Chief Supervisor

Prof. HE Mingguang

Project Title

Synopsis

Age-related macular degeneration (AMD) is the leading cause of central vision loss in the aging population, mainly consisting of atrophic (“dry”) AMD and neovascular (“wet”) AMD. Dry AMD may progress to wet AMD, which is characterized by central choroidal neovascularization (CNV), resulting in hemorrhaging within the central retina and profound visual impairment. Timely identification and intervention hold paramount importance in preventing AMDinduced blindness. However, large-scale screening for AMD has become a substantial burden on the global healthcare system, especially as the aging population intensifies. Indocyanine green angiography (ICGA) is a wellestablished fundus imaging technique for detecting and monitoring various chorioretinal diseases. However, ICGA is unsuitable for regular screening of choroidal conditions due to its invasive nature, time-consuming process and potential side effects. The main purpose of this project is to develop and validate a deep-learning model based on GAN architecture capable of generating realistic ICGA images from color fundus photography (CF) and provide a non-invasive alternative to improve the screening efficiency of AMD and several choroidal disease at low cost.