Deformable registration of X-ray and MRI for post-implant dosimetry in low-dose-rate prostate brachytherapy

Abstract

Purpose Dosimetric assessment following permanent prostate brachytherapy (PPB) commonly involves seed localization using CT and prostate delineation using coregistered MRI. However, pelvic CT leads to additional imaging dose and requires significant resources to acquire and process both CT and MRI. In this study, we propose an automatic postimplant dosimetry approach that retains MRI for soft‐tissue contouring, but eliminates the need for CT and reduces imaging dose while overcoming the inconsistent appearance of seeds on MRI with three projection x rays acquired using a mobile C‐arm. Methods Implanted seeds are reconstructed using x rays by solving a combinatorial optimization problem and deformably registered to MRI. Candidate seeds are located in MR images using local hypointensity identification. X ray‐based seeds are registered to these candidate seeds in three steps: (a) rigid registration using a stochastic evolutionary optimizer, (b) affine registration using an iterative closest point optimizer, and (c) deformable registration using a local feature point search and nonrigid coherent point drift. The algorithm was evaluated using 20 PPB patients with x rays acquired immediately postimplant and T2‐weighted MR images acquired the next day at 1.5 T with mean 0.8 × 0.8 × 3.0 mmurn:x-wiley:00942405:media:mp13667:mp13667-math-0001 voxel dimensions. Target registration error (TRE) was computed based on the distance from algorithm results to manually identified seed locations using coregistered CT acquired the same day as the MRI. Dosimetric accuracy was determined by comparing prostate D90 determined using the algorithm and the ground truth CT‐based seed locations. Results The mean ± standard deviation TREs across 20 patients including 1774 seeds were 2.23 ± 0.52 mm (rigid), 1.99 ± 0.49 mm (rigid + affine), and 1.76 ± 0.43 mm (rigid + affine + deformable). The corresponding mean ± standard deviation D90 errors were 5.8 ± 4.8%, 3.4 ± 3.4%, and 2.3 ± 1.9%, respectively. The mean computation time of the registration algorithm was 6.1 s. Conclusion The registration algorithm accuracy and computation time are sufficient for clinical PPB postimplant dosimetry.