Segmentation of Polypoidal Choroidal Vasculopathy Using Random Walk

• Main Authors: TSOU,MING-YU, 鄒明佑
• Other Authors: LIN,WEI-YANG
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/63867737684743159001

碩士 === 國立中正大學 === 資訊工程研究所 === 103 === According to World Health Organization statistics, Age-related Macular Degeneration (AMD) is the third leading cause of blindness and visual impairment around the world. AMD has also become one of the major causes of blindness among elderly people in Taiwan. Polypoidal choroidal vasculopathy (PCV) is a subtype of neovascular age-related macular degeneration (AMD) and is prevalent in 40% to 50% of the Asian patients with exudative maculopathy. Due to the considerably high incidence of PCV among Asian people, the goal of our research work is to develop a computer-aided diagnostic system for segmenting PCV lesions in indocyanine green angiography (ICGA) images. Our proposed system is based on the random walk algorithm. The user only needs to provide a few seed points and the random walk algorithm will segment the lesion area precisely. We have conducted several experiments using the EVEREST dataset and performed comparison with our previous work. The results show the proposed system achieves significantly better accuracy in segmenting Branching Vascular Network (BVN), which is a major pathological condition associated with PCV