FunduScope : A Human-centered Tool for ML-assisted e-Learning in Ophthalmology

Interpreting fundus images is an essential skill for diagnosing eye diseases, such as diabetic retinopathy (DR), one of the leading causes of visual impairment. However, the training of junior doctors relies on experienced ophthalmologists, who often lack time for teaching, or on printed training material that lacks variability in examples. Additionally, machine learning (ML) models successfully detect pathologies relevant to DR and grade the corresponding severity level of cases. With that, our work combines advances in ML with the need of junior doctors to learn independently. We present an interactive learning tool for ophthalmology, which lets junior doctors mark pathologies in fundus images and check them upon the solution of an applied ML algorithm. By aligning the learning concept with theories of cognitive load, usability, and e-learning factors, this system serves as a testbed to explore the potential of ML-supported learning tools for medical education, advancing interactive e-learning.