Cardiac CT image segmentation

DOI

10.2991/icmmita-16.2016.293How to use a DOI?

Keywords

CT image segmentation;Active contour;Contrast enhancement

Abstract

Image segmentation is an important technology for computer-aided diagnosis. Purpose of medical image segmentation is to separate the images' regions with special meanings and to make the segmentation as close as possible to the anatomical structure so as to provide a reliable foundation for clinical diagnosis and treatment and also for pathological study. Due to the complexity of human anatomy, the irregularity of organ and tissue shapes as well as the diversity between individuals, general medical image segmentation methods cannot be directly applied to achieve the ideal segmentation effect. Besides, medical images have different features which cannot endow segmentation methods with universality. Thus, a more targeted medical image segmentation method is needed. This paper is targeted at studying an effective method for segmenting cardiac images, namely, the segmentation of coronary arteries and the segmentation of ventricle and atrium (VA). According to the characteristics and special needs of medical images, a new method for cardiac image segmentation was proposed. This method combines contrast enhancement, threshold segmentation, morphological algorithm and level set-based active contour model. Furthermore, this method improves its own problems to ultimately achieve the algorithm in MATLAB platforms, obtaining a better segmentation result.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zihang Xu
AU  - Rui Jiang
PY  - 2017/01
DA  - 2017/01
TI  - Cardiac CT image segmentation
BT  - Proceedings of the 2016 4th International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 1291
EP  - 1294
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-16.2016.293
DO  - 10.2991/icmmita-16.2016.293
ID  - Xu2017/01
ER  -