Live-Wire-Based 3D Segmentation Method

Author

Wieclawek, W. ; Pietka, E.

Author_Institution

Silesian Univ. of Technol., Gliwice

fYear

2007

fDate

22-26 Aug. 2007

Firstpage

5645

Lastpage

5648

Abstract

Three-dimensional (3D) segmentation has become an essential part of volumetric image analysis. The methodology is based on the live-wire approach implemented in two-dimensional (2D) scene, yet two significant modifications have been employed. The wavelet-based cost map has improved the segmentation accuracy, whereas the fuzzy C-means (FCM) clustering procedure has shrunk the area to be searched, and thus has lower the numerical complexity. The 3D segmentation has been obtained by implementing the FCM clustering procedure with morphological operations. It does not require users interaction. The method has been employed to magnetic resonance imaging (MRI) and X-ray computed tomography (CT) studies. Additionally, noise resistance of the 3D approach has been measured.

Keywords

biomedical MRI; computerised tomography; image segmentation; FCM clustering; MRI; X-ray computed tomography; fuzzy C-means clustering; live wire based 3D segmentation method; magnetic resonance imaging; noise resistance; volumetric image analysis; wavelet-based cost map; Computed tomography; Costs; Electrical resistance measurement; Image analysis; Image segmentation; Layout; Magnetic noise; Magnetic resonance imaging; Morphological operations; X-ray imaging; Algorithms; Artificial Intelligence; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Lung; Magnetic Resonance Imaging; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Tomography, X-Ray Computed;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE

Conference_Location

Lyon

ISSN

1557-170X

Print_ISBN

978-1-4244-0787-3

Type

conf

DOI

10.1109/IEMBS.2007.4353627

Filename

4353627