GPU Accelerated Registration of a Statistical Shape Model of the Lumbar Spine to 3D Ultrasound Images
Dept. of Electrical and Computer Engineering, Queen’s University, Kingston, ON, Canada
Proceedings of SPIE, Volume 7964, 79642W, 2011
@inproceedings{khallaghi2011gpu,
title={GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images.},
author={Khallaghi, S. and Abolmaesumi, P. and Gong, R.H. and Chen, E. and Gill, S. and Boisvert, J. and Pichora, D. and Borschneck, D. and Fichtinger, G. and Mousavi, P.},
year={2011},
organization={Society of Photo-Optical Instrumentation Engineers}
}
We present a parallel implementation of a statistical shape model registration to 3D ultrasound images of the lumbar vertebrae (L2-L4). Covariance Matrix Adaptation Evolution Strategy optimization technique, along with Linear Correlation of Linear Combination similarity metric have been used, to improve the robustness and capture range of the registration approach. Instantiation and ultrasound simulation have been implemented on a graphics processing unit for a faster registration. Phantom studies show a mean target registration error of 3.2 mm, while 80% of all the cases yield target registration error of below 3.5 mm.
January 18, 2012 by hgpu
