A Contour-Guided Deformable Image Registration Algorithm for Adaptive Radiotherapy

Xuejun Gu, Bin Dong, Jing Wang, John Yordy, Loren Mell, Xun Jia, Steve B. Jiang
Center for Advanced Radiotherapy Technologies and Department of Radiation, Medicine and Applied Sciences, University of California San Diego, La Jolla, CA 92037-0843, USA
University of California San Diego, 2012


   title={A Contour-Guided Deformable Image Registration Algorithm for Adaptive Radiotherapy},

   author={Gu, X. and Dong, B. and Wang, J. and Yordy, J. and Mell, L. and Jia, X. and Jiang, S.B.},



Download Download (PDF)   View View   Source Source   



In adaptive radiotherapy, a deformable image registration is often conducted between the planning CT and the treatment CT (or cone beam CT) to generate a deformation vector field (DVF) for dose accumulation and contour propagation. The auto-propagated contours on the treatment CT may contain relatively large errors especially in low-contrast regions. Clinician’s inspection and editing on the propagated contours are always necessary. The edited contours are able to meet the clinical requirement for adaptive therapy; however, the DVF is still inaccurate and inconsistent with the edited contours. The purpose of this work is to develop a contour-guided deformable image registration (CG-DIR) algorithm to improve the accuracy and consistency of the DVF for adaptive radiotherapy. The incorporation of the edited contours into the registration algorithm is realized by regularizing the objective function of the original demons algorithm with a term of intensity matching between the delineated structures set pairs. The CG-DIR algorithm is implemented on computer graphics processing units (GPUs) by following the original GPU-based demons algorithm computation framework [Gu et al, Phys Med Biol. 55(1): 207-219, 2010]. The performance of CG-DIR is evaluated on five clinical head-and-neck and one pelvic cancer patient data. It is found that CG-DIR improves the accuracy and consistency of the DVF when compared with the original demons, while keeps the high computational efficiency of the original GPU-based demons.
No votes yet.
Please wait...

* * *

* * *

HGPU group © 2010-2021 hgpu.org

All rights belong to the respective authors

Contact us: