Chief Supervisor

Prof. HE Mingguang

Project Title

Synopsis

Fundus fluorescein angiography (FFA) plays a crucial role in the diagnosis and monitoring of retinal vascular diseases, while its evaluation is time-consuming and subject to inter-observer variability. Our study aims to address this gap by developing an automated and objective method for detecting and segmenting multi-lesions in FFA images. Unlike previous studies that focused on specific lesion types associated with particular diseases in the given modality, our approach seeks to identify and segment all types of lesions present in FFA images, regardless of the underlying retinal vascular disease and the modality. This comprehensive approach will enable a more holistic understanding of retinal pathology and aid in the diagnosis and management of diabetic retinopathy, retinal vein, and artery occlusions, neovascular AMD, and other common retinal vascular diseases. Through this research, we anticipate valuable insights into the complex interplay of various retinal lesions, facilitating improved patient care and outcomes.