Artificial Intelligence and Glaucoma: Going Back to Basics

Abstract There has been a recent surge in the number of publications centered on the use of artificial intelligence (AI) to diagnose various systemic diseases. The Food and Drug Administration has approved several algorithms for use in clinical practice. In ophthalmology, most advances in AI relate to diabetic retinopathy, which is a disease process with agreed upon diagnostic and classification criteria. However, this is not the case for glaucoma, which is a relatively complex disease without agreed-upon diagnostic criteria. Moreover, currently available public datasets that focus on glaucoma have inconstant label quality, further complicating attempts at training AI algorithms efficiently. In this perspective paper, we discuss specific details related to developing AI models for glaucoma and suggest potential steps to overcome current limitations.

[1]  P. Rajpurkar,et al.  Multimodal biomedical AI , 2022, Nature Medicine.

[2]  Aaron S. Coyner,et al.  External Validation of a Retinopathy of Prematurity Screening Model Using Artificial Intelligence in 3 Low- and Middle-Income Populations. , 2022, JAMA ophthalmology.

[3]  A. Hewitt,et al.  Diagnostic Accuracy of Artificial Intelligence in Glaucoma Screening and Clinical Practice , 2022, Journal of glaucoma.

[4]  J. Mohamed-Noriega,et al.  Defining and diagnosing glaucoma: a focus on blindness prevention , 2022, Community eye health.

[5]  Leonard K. Seibold,et al.  Designs and Methodologies Used in Landmark Clinical Trials of Glaucoma: Implications for Future Big Data Mining and Actionable Disease Treatment , 2022, Frontiers in Medicine.

[6]  Mohammad T. Al-Antary,et al.  Deep Learning Prediction of Response to Anti-VEGF among Diabetic Macular Edema Patients: Treatment Response Analyzer System (TRAS) , 2022, Diagnostics.

[7]  S. A. Alryalat,et al.  Machine learning in glaucoma: a bibliometric analysis comparing computer science and medical fields’ research , 2021, Expert Review of Ophthalmology.

[8]  T. Aung,et al.  Multi-modal Machine Learning using Visual Fields and Peripapillary Circular OCT Scans in Detection of Glaucomatous Optic Neuropathy. , 2021, Ophthalmology.

[9]  Xuan Xiao,et al.  Health care cost and benefits of artificial intelligence-assisted population-based glaucoma screening for the elderly in remote areas of China: a cost-offset analysis , 2021, BMC Public Health.

[10]  S. A. Alryalat.  Machine learning on glaucoma: the missing point , 2021, Eye.

[11]  F. Medeiros,et al.  An objective structural and functional reference standard in glaucoma , 2021, Scientific Reports.

[12]  F. Medeiros,et al.  The Effect of Age on Increasing Susceptibility to Retinal Nerve Fiber Layer Loss in Glaucoma , 2020, Investigative ophthalmology & visual science.

[13]  S. A. Alryalat,et al.  Simulating a colour-blind ophthalmologist for diagnosing and staging diabetic retinopathy , 2020, Eye.

[14]  Pearse A. Keane,et al.  A global review of publicly available datasets for ophthalmological imaging: barriers to access, usability, and generalisability. , 2020, The Lancet. Digital health.

[15]  Pearse A. Keane,et al.  Artificial Intelligence Algorithms to Diagnose Glaucoma and Detect Glaucoma Progression: Translation to Clinical Practice , 2020, Translational vision science & technology.

[16]  Michael V. Boland,et al.  Defining glaucomatous optic neuropathy using objective criteria from structural and functional testing , 2020, British Journal of Ophthalmology.

[17]  Felipe A. Medeiros,et al.  A Review of Deep Learning for Screening, Diagnosis, and Detection of Glaucoma Progression , 2020, Translational vision science & technology.

[18]  Rumi Chunara,et al.  No Computation without Representation: Avoiding Data and Algorithm Biases through Diversity , 2020, KDD.

[19]  April Y. Maa,et al.  Deep Learning and Glaucoma Specialists: The Relative Importance of Optic Disc Features to Predict Glaucoma Referral in Fundus Photographs. , 2018, Ophthalmology.

[20]  Jitendra Malik,et al.  Expert-level detection of acute intracranial hemorrhage on head computed tomography using deep learning , 2019, Proceedings of the National Academy of Sciences.

[21]  K. Park,et al.  Optical Coherence Tomography for the Diagnosis and Monitoring of Glaucoma , 2019, Asia-Pacific journal of ophthalmology.

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

[23]  T. Nakazawa,et al.  Stereoscopic Analysis of Optic Nerve Head Parameters in Primary Open Angle Glaucoma: The Glaucoma Stereo Analysis Study , 2014, PloS one.

[24]  F. Medeiros,et al.  The pathophysiology and treatment of glaucoma: a review. , 2014, JAMA.

[25]  Jayanthi Sivaswamy,et al.  Drishti-GS: Retinal image dataset for optic nerve head(ONH) segmentation , 2014, 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI).

[26]  Chris A. Johnson,et al.  Features of Optic Disc Progression in Patients With Ocular Hypertension and Early Glaucoma , 2013, Journal of glaucoma.

[27]  Brenda W Gillespie,et al.  Visual field progression in the Collaborative Initial Glaucoma Treatment Study the impact of treatment and other baseline factors. , 2009, Ophthalmology.

[28]  William M. Wells,et al.  Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation , 2004, IEEE Transactions on Medical Imaging.

[29]  M. Yablonski.  Ocular hypertension treatment study. , 2004, Archives of ophthalmology.

[30]  M. C. Leske,et al.  Reduction of intraocular pressure and glaucoma progression: results from the Early Manifest Glaucoma Trial. , 2002, Archives of ophthalmology.

[31]  Chris A. Johnson,et al.  The Ocular Hypertension Treatment Study: baseline factors that predict the onset of primary open-angle glaucoma. , 2002, Archives of ophthalmology.

[32]  C E Letocha,et al.  The American Academy of Ophthalmology. , 1996, Archives of ophthalmology.

[33]  Susan Vitale,et al.  Agreement among glaucoma specialists in assessing progressive disc changes from photographs in open-angle glaucoma patients. , 2009, American journal of ophthalmology.