Share Email Print
cover

Proceedings Paper

Local kernel mapping based piecewise constant model for medical image segmentation
Author(s): Wenchao Cui; Jian He; Guoqiang Gong; Ke Lu; Shuifa Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Intensity inhomogeneity and noise are two major obstacles for segmenting medical images. The global kernel mapping based piecewise constant model (PCM) has superior performance on resisting noise, though it fails to cope with intensity inhomogeneity. In order to overcome the difficulty caused by intensity inhomogeneity, we first establish an energy based on kernel mapping in a neighborhood of a pixel. Then such energies for all pixels in an image are integrated to formulate the energy of the local kernel mapping based PCM. Energy minimization has been implemented in level set framework. Comparative experimental results show that our proposed model has higher segmentation accuracy in the presence of intensity inhomogeneity and noise.

Paper Details

Date Published: 29 August 2016
PDF: 6 pages
Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100331O (29 August 2016); doi: 10.1117/12.2244918
Show Author Affiliations
Wenchao Cui, China Three Gorges Univ. (China)
Beijing Jiaotong Univ. (China)
Jian He, China Three Gorges Univ. (China)
Guoqiang Gong, China Three Gorges Univ. (China)
Beijing Jiaotong Univ. (China)
Ke Lu, China Three Gorges Univ. (China)
Shuifa Sun, China Three Gorges Univ. (China)


Published in SPIE Proceedings Vol. 10033:
Eighth International Conference on Digital Image Processing (ICDIP 2016)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top