Artificial intelligence applications in ophthalmology and vision science

Friday, October 1, 12:00 – 14:00 ET // Register here

This event has already occurred. You can watch a recording here.

Machine learning is playing an increasingly important role in retinal disease diagnosis, management, treatment, and progression. This session is aimed at medical image and data analysis of the retina using the latest approaches in artificial intelligence, with a special emphasis on disease management and clinical/translational applications, including examples from retinopathy of prematurity, age-related macular degeneration, glaucoma, and others.

This special session is being hosted by the Clinical Vision Sciences Technical Group, the Color Technical Group, and the Applications of Visual Science Technical Group along with the Fall Vision Meeting Planning Committee.

Invited Speakers:

  • Cecilia Lee, University of Washington

  • Hiroshi Ishikawa, Oregon Health & Science University

  • J. Peter Campbell, Oregon Health & Science University

  • Michael Abramoff, Digital Diagnostics


  • Jessica I. W. Morgan, University of Pennsylvania


Deep learning applications in clinical ophthalmology

Cecilia S. Lee, MD, MS, Department of Ophthalmology, University of Washington, Seattle, Washington, United States; Karalis Johnson Retina Center, Seattle, Washington, United States

Rapid advances in retinal imaging technology combined with deep learning approaches for image analysis have provided new avenues of investigation in ophthalmic disease. First, deep learning provides a de novo approach to image analysis, identifying previously unrecognized imaging features that correlate with functional changes. In age-related macular degeneration (AMD), deep learning approaches identified subtle retinal features, hyporeflective outer retinal bands in the central macula, that are associated with delayed rod-mediation dark adaptation, a functional biomarker of early AMD. Second, deep learning allows prediction of clinical outcomes such as visual field progression in glaucoma. Lastly, deep learning models can also be used to segment anatomic features from ophthalmic imaging, enabling accurate and fully automated periorbital measurements with many potential clinical applications in oculoplastics. Deep learning applications in ophthalmic imaging have potential to improve our understanding of disease and their clinical outcomes.

Funding Acknowledgement: Unrestricted grant RPB, NIA/NIH U19AG066567, NIA/NIH R01AG060942, Klorfine Family Endowed Chair.

AI applications in glaucoma

Hiroshi Ishikawa, MD, Department of Ophthalmology, Casey Eye Institute, Oregon Health & Science University

Glaucoma is the second cause of blindness worldwide. Due to the complicated non-linear relationships between structural and functional assessment outcomes together with the large variabilities of disease progression patterns, accurate and reliable clinical assessment is a paramount importance for this slow but irreversible progressing disease. Recent advances in medical applications of artificial intelligence, especially deep learning (DL) approaches, have opened up unprecedented possibilities in computer aided clinical care. I will discuss a variety of DL studies on our large longitudinal glaucoma cohort data in collaborating IBM Watson Research Team. The topics include: 1) estimation of visual field parameters out of raw 3D optical coherence tomography (OCT) image data using a feature agnostic data driven approach, 2) forecasting functional measurements out of clinically available demographic information augmented by OCT feature analysis, 3) generating future 2D biomarker color mapping on OCT image data, and 4) identifying novel biomarkers and exploration of structure-function relationships using a group class activation mapping technique.

Funding Acknowledgement: NIH R01-EY013178, NIH R01-EY030929, P30EY013079 (unrestricted grant by the Research to Prevent Blindness).

Machine learning and artificial intelligence in retinopathy of prematurity

J. Peter Campbell, MD, MPH, Department of Ophthalmology, Oregon Health & Science University

In this presentation, I will review a brief history of machine learning in retinopathy of prematurity, and discuss current and potential applications in research, education, and patient care.

Funding Acknowledgement: NIH R01EY19474, R01 EY031331, R21 EY031883, and P30 EY10572. Research to Prevent Blindness.

Disclosures: Genentech (grant funding). Boston AI Labs (consultant).

Autonomous AI for the Diabetic Eye Exam for improving outcomes: Lessons learnt

Michael D. Abràmoff, FARVO, Fellow IEEE; University of Iowa Retina Service; and Digital Diagnostics, Coralville, Iowa

Diabetic retinopathy leads to avoidable blindness and is an important cause of health disparities. Autonomous AI allows immediate point of care diabetic eye exams can increase access, address disparities and lower cost. Major hurdles needed to be overcome: ethical framework, liability, standard of care, (FDA) regulation, CPT coding, reimbursement, and HEDIS / MIPS quality measurements. How we overcame these hurdles is illustrative for AI of the eye in other fields.

Funding Acknowledgement: NIH.

Disclosures: founder, consultant, equity, director of Digital Diagnostics