Automated segmentation of the quadratus lumborum muscle from magnetic resonance images using a hybrid atlas based - geodesic active contour scheme

Jurcak,V., Fripp, J., Engstrom, C., Walker, D., Salvado, O., Ourselin, S. and Crozier, S. (2008). Automated segmentation of the quadratus lumborum muscle from magnetic resonance images using a hybrid atlas based - geodesic active contour scheme. In: IEEE Engineering in Medicine and Biology Society Conference Proceedings, EMBS 2008. 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2008, Vancouver, Canada, (867-870). 20-25 Aug 2008. doi:10.1109/IEMBS.2008.4649291


Author Jurcak,V.
Fripp, J.
Engstrom, C.
Walker, D.
Salvado, O.
Ourselin, S.
Crozier, S.
Title of paper Automated segmentation of the quadratus lumborum muscle from magnetic resonance images using a hybrid atlas based - geodesic active contour scheme
Conference name 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2008
Conference location Vancouver, Canada
Conference dates 20-25 Aug 2008
Proceedings title IEEE Engineering in Medicine and Biology Society Conference Proceedings, EMBS 2008   Check publisher's open access policy
Journal name 2008 30Th Annual International Conference of the Ieee Engineering in Medicine and Biology Society, Vols 1-8   Check publisher's open access policy
Place of Publication New York, USA
Publisher IEEE
Publication Year 2008
Sub-type Fully published paper
DOI 10.1109/IEMBS.2008.4649291
ISBN 978-1-4244-1814-5
ISSN 1557-170X
Volume 1-8
Start page 867
End page 870
Total pages 4
Language eng
Abstract/Summary This study presents a novel method for the automatic segmentation of the quadratus lumborum (QL) muscle from axial magnetic resonance (MR) images using a hybrid scheme incorporating the use of non-rigid registration with probabilistic atlases (PAs) and geodesic active contours (GACs). The scheme was evaluated on an MR database of 7mm axial images of the lumbar spine from 20 subjects (fast bowlers and athletic controls). This scheme involved several steps, including (i) image pre-processing, (ii) generation of PAs for the QL, psoas (PS) and erector spinae+multifidus (ES+MT) muscles and (iii) segmentation, using 3D GACs initialized and constrained by the propagation of the PAs using non-rigid registration. Pre-processing of the images involved bias field correction based on local entropy minimization with a bicubic spline model and a reverse diffusion interpolation algorithm to increase the slice resolution to 0.98x0.98x1.75mm. The processed images were then registered (affine and non-rigid) and used to generate an average atlas. The PAs for the QL, PS and ES+MT were then generated by propagation of manual segmentations. These atlases were further analysed with specialised filtering to constrain the QL segmentation from adjacent non-muscle tissues (kidney, fat). This information was then used in 3D GACs to obtain the final segmentation of the QL. The automatic segmentation results were compared with the manual segmentations using the Dice similarity metric (DSC), with a median DSC for the right and left QL muscles of 0.78 (mean=0.77, sd=0.07) and 0.75 (mean=0.74, sd=0.07), respectively.
Subjects 0903 Biomedical Engineering
Keyword quadratus lumborum
geodesic active contours
automatic segmentation
probability atlases
MRI
Q-Index Code E1
Q-Index Status Provisional Code

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Fri, 22 Jan 2010, 01:01:25 EST by Thelma Whitbourne on behalf of Faculty Of Engineering, Architecture & Info Tech