News & Events

Bridging Patients to Therapy: Advanced Imaging and Analysis in Ophthalmic and Neurological OCT

Shuwen Wei, Postdoctoral Fellow in the Department of Electrical and Computer Engineering at Johns Hopkins University

601 Computer Studies Building

Optical coherence tomography (OCT) is central to bridging patients and therapy through advanced imaging and analysis in modern clinical workflows across ophthalmology and neurology. In this talk, I will present two complementary advances along this pathway. First, on the imaging side, I introduce a real-time microscope-integrated OCT system to guide calibration-free autonomous robotic subretinal injections, enabling safer and more precise therapeutic interventions for retinal diseases such as age-related macular degeneration. Second, on the analysis side, I present a harmonization framework based on latent metric Schrödinger bridge, which improves upon standard Schrödinger bridge methods by better preserving retinal anatomy when standardizing OCT images across different devices. This analysis supports consistent longitudinal monitoring for neurological diseases such as multiple sclerosis. Together, these innovations demonstrate how advanced imaging and intelligent analysis can transform patient data into actionable, personalized therapy.

Shuwen Wei is a postdoctoral fellow in the Department of Electrical and Computer Engineering at Johns Hopkins University, where he conducts research at the intersection of medical imaging and deep learning. He received his Ph.D. and M.S. in Electrical Engineering from Johns Hopkins University in 2022 and 2019, respectively, and B.S. from Huazhong University of Science and Technology in 2017. He has published over ten first-author peer-reviewed articles in journals including Medical Image Analysis, IEEE Robotics and Automation Letters, Optics Letters, Optics Express, Biomedical Optics Express, and Journal of the Optical Society of America A, as well as conferences such as NeurIPS and MICCAI. He also serves as an organizer of the Learn2Reg Challenge for medical image registration.