No Access

GRID-ENABLED NON-RIGID REGISTRATION OF MEDICAL IMAGES

RADU STEFANESCU

INRIA Sophia-Antipolis, Epidaure Project, 2004 Route des Lucioles, BP 93 06902 Sophia-Antipolis, France

Search for more papers by this author

XAVIER PENNEC

INRIA Sophia-Antipolis, Epidaure Project, 2004 Route des Lucioles, BP 93 06902 Sophia-Antipolis, France

Search for more papers by this author

, and

NICHOLAS AYACHE

INRIA Sophia-Antipolis, Epidaure Project, 2004 Route des Lucioles, BP 93 06902 Sophia-Antipolis, France

Search for more papers by this author

https://doi.org/10.1142/S0129626404001830Cited by:3 (Source: Crossref)

Abstract

Over recent years, non-rigid registration has become a major issue in medical imaging. It consists in recovering a dense point-to-point correspondence field between two images, and usually takes a long time. This is in contrast to the needs of a clinical environment, where usability and speed are major constraints, leading to the necessity of reducing the computation time from slightly less than an hour to just a few minutes. As financial pressure makes it hard for healthcare organizations to invest in expensive high-performance computing (HPC) solutions, cluster computing proves to be a convenient solution to our computation needs, offering a large processing power at a low cost. Among the fast and efficient non-rigid registration methods, we chose the demons algorithm for its simplicity and good performances. The parallel implementation decomposes the correspondence field into spatial blocks, each block being assigned to a node of the cluster. We obtained an acceleration of 11 by using 15 2GHz PC's connected through a 1GB/s Ethernet network and reduced the computation time from 40min to 3min30. In order to further optimize the costs and the maintenance load, we investigate in the second part the transparent use of shared computing resources, either through a graphic client or a Web one.

Keywords:

References

D. T. Geringet al., Journal of Magnetic Resonance Imaging 13, 967 (2001), DOI: 10.1002/jmri.1139. Crossref, Web of Science, Google Scholar
X. Pennec et al. , Multi-Sensor Image Fusion and Its Applications , eds. R. S. Blum and Zh. Liu ( Marcel Dekker Inc. , 2005 ) . Google Scholar
O. Skrinjar, A. Nabavi and J. Duncan, Medical Image Analysis 6(4), 361 (2002), DOI: 10.1016/S1361-8415(02)00062-2. Crossref, Web of Science, Google Scholar
T. Rohlfing and C. R. Maurer Jr., IEEE Transactions on Information Technology in Biomedicine 7(1), 16 (2003), DOI: 10.1109/TITB.2003.808506. Crossref, Web of Science, Google Scholar
H. Muller , Grid Computing at the University Hospital of Geneva , Proc. of HealthGrid 2003 ( 2003 ) . Google Scholar
C. Broit, Optimal Registration of Deformed Images, PhD thesis, University of Pennsylvania, August 1981 . Google Scholar
R. Bajcsy and S. Kovačič, Computer Vision, Graphics and Image Processing 46, 1 (1989), DOI: 10.1016/S0734-189X(89)80014-3. Crossref, Google Scholar
J.-P. Thirion, Medical Image Analysis 2(3), (1998), DOI: 10.1016/S1361-8415(98)80022-4. Google Scholar
P. Cachieret al., CVIU - Special Issue on Nonrigid Registration 89, 272 (2003). Google Scholar
X. Pennec, P. Cachier and N. Ayache, Understanding the "Demon's Algorithm": 3D Non-Rigid registration by Gradient Descent, Proc. of Medical Image Computing and Computer-Assisted Intervention (MICCAI'99), LNCS 1679 (Springer Verlag, 1999) pp. 597–605. Google Scholar
J. Rexiliuset al., A Novel Non-Rigid Registration Algorithm and Applications, Proc. of Medical Image Computing and Computer-Assisted Intervention (MICCAI'01), LNCS 2208 (Springer Verlag, 2001) pp. 923–931. Google Scholar
D. Rueckertet al., IEEE Trans. Medical Imaging 18(8), 712 (1999), DOI: 10.1109/42.796284. Crossref, Web of Science, Google Scholar
R. Deriche, Recursively Implementing the Gaussian and Its Derivatives, Proc. of The Second International Conference On Image Processing (1992) pp. 263–267. Google Scholar
E. Bardinetet al., A Posteriori Validation of Pre-operative Planning in Functional Neurosurgery by Quantification of Brain Pneumocephalus, Proc. of Medical Image Computing and Computer-Assisted Intervention (MICCAI'02), LNCS 2488 (Springer Verlag, 2002) pp. 323–330. Google Scholar
R. Stefanescu , X. Pennec and N. Ayache , A Grid Service for the Interactive Use of a Parallel Non-Rigid Registration Algorithm , Proc. of HealthGrid 2004 ( 2004 ) . Google Scholar
G. Bosilca et al. , MPICH-V: Toward a Scalable Fault Tolerant MPI for Volatile Nodes , Proc. of ACM/IEEE International Conference on Supercomputing SC 2002 ( 2002 ) . Google Scholar
D. Hill et al. , Intraoperable Medical Image Registration Grid Service , Proc. of HealthGrid 2004 ( 2004 ) . Google Scholar
R. Ziegler , Pharma GRIDS: Key to Pharmaceutical Innovation? , Proc. of HealthGrid 2004 ( 2004 ) . Google Scholar