A parallel-friendly normalised mutual information gradient for registration: comparison with the analytic gradient

Modat, Marc, Ridgway, Gerard R., Taylor, Zeike A., Hawkes, David J., Fox, Nick C. and Ourselin, Sebastien (2009). A parallel-friendly normalised mutual information gradient for registration: comparison with the analytic gradient. In: Proceedings of SPIE. SPIE Medical Imaging 2009, Lake Buena Vista, Florida, USA, (1-8). 7-12 February, 2009. doi:10.1117/12.811588

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
UQ220514_OA.pdf Full text (open access) application/pdf 424.22KB 0

Author Modat, Marc
Ridgway, Gerard R.
Taylor, Zeike A.
Hawkes, David J.
Fox, Nick C.
Ourselin, Sebastien
Title of paper A parallel-friendly normalised mutual information gradient for registration: comparison with the analytic gradient
Conference name SPIE Medical Imaging 2009
Conference location Lake Buena Vista, Florida, USA
Conference dates 7-12 February, 2009
Proceedings title Proceedings of SPIE   Check publisher's open access policy
Place of Publication Washington, D. C., U.S.A.
Publisher SPIE - International Society for Optical Engineering
Publication Year 2009
Sub-type Fully published paper
DOI 10.1117/12.811588
Open Access Status File (Publisher version)
ISSN 0277-786X
Volume 7259
Issue 72590L
Start page 1
End page 8
Total pages 8
Language eng
Abstract/Summary Non-rigid registration techniques are commonly used in medical image analysis. However these techniques are often time consuming. Graphics Processing Unit (GPU) execution appears to be a good way to decrease computation time significantly. However for an efficient implementation on GPU, an algorithm must be data parallel. In this paper we compare the analytical calculation of the gradient of Normalised Mutual Information with an approximation better suited to parallel implementation. Both gradient approaches have been implemented using a Free-Form Deformation framework based on cubic B-Splines and including a smoothness constraint. We applied this technique to recover realistic deformation fields generated from 65 3D-T1 images. The recovered fields using both gradients and the ground truth were compared. We demonstrated that the approximated gradient performed similarly to the analytical gradient but with a greatly reduced computation time when both approaches are implemented on the CPU. The implementation of the approximated gradient on the GPU leads to a computation time of 3 to 4 minutes when registering 190 × 200 × 124 voxel images with a grid including 57 × 61 × 61 control points.
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status Unknown

Document type: Conference Paper
Collection: School of Medicine Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 2 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 16 Nov 2010, 21:09:16 EST by Dr Zeike Taylor on behalf of Centre for Medical Diagnostic Technologies in Qld