ML Anthology

Segmentation and Removal of Pulmonary Arteries, Veins and Left Atrial Appendage for Visualizing Coronary and Bypass Arteries

Hua Zhong, Yefeng Zheng, Gareth Funka-Lea, Fernando Vega Higuera
CVPRW 2012 pp. 24-30
doi:10.1109/CVPRW.2012.6239243 /cvprw/2012/zhong2012cvprw-segmentation/

Abstract

In this paper we present an automatic heart segmentation system for helping the diagnosis of the coronary artery diseases (CAD). The goal is to visualize the heart from a cardiac CT image with pulmonary veins, pulmonary arteries and left atrial appendage removed so that doctors can clearly see major coronary artery trees, aorta and bypass arteries if exist. The system combines model-based detection framwork with data-driven post-refinements to create voxel-based heart mask for the visualization. The marginal space learning [6] algorithm is used to detect mesh or landmark models of different heart anatomies in the CT image. Guided by such detected models, local data-driven refinements are added to produce precise boundaries of the heart mask. The system is fully automatic and can process a 3D cardiac CT volume within 5 seconds.

CVPRW Semantic Scholar

Cite

Text

Zhong et al. "Segmentation and Removal of Pulmonary Arteries, Veins and Left Atrial Appendage for Visualizing Coronary and Bypass Arteries." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012. doi:10.1109/CVPRW.2012.6239243

Markdown

[Zhong et al. "Segmentation and Removal of Pulmonary Arteries, Veins and Left Atrial Appendage for Visualizing Coronary and Bypass Arteries." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2012.](https://mlanthology.org/cvprw/2012/zhong2012cvprw-segmentation/) doi:10.1109/CVPRW.2012.6239243

BibTeX

@inproceedings{zhong2012cvprw-segmentation,
  title     = {{Segmentation and Removal of Pulmonary Arteries, Veins and Left Atrial Appendage for Visualizing Coronary and Bypass Arteries}},
  author    = {Zhong, Hua and Zheng, Yefeng and Funka-Lea, Gareth and Higuera, Fernando Vega},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2012},
  pages     = {24-30},
  doi       = {10.1109/CVPRW.2012.6239243},
  url       = {https://mlanthology.org/cvprw/2012/zhong2012cvprw-segmentation/}
}