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

PURPOSE 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 presence of angle closure. DESIGN Development of an artificial intelligence automated detection system for the presence of angle closure. METHODS 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 (ACA) images with 7375 open-angle and 895 angle-closure) were examined. The deep learning angle-closure detection system for a two-class classification problem was tested by five-fold cross-validation. The deep learning system, and the automated angle-closure detection system based on quantitative features were evaluated against clinician's grading of AS-OCT images as the reference standard. RESULTS The area under the receiver operating characteristic curve (AUC) 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 AUC 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 clinician's grading of AS-OCT images as the reference standard. CONCLUSIONS The results demonstrate the potential of the deep learning system for angle-closure detection in AS-OCT images.

[1]  Tien Yin Wong,et al.  Novel association of smaller anterior chamber width with angle closure in Singaporeans. , 2010, Ophthalmology.

[2]  Alejandro F. Frangi,et al.  Segmentation and Quantification for Angle-Closure Glaucoma Assessment in Anterior Segment OCT , 2017, IEEE Transactions on Medical Imaging.

[3]  Stephen Lin,et al.  Multi-context Deep Network for Angle-Closure Glaucoma Screening in Anterior Segment OCT , 2018, MICCAI.

[4]  G. Johnson,et al.  The Burden of Trachoma in the Rural Nile Delta of Egypt : a Survey of Menofiya Governorate The Epidemiology of Ocular Trauma in Singapore : Perspective from the Emergency Service of a Large Tertiary Hospital , 2005 .

[5]  Tin Aung,et al.  Determinants of lens vault and association with narrow angles in patients from Singapore. , 2012, American journal of ophthalmology.

[6]  Huazhu Fu,et al.  Automatic anterior chamber angle structure segmentation in AS-OCT image based on label transfer , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[7]  Spaeth Gl,et al.  The normal development of the human anterior chamber angle: a new system of descriptive grading. , 1971 .

[8]  M. He,et al.  Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs. , 2018, Ophthalmology.

[9]  H. Quigley,et al.  The number of people with glaucoma worldwide in 2010 and 2020 , 2006, British Journal of Ophthalmology.

[10]  Daniel S. Kermany,et al.  Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning , 2018, Cell.

[11]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[12]  Tin Aung,et al.  Classification algorithms based on anterior segment optical coherence tomography measurements for detection of angle closure. , 2013, Ophthalmology.

[13]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[14]  Jiang Liu,et al.  Anterior chamber angle classification using multiscale histograms of oriented gradients for glaucoma subtype identification , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[16]  Hiroshi Murata,et al.  Detecting Preperimetric Glaucoma with Standard Automated Perimetry Using a Deep Learning Classifier. , 2016, Ophthalmology.

[17]  T. Wong,et al.  Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. , 2014, Ophthalmology.

[18]  E. Finkelstein,et al.  Development and Validation of a Deep Learning System for Diabetic Retinopathy and Related Eye Diseases Using Retinal Images From Multiethnic Populations With Diabetes , 2017, JAMA.

[19]  Tin Aung,et al.  Diagnostic performance of anterior chamber angle measurements for detecting eyes with narrow angles: an anterior segment OCT study. , 2010, Archives of ophthalmology.

[20]  Ravi Thomas,et al.  Anterior segment optical coherence tomography. , 2007, Ophthalmology.

[21]  Tin Aung,et al.  Association of narrow angles with anterior chamber area and volume measured with anterior-segment optical coherence tomography. , 2011, Archives of ophthalmology.

[22]  Sebastian Thrun,et al.  Dermatologist-level classification of skin cancer with deep neural networks , 2017, Nature.

[23]  Tin Aung,et al.  High-definition optical coherence tomography imaging of the iridocorneal angle of the eye. , 2009, Archives of ophthalmology.

[24]  Xiaochun Cao,et al.  Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation , 2018, IEEE Transactions on Medical Imaging.

[25]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[26]  Andrew H. Beck,et al.  Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer , 2017, JAMA.

[27]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[28]  D. Friedman,et al.  Quantitative analysis of anterior segment optical coherence tomography images: the Zhongshan Angle Assessment Program , 2008, British Journal of Ophthalmology.

[29]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.

[30]  Michael V. McConnell,et al.  Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning , 2017, Nature Biomedical Engineering.

[31]  Ann L. Albright,et al.  Prevalence of diabetic retinopathy in the United States, 2005-2008. , 2010, JAMA.

[32]  Leopold Schmetterer,et al.  Anterior segment optical coherence tomography , 2018, Progress in Retinal and Eye Research.

[33]  Pina Marziliano,et al.  Anterior Chamber Angle Shape Analysis and Classification of Glaucoma in SS-OCT Images , 2014, Journal of ophthalmology.

[34]  Jiang Liu,et al.  Automated anterior chamber angle localization and glaucoma type classification in OCT images , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[35]  Tin Aung,et al.  Assessment of the scleral spur in anterior segment optical coherence tomography images. , 2008, Archives of ophthalmology.

[36]  Y M Buys,et al.  Ultrasound biomicroscopic quantitative analysis of light-dark changes associated with pupillary block. , 1999, American journal of ophthalmology.

[37]  Liming Wang,et al.  An artificial intelligence platform for the multihospital collaborative management of congenital cataracts , 2017, Nature Biomedical Engineering.

[38]  A. Peters,et al.  A Deep Learning Algorithm for Prediction of Age-Related Eye Disease Study Severity Scale for Age-Related Macular Degeneration from Color Fundus Photography. , 2018, Ophthalmology.

[39]  Neil J. Joshi,et al.  Automated Grading of Age-Related Macular Degeneration From Color Fundus Images Using Deep Convolutional Neural Networks , 2017, JAMA ophthalmology.

[40]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[41]  Tin Aung,et al.  Association of Baseline Anterior Segment Parameters With the Development of Incident Gonioscopic Angle Closure , 2017, JAMA ophthalmology.

[42]  Xiaochun Cao,et al.  Disc-Aware Ensemble Network for Glaucoma Screening From Fundus Image , 2018, IEEE Transactions on Medical Imaging.

[43]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.