Current state and future prospects of artificial intelligence in ophthalmology: a review

Artificial intelligence (AI) has emerged as a major frontier in computer science research. Although AI has broad application across many medical fields, it will have particular utility in ophthalmology and will dramatically change the diagnostic and treatment pathways for many eye conditions such as corneal ectasias, glaucoma, age‐related macular degeneration and diabetic retinopathy. However, given that AI has primarily been driven as a computer science, its concepts and terminology are unfamiliar to many medical professionals. Important key terms such as machine learning and deep learning are often misunderstood and incorrectly used interchangeably. This article presents an overview of AI and new developments relevant to ophthalmology.

[1]  D. Musch,et al.  Extended long-term outcomes of penetrating keratoplasty for keratoconus. , 2006, Ophthalmology.

[2]  Qaisar Abbas,et al.  Automatic recognition of severity level for diagnosis of diabetic retinopathy using deep visual features , 2017, Medical & Biological Engineering & Computing.

[3]  Philippe Burlina,et al.  Comparing humans and deep learning performance for grading AMD: A study in using universal deep features and transfer learning for automated AMD analysis , 2017, Comput. Biol. Medicine.

[4]  Safak Bayir,et al.  Automatic Detection of Optic Disc in Retinal Image by Using Keypoint Detection, Texture Analysis, and Visual Dictionary Techniques , 2016, Comput. Math. Methods Medicine.

[5]  J. Alfonso,et al.  Intrastromal corneal ring segment implantation in paracentral keratoconus with coincident topographic and coma axis , 2012, Journal of cataract and refractive surgery.

[6]  Woohyung Lim,et al.  Interpretation of the Outputs of a Deep Learning Model Trained with a Skin Cancer Dataset. , 2018, The Journal of investigative dermatology.

[7]  Rishab Gargeya,et al.  Automated Identification of Diabetic Retinopathy Using Deep Learning. , 2017, Ophthalmology.

[8]  Alain Saad,et al.  Validation of an Objective Keratoconus Detection System Implemented in a Scheimpflug Tomographer and Comparison With Other Methods , 2017, Cornea.

[9]  M. Vassar,et al.  Evaluating Industry Payments Among Dermatology Clinical Practice Guidelines Authors , 2017, JAMA dermatology.

[10]  Tzyy-Ping Jung,et al.  Glaucoma Progression Detection Using Structural Retinal Nerve Fiber Layer Measurements and Functional Visual Field Points , 2014, IEEE Transactions on Biomedical Engineering.

[11]  Ayala Cohen,et al.  Detection of subclinical keratoconus using an automated decision tree classification. , 2013, American journal of ophthalmology.

[12]  S. Klyce,et al.  Unilateral keratoconus. Incidence and quantitative topographic analysis. , 1997, Ophthalmology.

[13]  Peter Szolovits,et al.  The coming of age of artificial intelligence in medicine , 2009, Artif. Intell. Medicine.

[14]  Sejong Oh,et al.  Development of machine learning models for diagnosis of glaucoma , 2017, PloS one.

[15]  Z. Nagy,et al.  Accuracy of machine learning classifiers using bilateral data from a Scheimpflug camera for identifying eyes with preclinical signs of keratoconus , 2016, Journal of cataract and refractive surgery.

[16]  M. Treder,et al.  Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning , 2018, Graefe's Archive for Clinical and Experimental Ophthalmology.

[17]  Tae Keun Yoo,et al.  Artificial Neural Network Approach for Differentiating Open-Angle Glaucoma From Glaucoma Suspect Without a Visual Field Test. , 2015, Investigative ophthalmology & visual science.

[18]  Irene Ruiz Hidalgo,et al.  Evaluation of a Machine-Learning Classifier for Keratoconus Detection Based on Scheimpflug Tomography , 2016, Cornea.

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

[20]  Bianca S. Gerendas,et al.  Prediction of Anti-VEGF Treatment Requirements in Neovascular AMD Using a Machine Learning Approach. , 2017, Investigative ophthalmology & visual science.

