Deep learning-enhanced image registration for accelerating daily adaptive magnetic resonance imaging-guided prostate radiotherapy

Background and purpose: Daily auto-contouring remains a workflow bottleneck in magnetic resonance-guided adaptive prostate radiotherapy (MRgRT). This study proposes and clinically validates a novel deep learning-enhanced deformable image registration (DIR) solution to accelerate this critical step. Materials and Methods: A hybrid framework combining a 3D nnU-Net segmenting bladder/rectum on planning/daily MRI with an in-house DIR algorithm was implemented for 5-fraction prostate MRgRT ((Formula presented) Gy) on an MR-Linac. The DIR uses nnU-Net contours to propagate target and organs-of-interest structures. The solution was clinically deployed and evaluated in 275 patients/1375 fractions. Results: Evaluation following clinical introduction, has shown a median contouring time of ≈[jls-end-space/]190 s, halving the time required by the previously-employed vendor-provided solution. Quantitative evaluation showed high agreement with clinically approved contours: Dice similarity coefficients >[jls-end-space/]0.9 and 95th percentile Hausdorff distances <[jls-end-space/]2.0 mm for most structures. Conclusions: The implemented solution demonstrated reliable, high-accuracy daily auto-contouring, significantly accelerating MRgRT workflows. It has become our institutional standard for prostate treatments. Future work will extend this approach to additional treatment sites and modalities.