Diagnosis of Multiple Fundus Disorders Amidst a Scarcity of Medical Experts Via Self-supervised Machine Learning
This addresses the shortage of ophthalmologists in underdeveloped regions for timely diagnosis of fundus diseases, which are major causes of visual impairment and blindness, though it is incremental as it builds on existing AI-assisted methods.
The paper tackles the problem of diagnosing multiple fundus disorders in regions with scarce medical experts by proposing a self-supervised machine learning framework that uses unlabeled fundus images, achieving an AUC that surpasses existing supervised approaches by 15.7% and exceeds the performance of a single human expert.
Fundus diseases are major causes of visual impairment and blindness worldwide, especially in underdeveloped regions, where the shortage of ophthalmologists hinders timely diagnosis. AI-assisted fundus image analysis has several advantages, such as high accuracy, reduced workload, and improved accessibility, but it requires a large amount of expert-annotated data to build reliable models. To address this dilemma, we propose a general self-supervised machine learning framework that can handle diverse fundus diseases from unlabeled fundus images. Our method's AUC surpasses existing supervised approaches by 15.7%, and even exceeds performance of a single human expert. Furthermore, our model adapts well to various datasets from different regions, races, and heterogeneous image sources or qualities from multiple cameras or devices. Our method offers a label-free general framework to diagnose fundus diseases, which could potentially benefit telehealth programs for early screening of people at risk of vision loss.