The significance of the analysis of color fundus image and a survey of the retinal vessel segmentation

12.8.2016 10:15


Infotech Oulu Lecture Series

Lecturer: Professor Beiji Zou, Central South University, China

Date: August 12, 2016
Time: 10:15-11:00
Room: TS126


Color fundus image is not only the important basis to diagnose the ophthalmology disease and other systemic diseases, such as diabetic retinopathy, hypertension, and glaucoma, but also the foundation of the ophthalmic disease computer-aided diagnosis and large-scale screening system. The analysis of color fundus image based on the digital image processing method is the frontier of the interdisciplinary area of Ophthalmology and Information Science. This talk not only outlines the background and significance of the analysis of color fundus image, but also reviews the progress of retinal vessel segmentation in fundus image, the standard databases, commonly used performance metrics, and current vessel segmentation algorithms, which can be divided into five main categories: blood vessel tracking, matched filtering, mathematical morphology, deformable model based, and machine learning. Finally, this talk points out the difficulties to be resolved in retinal vessel segmentation, such as the interference by physiological structure and lesions, and the segmentation of microvascular, vessels on the optic disc and intraretinal microvascular abnormalities (IRMA).


Dr. Beiji Zou, a professor and doctor supervisor of Central South University, China, received his B.S., M.S. and Ph.D degrees from Zhejiang University, Tsinghua University and Hunan University in 1982, 1984 and 2001, respectively. He is now the dean of School of Information Science and Engineering, Central South University, and also the member of the council of China Computer Federation (CCF), a deputy director of the CCF CAD & CG committee, the chairman of Hunan higher Education Federation Computer Education Committee, the deputy director of the Mobile Health Ministry of Education China Mobile Jointly laboratory, and a member of editorial board of the “Chinese Journal of Electronics” (in English). His research areas include computer graphics, computer vision, medical image processing, and big data analytics in healthcare. He has hosted five projects of National Natural Science Foundation of China, two projects of National High Technology Research and Development Program of China (863 Program), one subprojects of Major State Basic Research Development Program of China (973 Program), and more than 30 provincial /enterprise commissioned projects. He has published more than 150 papers in the core international conferences and journals, among which more than 60 papers are indexed by SCI. He has compiled three teaching monographs and obtained seven granted invention patents. He has also received the Hunan Provincial Science and Technology Progress Award once. He has already carried out many collaborative researches with the universities in Australia, the United States, France, Finland and Japan.

More information: Guoying Zhao

Last updated: 4.8.2016