Automatic Retinal Health Monitoring through Multi-modal Medical Imaging

The School of EECS is hosting the following PhD Progress Review 1 Confirmation Seminar:

Automatic Retinal Health Monitoring through Multi-modal Medical Imaging

Speaker: Hongwei Sheng
Host: Dr Xin Yu

Abstract: The retina, as the only accessible part of the central nervous system through non-invasive imaging, plays a crucial role in diagnosing and monitoring systemic and ocular diseases like diabetic retinopathy and glaucoma. Multi-modal imaging, including fundus photography, OCT, and fluorescein angiography, provides complementary information necessary for accurate diagnosis. However, the integration of multiple modalities introduces significant challenges, increasing the workload for healthcare professionals and complicating the diagnostic process. Despite the development of deep learning-based computer-aided diagnosis systems, these models struggle with automation and the effective integration of multi-modal data, limiting their real-world impact in clinical settings.

To tackle these challenges, this project aims to develop a multi-modal, multitask diagnostic algorithm that leverages several novel deep learning innovations. This project not only advances the field of multi-modal retinal image analysis but also has the potential to uncover new clinical diagnostic methods, offering significant contributions to both medical imaging and clinical applications.