Deep Learning for Anterior Segment Optical Coherence Tomography to Predict the Presence of Plateau Iris

Abstract

The purpose of this study was to evaluate the diagnostic performance of deep learning (DL) anterior segment optical coherence tomography (AS-OCT) as a plateau iris prediction model. Design:We used a cross-sectional study of the development and validation of the DL system. Methods:We conducted a collaboration between a referral eye center and an informative technology department. The study enrolled 179 eyes from 142 patients with primary angle closure disease (PACD). All patients had remaining appositional angle after iridotomy. Each eye was scanned in four quadrants for both AS-OCT and ultrasound biomicroscopy (UBM). A DL algorithm for plateau iris prediction of AS-OCT was developed from training datasets and was validated in test sets. Sensitivity, specificity, and area under the receiver operating characteristics curve (AUC-ROC) of the DL for predicting plateau iris were evaluated, using UBM as a reference standard.Results: Total paired images of AS-OCT and UBM were from 716 quadrants. Plateau iris was observed with UBM in 276 (38.5%) quadrants. Trainings dataset with data augmentation were used to develop an algorithm from 2500 images, and the test set was validated from 160 images. AUC-ROC was 0.95 (95% confidence interval [CI] = 0.91 to 0.99), sensitivity was 87.9%, and specificity was 97.6%.Conclusions: DL revealed a high performance in predicting plateau iris on the noncontact AS-OCT images.

Diagnostic performance of anterior segment optical coherence tomography in detecting plateau iris

“…Kumar et al reported the prevalence of plateau iris at 30% in PACS and PACG in South-East Asian patients,17 18 while in a study in Japan, it was found in 20% of cases of PAC and PACG 21. In Indian patients, plateau iris was found in 31.7% of PACG,22 whereas in our previous report, it was found in 47.5% of PACD cases 15. The accuracy of manual grading of AS-OCT was relatively low, however, at 51%–65%, indicating a discrepancy between AS-OCT and UBM, the latter being the reference standard for PIC classification in the literature.…”

“…Computer-aided technology of deep learning (DL) may be helpful in screening for this subtype of PACD. We previously reported the good performance of DL of AS-OCT in detecting PIC in the same dataset 15. The AUC-ROC was 0.95 (95% CI=0.91 to 0.99), sensitivity was 87.9%, and specificity was 97.6%.…”

“…The present research was an associated study of the imaging in PIC described elsewhere 15. In brief, it was a cross-sectional study of the performance of AS-OCT in detection of PIC based on standardised UBM criteria, undertaken at a tertiary eye care centre in Rajavithi Hospital.…”

“…Intraobserver agreement was assessed for reproducibility of the classification on 30 images, kappa=0.79. Interobserver agreements were tested by two glaucoma specialists (KS and NP), with kappa=0.71 and 0.73, respectively 15. At eye level, UBM-PIC in at least two quadrants was defined as diagnosis of PIC (DxPIC).…”

GAN-Based Approaches for Generating Structured Data in the Medical Domain

“…GANs have also attracted a lot of interest in the medical field to generate synthetic data for various applications, such as data augmentation for patient data collected from Internet of Medical Things devices, as the process of data collection can run into trouble for various reasons and cause problems for patient monitoring, and ultimately for clinical decision-making systems [28]. GAN-based models have also been used for the fast MRI (magnetic resonance imaging) reconstruction of blurry scans [29], as well as the segmentation of meibomian glands from infrared images, i.e., automatically identifying the area of meibomian glands [30], and style transfer from UBM (Ultrasound Biomicroscopy) to AS-OCT (Anterior Segment Optical Coherence Tomography) in ophthalmology image domains [31]. VAE-GAN models further combine the architecture of both methods, i.e., they use a GAN-like architecture where the discriminator is a variational autoencoder [32].…”