You are not logged in.
Openly accessible

Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method

Chu, Chengwen, Belavy, Daniel L., Armbrecht, Gabriele, Bansmann, Martin, Felsenberg, Dieter and Zheng, Guoyan 2015, Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method, PLoS One, vol. 10, no. 11, Article Number : e0143327, pp. 1-22, doi: 10.1371/journal.pone.0143327.

Attached Files
Name Description MIMEType Size Downloads
belavy-fullyautomatic-2015.pdf Published version application/pdf 7.07MB 16

Title Fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images via a learning-based method
Author(s) Chu, Chengwen
Belavy, Daniel L.ORCID iD for Belavy, Daniel L. orcid.org/0000-0002-9307-832X
Armbrecht, Gabriele
Bansmann, Martin
Felsenberg, Dieter
Zheng, Guoyan
Journal name PLoS One
Volume number 10
Issue number 11
Season Article Number : e0143327
Start page 1
End page 22
Total pages 22
Publisher Public Library of Science (PLOS)
Place of publication San Francisco, Calif.
Publication date 2015
ISSN 1932-6203
Keyword(s) Science & Technology
Multidisciplinary Sciences
Science & Technology - Other Topics
SPINAL MRI
MODEL
CUTS
3-D
CT
Summary In this paper, we address the problems of fully automatic localization and segmentation of 3D vertebral bodies from CT/MR images. We propose a learning-based, unified random forest regression and classification framework to tackle these two problems. More specifically, in the first stage, the localization of 3D vertebral bodies is solved with random forest regression where we aggregate the votes from a set of randomly sampled image patches to get a probability map of the center of a target vertebral body in a given image. The resultant probability map is then further regularized by Hidden Markov Model (HMM) to eliminate potential ambiguity caused by the neighboring vertebral bodies. The output from the first stage allows us to define a region of interest (ROI) for the segmentation step, where we use random forest classification to estimate the likelihood of a voxel in the ROI being foreground or background. The estimated likelihood is combined with the prior probability, which is learned from a set of training data, to get the posterior probability of the voxel. The segmentation of the target vertebral body is then done by a binary thresholding of the estimated probability. We evaluated the present approach on two openly available datasets: 1) 3D T2-weighted spine MR images from 23 patients and 2) 3D spine CT images from 10 patients. Taking manual segmentation as the ground truth (each MR image contains at least 7 vertebral bodies from T11 to L5 and each CT image contains 5 vertebral bodies from L1 to L5), we evaluated the present approach with leave-one-out experiments. Specifically, for the T2-weighted MR images, we achieved for localization a mean error of 1.6 mm, and for segmentation a mean Dice metric of 88.7% and a mean surface distance of 1.5 mm, respectively. For the CT images we achieved for localization a mean error of 1.9 mm, and for segmentation a mean Dice metric of 91.0% and a mean surface distance of 0.9 mm, respectively.
Language eng
DOI 10.1371/journal.pone.0143327
Field of Research 110699 Human Movement and Sports Science not elsewhere classified
Socio Economic Objective 920116 Skeletal System and Disorders (incl. Arthritis)
HERDC Research category C1 Refereed article in a scholarly journal
ERA Research output type C Journal article
Copyright notice ©2015, Information Age Publishing
Persistent URL http://hdl.handle.net/10536/DRO/DU:30080608

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

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.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in TR Web of Science
Scopus Citation Count Cited 4 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 72 Abstract Views, 17 File Downloads  -  Detailed Statistics
Created: Fri, 08 Jan 2016, 14:15:27 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.