or expensive to obtain. In the current study, we developed and evaluated a semi-supervised generative adversarial networks (GANs) model that detects closed-angle on anterior segment optical coherence tomography (AS-OCT) images using a small labeled dataset.MethodsIn this cross-sectional study, a semi-supervised GANs model was developed for automatic closed-angle detection training on a small labeled and large unsupervised training dataset collected from the Joint Shantou International Eye Center of Shantou University and the Chinese University of Hong Kong (JSIEC). The closed-angle was defined as iris-trabecular contact beyond the scleral spur in AS-OCT images. We further developed two supervised deep learning (DL) models training on the same supervised dataset and the whole dataset separately. The semi-supervised GANs model and supervised DL models' performance were compared on two independent testing datasets from JSIEC (515 images) and the Department of Ophthalmology (84 images), National University Health System, respectively. The diagnostic performance was assessed by evaluation matrices, including the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).ResultsFor closed-angle detection using clinician grading of AS-OCT imaging as the reference standard, the semi-supervised GANs model showed comparable performance, with AUCs of 0.97 (95% CI, 0.96-0.99) and 0.98 (95% CI, 0.94-1.00), compared with the supervised DL model (using the whole dataset) [AUCs of 0.97 (95% CI, 0.96-0.99), and 0.97 (95% CI, 0.94-1.00)]. When training on the same small supervised dataset, the semi-supervised GANs achieved performance at least as well as, if not better than, the supervised DL model [AUCs of 0.90 (95% CI: 0.84-0.96), and 0.92 (95% CI, 0.86-0.97)].ConclusionsThe semi-supervised GANs method achieves diagnostic performance at least as good as a supervised DL model when trained on small labeled datasets. Further development of semi-supervised learning methods could be useful within clinical and research settings.Trial registration numberChiCTR2000037892.

Dataset Information

Automated classification of angle-closure mechanisms based on anterior segment optical coherence tomography images via deep learning.

Purpose

Methods

Results

Conclusions

Publications

Automated classification of angle-closure mechanisms based on anterior segment optical coherence tomography images via deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets