GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images
Published in SPIE Medical Imaging, 2011
Recommended citation: Khallaghi S, Abolmaesumi P, Gong R, Chen ECS, Gill S, Boisvert J, Pichora D, Borschneck D, Fichtinger G, Mousavi P, (2011). "GPU accelerated registration of a statistical shape model of the lumbar spine to 3D ultrasound images"; SPIE Medical Imaging: Visualization, Image-Guided Procedures, and Modeling, 79642W, pp. 871-878. https://doi.org/10.1117/12.878377
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.