Fuzzy clustering in Intelligent Scissors

W Wieclawek; E Pietka

doi:10.1016/j.compmedimag.2012.03.004

Fuzzy clustering in Intelligent Scissors

Comput Med Imaging Graph. 2012 Jul;36(5):396-409. doi: 10.1016/j.compmedimag.2012.03.004. Epub 2012 Apr 6.

Authors

W Wieclawek¹, E Pietka

Affiliation

¹ Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland. [email protected]

PMID: 22483373
DOI: 10.1016/j.compmedimag.2012.03.004

Abstract

In this study a modified Live-Wire approach is presented. A Fuzzy C-Means (FCM) clustering procedure has been implemented before the wavelet transform cost map function is defined. This shrinks the area to be searched resulting in a significant reduction of the computational complexity. The method has been employed to computed tomography (CT) and magnetic resonance (MR) studies. The 2D segmentation of lungs, abdominal structures and knee joint has been performed in order to evaluate the method. Significant numerical complexity reduction of the Live-Wire algorithm as well as improvement of the object delineation with a decreased number of user interactions have been obtained.

MeSH terms

Algorithms*
Fuzzy Logic*
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Magnetic Resonance Imaging / methods*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Tomography, X-Ray Computed / methods*