How to Use Poor-Quality Retinal Images to Make Diagnoses of Diabetic Retinopathy: Improving Access to Care with Noisy Images
Open Access DepositedDiabetic retinopathy is characterized by progressive damage to the blood vessels supporting the retina and early access to retinal imaging and appropriate treatment can quickly change an individual’s outcome by significantly reducing the risk of vision loss. According to the Center for Disease Control and Prevention, diabetic retinopathy is the leading cause of blindness in American adults. As of a 2021 report, an estimated 9.6 million people in the United States of America were living with diabetic retinopathy. Of this population, 1.84 million were living with an elevated risk of permanent vision-loss. Despite these figures, diabetic retinopathy is not solely a domestic issue, and current cases exceed 103 million globally. However, many patients do not seek regular eye exams at ophthalmic clinics. To make this diagnostic technology more accessible, portable retinal imaging devices have been developed, but are often large, expensive, and require dilation of the patient's eyes. This research seeks to develop the software component of an alternative approach: a smartphone-compatible retinal imaging attachment that doesn’t require dilation of the patient's eyes and uses post-processing of the resulting poor-quality image to make diagnoses. A transfer-learning approach using pre-trained neural networks will be taken to analyze the poor-quality image and make a diagnosis for the clinician. In addition to diagnosing diabetic retinopathy, the trained algorithm will also be able to discern other disease states in the presence of varying amounts of simulated noise. Overall, this technology seeks to increase access to retinal imaging and diagnosis for early clinician intervention.
- All rights reserved
Notice to Authors
If you are the author of this work and you have any questions about the information on this page, please use the Contact form to get in touch with us.