You are not logged in.

Localization and degmentation of 3D intervertebral discs in MR Images by data driven estimation

Chen, Cheng, Belavy, Daniel, Yu, Weimin, Chu, Chengwen, Armbrecht, Gabriele, Bansmann, Martin, Felsenberg, Dieter and Zheng, Guoyan 2015, Localization and degmentation of 3D intervertebral discs in MR Images by data driven estimation, IEEE transactions on medical imaging, vol. 34, no. 8, pp. 1719-1729, doi: 10.1109/TMI.2015.2403285.

Attached Files
Name Description MIMEType Size Downloads

Title Localization and degmentation of 3D intervertebral discs in MR Images by data driven estimation
Author(s) Chen, Cheng
Belavy, DanielORCID iD for Belavy, Daniel orcid.org/0000-0002-9307-832X
Yu, Weimin
Chu, Chengwen
Armbrecht, Gabriele
Bansmann, Martin
Felsenberg, Dieter
Zheng, Guoyan
Journal name IEEE transactions on medical imaging
Volume number 34
Issue number 8
Start page 1719
End page 1729
Total pages 11
Publisher IEEE
Place of publication Champaign, Ill.
Publication date 2015-08
ISSN 1558-254X
Keyword(s) intervertebral discs
Magnetic Resonance Imaging (MRI)
Segmentation
spine
Science & Technology
Technology
Life Sciences & Biomedicine
Computer Science, Interdisciplinary Applications
Engineering, Biomedical
Engineering, Electrical & Electronic
Imaging Science & Photographic Technology
Radiology, Nuclear Medicine & Medical Imaging
Computer Science
Engineering
AUTOMATIC SEGMENTATION
SPINE DETECTION
CT
OPTIMIZATION
REGISTRATION
FEATURES
MODEL
Summary This paper addresses the problem of fully-automatic localization and segmentation of 3D intervertebral discs (IVDs) from MR images. Our method contains two steps, where we first localize the center of each IVD, and then segment IVDs by classifying image pixels around each disc center as foreground (disc) or background. The disc localization is done by estimating the image displacements from a set of randomly sampled 3D image patches to the disc center. The image displacements are estimated by jointly optimizing the training and test displacement values in a data-driven way, where we take into consideration both the training data and the geometric constraint on the test image. After the disc centers are localized, we segment the discs by classifying image pixels around disc centers as background or foreground. The classification is done in a similar data-driven approach as we used for localization, but in this segmentation case we are aiming to estimate the foreground/background probability of each pixel instead of the image displacements. In addition, an extra neighborhood smooth constraint is introduced to enforce the local smoothness of the label field. Our method is validated on 3D T2-weighted turbo spin echo MR images of 35 patients from two different studies. Experiments show that compared to state of the art, our method achieves better or comparable results. Specifically, we achieve for localization a mean error of 1.6-2.0 mm, and for segmentation a mean Dice metric of 85%-88% and a mean surface distance of 1.3-1.4 mm.
Language eng
DOI 10.1109/TMI.2015.2403285
Field of Research 110699 Human Movement and Sports Science not elsewhere classified
Socio Economic Objective 929999 Health not elsewhere classified
HERDC Research category C1.1 Refereed article in a scholarly journal
Copyright notice ©2015, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30078353

Document type: Journal Article
Collection: School of Exercise and Nutrition Sciences
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 14 times in TR Web of Science
Scopus Citation Count Cited 20 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 94 Abstract Views, 3 File Downloads  -  Detailed Statistics
Created: Thu, 17 Sep 2015, 14:03:38 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.