A new parametric model-based technique in bone tumour analysis

Joanna Czajkowska; Ewa Pietka

doi:10.1016/j.compmedimag.2014.04.002

A new parametric model-based technique in bone tumour analysis

Comput Med Imaging Graph. 2014 Jul;38(5):315-25. doi: 10.1016/j.compmedimag.2014.04.002. Epub 2014 Apr 24.

Authors

Joanna Czajkowska¹, Ewa Pietka²

Affiliations

¹ Department of Computer Science and Medical Equipment, Faculty of Biomedical Engineering, Silesian University of Technology, ul. Charlesa de Gaulle'a 66, 41-800 Zabrze, Poland; Institute for Vision and Graphics, University of Siegen, Hoerlindstr. 3, 57076 Siegen, Germany. Electronic address: jczajkowska@polsl.pl.
² Department of Computer Science and Medical Equipment, Faculty of Biomedical Engineering, Silesian University of Technology, ul. Charlesa de Gaulle'a 66, 41-800 Zabrze, Poland. Electronic address: epietka@polsl.pl.

PMID: 24815368
DOI: 10.1016/j.compmedimag.2014.04.002

Abstract

The study presents a new statistical model based segmentation technique dedicated to inhomogeneous bone tumours structure analysis. The presented 3-D segmentation procedure applies a statistic description of the structure based on Gaussian mixture model and an adaptive model-based relative fuzzy connectedness technique. It has been tested on 94 different MR series of 38 young patients. The final segmentation results have been evaluated using two different verification techniques and compared with other segmentation methods. The developed technique yields higher bone tumours segmentation accuracy compared to results obtained with conventional fuzzy connectedness approach and different segmentation methods presented in the literature, and based on active contour models or statistical analysis.

Keywords: 3-D segmentation; Bone tumours; Fuzzy connectedness analysis; Gaussian mixture model; Magnetic resonance imaging.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Bone Neoplasms / diagnosis*
Diagnostic Imaging
Fuzzy Logic
Humans
Image Interpretation, Computer-Assisted / methods*
Imaging, Three-Dimensional*
Magnetic Resonance Imaging
Models, Statistical*
Normal Distribution