[21]  A. Loewenstein,et al.  Automated Identification of Lesion Activity in Neovascular Age-Related Macular Degeneration. , 2016, Ophthalmology.

[22]  Hamid Safi,et al.  Early detection of diabetic retinopathy. , 2018, Survey of ophthalmology.

[23]  Bianca S. Gerendas,et al.  Machine Learning to Analyze the Prognostic Value of Current Imaging Biomarkers in Neovascular Age-Related Macular Degeneration. , 2018, Ophthalmology. Retina.

[24]  Tien Yin Wong,et al.  Glaucoma detection based on deep convolutional neural network , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[25]  T. Seiler,et al.  Riboflavin/ultraviolet-a-induced collagen crosslinking for the treatment of keratoconus. , 2003, American journal of ophthalmology.

[26]  Anjan Gudigar,et al.  Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images , 2018, Inf. Sci..

[27]  Arthur L. Samuel,et al.  Some studies in machine learning using the game of checkers , 2000, IBM J. Res. Dev..

[28]  Bianca S. Gerendas,et al.  Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning. , 2017, Ophthalmology.

[29]  C. Mazzotta,et al.  Corneal Collagen Cross-Linking With Riboflavin and Ultraviolet A Light for Pediatric Keratoconus: Ten-Year Results , 2018, Cornea.

[30]  U. Schmidt-Erfurth,et al.  Machine Learning of the Progression of Intermediate Age-Related Macular Degeneration Based on OCT Imaging. , 2017, Investigative ophthalmology & visual science.

[31]  Deniz Erdogmus,et al.  Expert Diagnosis of Plus Disease in Retinopathy of Prematurity From Computer-Based Image Analysis. , 2016, JAMA ophthalmology.

[32]  Gilmer Valdes,et al.  Artificial intelligence in radiation oncology: A specialty-wide disruptive transformation? , 2018, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[33]  Murilo Barreto Souza,et al.  Evaluation of machine learning classifiers in keratoconus detection from orbscan II examinations , 2010, Clinics.

[34]  Thomas J. Fuchs,et al.  Hybrid Deep Learning on Single Wide-field Optical Coherence tomography Scans Accurately Classifies Glaucoma Suspects , 2017, Journal of glaucoma.

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

[36]  R. P. Madden,et al.  characteristics of , 2007 .

[37]  Haibo Mi,et al.  Deep Convolutional Neural Network-Based Early Automated Detection of Diabetic Retinopathy Using Fundus Image , 2017, Molecules.

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

[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]  Aaron Y. Lee,et al.  Deep learning is effective for the classification of OCT images of normal versus Age-related Macular Degeneration , 2016, bioRxiv.

[41]  Ahmed Elsheikh,et al.  Integration of Scheimpflug-Based Corneal Tomography and Biomechanical Assessments for Enhancing Ectasia Detection. , 2017, Journal of refractive surgery.

[42]  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.

[43]  Kipp W. Johnson,et al.  Artificial Intelligence in Cardiology. , 2018, Journal of the American College of Cardiology.

[44]  Cristian Navarrete-Dechent,et al.  Automated Dermatological Diagnosis: Hype or Reality? , 2018, The Journal of investigative dermatology.

[45]  Michael D Twa,et al.  Characteristics of Corneal Ectasia After LASIK for Myopia , 2004, Cornea.

[46]  K. Balaskas,et al.  Use of a Neural Net to Model the Impact of Optical Coherence Tomography Abnormalities on Vision in Age-related Macular Degeneration. , 2018, American journal of ophthalmology.

[47]  Manoj Raju,et al.  Development of a Deep Learning Algorithm for Automatic Diagnosis of Diabetic Retinopathy , 2017, MedInfo.

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

[49]  Wesley De Neve,et al.  Few-shot Learning Using a Small-Sized Dataset of High-Resolution FUNDUS Images for Glaucoma Diagnosis , 2017, MMHealth@MM.

[50]  Miguel Caixinha,et al.  In-Vivo Automatic Nuclear Cataract Detection and Classification in an Animal Model by Ultrasounds , 2016, IEEE Transactions on Biomedical Engineering.

