Abstract #4169
Small-patch CNN and random forest to model and quantify the lenticulostriate artery from 7T time-of-flight MR angiography
Zhixin Li1,2,3, Dongbiao Sun1,2,3, Yue Wu1,2,3, Chen Ling4,5, Jing An6, Yun Yuan4,5, Zhaoxia Wang4,5, Rong Xue1,2,3, Yan Zhuo1,2,3, and Zihao Zhang1,2,3
1State Key Laboratory of Brain and Cognitive Science, Institute of Biophysics, Chinese Academy of Sciences, Beijing, China, Beijing, China, 2University of Chinese Academy of Sciences, Beijing, China, Beijing, China, 3The Innovation Center of Excellence on Brain Science, Chinese Academy of Sciences, Beijing, China, Beijing, China, 4Department of Neurology, Peking University First Hospital, Beijing, 100034, China, Beijing, China, 5Beijing Key Laboratory of Neurovascular Disease Discovery, Peking University First Hospital, Beijing, 100034, China, Beijing, China, 6Siemens Shenzhen Magnetic Resonance Ltd., Shenzhen, China, Shenzhen, China
Synopsis
Time-of-flight MR angiography at 7T allowed noninvasive visualization of the lenticulostriate artery (LSA). However, vasculature modeling of LSA remained challenging due to limited signal-to-noise ratio and pulsation artifact. In this study, we introduced an automated vascular segmentation and tracing method based on small-patch convolutional neural network (CNN), random forest, and multiple filtering. This method outperformed existing U-NET based methods and found radius changes of LSA branches in patients with cerebral small vessel diseases (cSVD). The automated quantification of LSA vasculatures will potentially facilitate diagnosis and clinical studies of cSVD.
This abstract and the presentation materials are available to members only;
a login is required.
Join Here
