27 February 2010 Rapid block matching based nonlinear registration on GPU for image guided radiation therapy
Author Affiliations +
To compensate for non-uniform deformation due to patient motion within and between fractions in image guided radiation therapy, a block matching technique was adapted and implemented on a standard graphics processing unit (GPU) to determine the displacement vector field that maps the nonlinear transformation between successive CT images. Normalized cross correlation (NCC) was chosen as the similarity metric for the matching step, with regularization of the displacement vector field being performed by Gaussian smoothing. A multi-resolution framework was adopted to further improve the performance of the algorithm. The nonlinear registration algorithm was first applied to estimate the intrafractional motion from 4D lung CT images. It was also used to calculate the inter-fractional organ deformation between planning CT (PCT) and Daily Cone Beam CT (CBCT) images of thorax. For both experiments, manual landmark-based evaluation was performed to quantify the registration performance. In 4D CT registration, the mean TRE of 5 cases was 1.75 mm. In PCT-CBCT registration, the TRE of one case was 2.26mm. Compared to the CPU-based AtamaiWarp program, our GPU-based implementation achieves comparable registration accuracy and is ~25 times faster. The results highlight the potential utility of our algorithm for online adaptive radiation treatment.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
An Wang, Brandon Disher, Greg Carnes, and Terry M. Peters "Rapid block matching based nonlinear registration on GPU for image guided radiation therapy", Proc. SPIE 7625, Medical Imaging 2010: Visualization, Image-Guided Procedures, and Modeling, 762511 (27 February 2010); doi: 10.1117/12.843935; https://doi.org/10.1117/12.843935

Back to Top