A Deep Learning System for Automated Angle-Closure Detection in Anterior Segment Optical Coherence Tomography Images

• Published in: American journal of ophthalmology Vol. 203; pp. 37 - 45
• Main Authors: Fu, Huazhu, Baskaran, Mani, Xu, Yanwu, Lin, Stephen, Wong, Damon Wing Kee, Liu, Jiang, Tun, Tin A., Mahesh, Meenakshi, Perera, Shamira A., Aung, Tin
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.07.2019; Elsevier Limited
• Subjects: Anterior Eye Segment - diagnostic imaging; Artificial Intelligence; Automation; Data analysis; Datasets; Deep Learning; Diabetic retinopathy; Female; Funding; Glaucoma; Glaucoma, Angle-Closure - diagnosis; Gonioscopy - methods; Humans; Lasers; Machine learning; Male; Medical imaging; Middle Aged; Ophthalmology; ROC Curve; Tomography, Optical Coherence - methods; Singapore
• ISSN: 0002-9394; 1879-1891; 1879-1891
• DOI: 10.1016/j.ajo.2019.02.028

Anterior segment optical coherence tomography (AS-OCT) provides an objective imaging modality for visually identifying anterior segment structures. An automated detection system could assist ophthalmologists in interpreting AS-OCT images for the presence of angle closure. Development of an artificial intelligence automated detection system for the presence of angle closure. A deep learning system for automated angle-closure detection in AS-OCT images was developed, and this was compared with another automated angle-closure detection system based on quantitative features. A total of 4135 Visante AS-OCT images from 2113 subjects (8270 anterior chamber angle images with 7375 open-angle and 895 angle-closure) were examined. The deep learning angle-closure detection system for a 2-class classification problem was tested by 5-fold cross-validation. The deep learning system and the automated angle-closure detection system based on quantitative features were evaluated against clinicians' grading of AS-OCT images as the reference standard. The area under the receiver operating characteristic curve of the system using quantitative features was 0.90 (95% confidence interval [CI] 0.891–0.914) with a sensitivity of 0.79 ± 0.037 and a specificity of 0.87 ± 0.009, while the area under the receiver operating characteristic curve of the deep learning system was 0.96 (95% CI 0.953–0.968) with a sensitivity of 0.90 ± 0.02 and a specificity of 0.92 ± 0.008, against clinicians' grading of AS-OCT images as the reference standard. The results demonstrate the potential of the deep learning system for angle-closure detection in AS-OCT images.