Hardware Accelerated Image Registration and Dose Calculation for Adaptive Radiation Therapy

Purpose/Objectives: Adaptive radiation therapy (ART) is a process to improve radiation treatment by adaptively monitoring treatment variations and incorporate them to re-optimize the treatment plan during the course of treatment. A critical requirement of ART is the knowledge of the anatomical changes as well as the actual dose delivered to the patient during the course of treatment. While cone-beam CT (CBCT) is typically used to minimize the patient setup error and monitor daily anatomical changes, its poor quality impedes accurate segmentation of the target structures and the dose computation. We developed an integrated ART software platform that combines fast and accurate image registration, segmentation, and dose computation/accumulation methods. The developed platform automatically links patient images, radiotherapy plan, beam and dosimetric parameters, and daily treatment information, thus providing an efficient ART workflow.

Methods: The proposed system consists of three key components; 1) deformable image registration (DIR), 2) automatic segmentation, and 3) dose computation/accumulation. The computationally intensive modules including DIR and dose computation have been parallelized and implemented on graphic processing units (GPUs). All required patient-specific data including the planning CT (pCT) with contours, daily cone-beam CTs, and treatment plan are automatically queried and retrieved from their own databases to our platform. To improve the accuracy of DIR between the planning CT and CBCTs, we iteratively correct CBCT intensities by matching local intensity histograms in conjunction with the DIR process. The GPU-accelerated double force demons algorithm is employed for DIR. Segmentation for daily CBCT is then obtained by propagating contours from the pCT using the displacement vector field. Daily dose delivered to the patient is then computed on the registered pCT by a GPU-accelerated superposition/convolution algorithm. Finally, computed daily doses are accumulated to show the total delivered dose to date.