| Issue |
ITM Web Conf.
Volume 45, 2022
2021 3rd International Conference on Computer Science Communication and Network Security (CSCNS2021)
|
|
|---|---|---|
| Article Number | 01036 | |
| Number of page(s) | 12 | |
| Section | Computer Technology and System Design | |
| DOI | https://doi.org/10.1051/itmconf/20224501036 | |
| Published online | 19 May 2022 | |
A parallel 3D image segmentation method for Coronary CT Angiography
School of Information Engineering, Yancheng Teachers University, 224002 Yan Cheng City, China
* Corresponding author: TZCY@163.com
Coronary artery (CA) disease is one of the major cardiovascular diseases that has been proved to be the leading cause of human death in world. In this paper, a 3D image segmentation algorithm based on Lattice Boltzmann (LB) is proposed for 3D CA segmentation. After investigating the behavior of Boundary Treatment schemes, a non-equilibrium extrapolation scheme is applied to keep the stability of the computation, and reduce the frequency of the re-initialization. The denoising and clipping method are also proposed for the segmentation refining. The segmentation result shows our LB model for 3D CAD segmentation is effective. More importantly, the LB model has natural parallelism. Our model can run on massively parallel architectures, ranging from inexpensive embedded FPGAs and DSPs up to GPUs.
© The Authors, published by EDP Sciences, 2022
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.