RETFound - A foundation model for ophthalmology

Speaker: 

• Yukun Zhou.

Abstract

Medical AI offers great potential for recognising signs of health conditions in retinal images and expediting the disease detection.

However, the development of AI models requires substantial annotation and models are usually task-specific with limited generalisability to different clinical applications.

In this talk, Yukun will introduce a foundation model for retinal images that learns generalisable representations from unlabelled retinal images and provides a basis for label-efficient model adaptation in several applications, including the diagnosis and prognosis of sight-threatening eye diseases, as well as incident prediction of complex systemic disorders such as heart failure and myocardial infarction.

About the speaker

Yukun Zhou is a post-doc at University College London, affiliated with the Centre for Medical Image Computing and Institute of Ophthalmology.

His primary research focus lies in generalisable medical image analysis, foundation model development, and large-scale translational research on real-world clinical data.