[51]  Ehsan Rahimy,et al.  Deep learning applications in ophthalmology , 2018, Current opinion in ophthalmology.

[52]  Jason Weston,et al.  Question Answering with Subgraph Embeddings , 2014, EMNLP.

[53]  J. Krachmer,et al.  Keratoconus and related noninflammatory corneal thinning disorders. , 1984, Survey of ophthalmology.

[54]  Jiewei Jiang,et al.  Automatic diagnosis of imbalanced ophthalmic images using a cost-sensitive deep convolutional neural network , 2017, BioMedical Engineering OnLine.

[55]  E. Siegel,et al.  Artificial Intelligence in Medicine and Cardiac Imaging: Harnessing Big Data and Advanced Computing to Provide Personalized Medical Diagnosis and Treatment , 2013, Current Cardiology Reports.

[56]  Jianqiang Li,et al.  Automatic cataract detection and grading using Deep Convolutional Neural Network , 2017, 2017 IEEE 14th International Conference on Networking, Sensing and Control (ICNSC).

[57]  Mhd Saeed Sharif,et al.  Medical image classification based on artificial intelligence approaches: A practical study on normal and abnormal confocal corneal images , 2015, Appl. Soft Comput..

[58]  N Maeda,et al.  Automated keratoconus screening with corneal topography analysis. , 1994, Investigative ophthalmology & visual science.

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

[60]  K. Shimizu,et al.  Repeatability, reproducibility, and agreement characteristics of rotating Scheimpflug photography and scanning‐slit corneal topography for corneal power measurement , 2009, Journal of cataract and refractive surgery.

[61]  Jiangtao Cui,et al.  Localization and diagnosis framework for pediatric cataracts based on slit-lamp images using deep features of a convolutional neural network , 2017, PloS one.

[62]  Michael D Twa,et al.  CLMI: The Cone Location and Magnitude Index , 2008, Cornea.

[63]  [Deep learning to support therapy decisions for intravitreal injections]. , 2018, Der Ophthalmologe : Zeitschrift der Deutschen Ophthalmologischen Gesellschaft.

[64]  Stephen Lin,et al.  Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning , 2014, IEEE Transactions on Biomedical Engineering.

[65]  M. Ziaei,et al.  Deep anterior lamellar keratoplasty versus penetrating keratoplasty for treating keratoconus. , 2014, The Cochrane database of systematic reviews.

[66]  Y. Rabinowitz,et al.  KISA% index: a quantitative videokeratography algorithm embodying minimal topographic criteria for diagnosing keratoconus. , 1999, Journal of cataract and refractive surgery.

[67]  Lukás Burget,et al.  Strategies for training large scale neural network language models , 2011, 2011 IEEE Workshop on Automatic Speech Recognition & Understanding.

[68]  M. Al-Jarrah,et al.  Non-proliferative diabetic retinopathy symptoms detection and classification using neural network , 2017, Journal of medical engineering & technology.

[69]  A. Ozcan,et al.  Computational Sensing of Staphylococcus aureus on Contact Lenses Using 3D Imaging of Curved Surfaces and Machine Learning. , 2018, ACS nano.

[70]  Michael J Lynn,et al.  Risk assessment for ectasia after corneal refractive surgery. , 2008, Ophthalmology.

[71]  Daniel B. Neill,et al.  Using Artificial Intelligence to Improve Hospital Inpatient Care , 2013, IEEE Intelligent Systems.

[72]  Francesco Versaci,et al.  Use of a support vector machine for keratoconus and subclinical keratoconus detection by topographic and tomographic data. , 2012, Ophthalmology.

[73]  Hideo Yokota,et al.  Classification of optic disc shape in glaucoma using machine learning based on quantified ocular parameters , 2017, PloS one.

[74]  Haipeng Shen,et al.  Artificial intelligence in healthcare: past, present and future , 2017, Stroke and Vascular Neurology.

[75]  O Findl,et al.  Medical interventions for primary open angle glaucoma and ocular hypertension. , 2007, The Cochrane database of systematic reviews.