A Semantic Segmentation Method with Emphasizing Edge information for Automatic Vessel Wall Analysis
Wenjing Xu1,2, Qing Zhu1, Guanxun Cheng3, Liwen Wan2, Lei Zhang2, Qiang He4, Yongming Dai4, Dong Liang2, Ye Li2, Hairong Zheng2, Xin Liu2, and Na Zhang2
1Faculty of Information Technology, Beijing University of Technology, Beijing, China, 2Paul C. Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China, 3Department of Radiology, Peking university shenzhen hospital, Shenzhen, China, 4United Imaging Healthcare, Shanghai, China
Edge information is essential for medical image analysis, especially for image segmentation. This paper aims to develop a precise semantic segmentation method with emphasizing the edges for automated segmentation of arterial vessel wall and plaque based on the convolutional neural network (CNN) for facilitating the quantitative assessment of plaque in patients with ischemic stroke. An end-to-end architecture network that can emphasize the edge information is proposed. The results suggest that the proposed segmentation method improves segmentation accuracy effectively and will facilitate the quantitative assessment on atherosclerosis.
This abstract and the presentation materials are available to members only;
a login is required.