Small-patch CNN and random forest to model and quantify the lenticulostriate artery from 7T time-of-flight MR angiography
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{li2023small,
author = {Zhixin Li and Dongbiao Sun and Yue Wu and Ling Chen and Jing An and Yun Yuan and Zhaoxia Wang and Rong Xue and Yan Zhuo and Zihao Zhang},
title = {{Small-patch CNN and random forest to model and quantify the lenticulostriate artery from 7T time-of-flight MR angiography}},
booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
year = {2023},
doi = {10.58530/2022/4169},
}Loading related content...