Segmentation of vertebral bodies in MR images based on geometrical models in 3D

Authors:
Darko Štern;Boštjan Likar;Franjo Pernuš;Tomaž Vrtovec
Affiliations:
Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia;Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia;Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia;Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia
Venue:
MIAR'10 Proceedings of the 5th international conference on Medical imaging and augmented reality
Year:
2010

Citing 3
Cited 1

Segmentation and recovery of superquadrics: computational imaging and vision

Segmentation and recovery of superquadrics: computational imaging and vision
Numerical Recipes in C++: the art of scientific computing

Numerical Recipes in C++: the art of scientific computing
Digital Image Processing (3rd Edition)

Digital Image Processing (3rd Edition)

Automated identification of thoracolumbar vertebrae using orthogonal matching pursuit

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

Segmentation of vertebrae provides means for reliable measurement of vertebral deformations, which is important for the diagnosis and therapy of pathological conditions affecting the spine. In this paper we propose a method for segmentation of vertebral bodies in three-dimensional (3D) magnetic resonance (MR) images that is based on efficient geometrical modeling of the vertebral body and evaluation of dissimilarity between the vertebral body and the surrounding soft tissue in MR images. The results show that the proposed geometrical model of the vertebral body can describe a variety of vertebral body shapes and therefore the method may be used for quantitative assessment of vertebral body deformations or initialization of whole vertebra segmentation.