Live-wire-based 3D segmentation method

Wojciech Wiecławek; Ewa Pietka

doi:10.1109/IEMBS.2007.4353627

Live-wire-based 3D segmentation method

Annu Int Conf IEEE Eng Med Biol Soc. 2007:2007:5646-9. doi: 10.1109/IEMBS.2007.4353627.

Authors

Wojciech Wiecławek¹, Ewa Pietka

Affiliation

¹ Division of Biomedical Electronics, Institute of Electronics, Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, ul. Akademicka 16, 44-100 Gliwice, Poland. [email protected]

PMID: 18003293
DOI: 10.1109/IEMBS.2007.4353627

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.

Publication types

Evaluation Study

MeSH terms

Algorithms
Artificial Intelligence
Humans
Image Enhancement / methods
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional / methods*
Lung / anatomy & histology*
Lung / diagnostic imaging*
Magnetic Resonance Imaging / methods*
Pattern Recognition, Automated / methods*
Reproducibility of Results
Sensitivity and Specificity
Tomography, X-Ray Computed / methods*