Retinal Vascular Tree Reconstruction with Anatomical Realism

• Main Authors: Lin Kai-Shun, 林凱舜
• Other Authors: Chia-Ling Tsai
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/05776752065635300133

博士 === 國立中正大學 === 資訊工程研究所 === 101 === Motivated by the goals of automatically analyzing vascular trees and reconstructing retinal vascular trees with anatomical realism, this thesis presents and analyses an algorithm that combines vessel segmentation and grouping of the extracted vessel segments. The proposed method aims to restore the topology of the vascular trees with anatomical realism for clinical studies and diagnosis of retinal vascular diseases, which manifest abnormalities in either venous and/or arterial vascular systems. With the knowledge of the vascular trees, an automated computational framework for retinal vascular tree and analysis is presented in this work. In reconstruction vascular trees, vessel segments are grouped using extended Kalman filter which takes into account continuities in curvature, width, and intensity changes at the bifurcation or crossover point. At a junction, the proposed method applies the minimum-cost matching algorithm to resolve the conflict in grouping due to error in tracing. The system was trained with twenty images from the DRIVE dataset, and tested using the remaining twenty images. The dataset contained a mixture of normal and pathological images. In addition, six pathological fluorescein angiogram sequences were also included in this study. Finally, we have also developed an automatic method to measure and quantify the geometrical and topological properties of retinal blood vessels from fundus retinal images. According to the experimental results, the proposed approaches are indeed effective in relative topics. In the future, we will focus on the correctness of grouping and improve the clinical usability of the system.