Contour‐guided deep learning based deformable image registration for dose monitoring during CBCT‐guided radiotherapy of prostate cancer

Abstract

To evaluate deep learning (DL)-based deformable image registration (DIR) for dose accumulation during radiotherapy of prostate cancer patients. Methods and Materials: Data including 341 CBCTs (209 daily, 132 weekly) and 23 planning CTs from 23 patients was retrospectively analyzed. Anatomical deformation during treatment was estimated using free-form deformation (FFD) method from Elastix and DL-based VoxelMorph approaches. The VoxelMorph method was investigated using anatomical scans (VMorph_Sc) or label images (VMorph_Msk), or the combination of both (VMorph_Sc_Msk). Accumulated doses were compared with the planning dose. Results: The DSC ranges, averaged for prostate, rectum and bladder, were 0.60-0.71, 0.67-0.79, 0.93-0.98, and 0.89-0.96 for the FFD, VMorph_Sc, VMorph_Msk, and VMorph_Sc_Msk methods, respectively. When including both anatomical and label images, VoxelMorph estimated more complex deformations resulting in heterogeneous determinant of Jacobian and higher percentage of deformation vector field (DVF) folding (up to a mean value of 1.90% in the prostate). Large differences were observed between DL-based methods regarding estimation of the accumulated dose, showing systematic overdosage and underdosage of the bladder and rectum, respectively. The difference between planned mean dose and accumulated mean dose with VMorph_Sc_Msk reached a median value of +6.3 Gy for the bladder and −5.1 Gy for the rectum. Conclusion:The estimation of the deformations using DL-based approach is feasible for male pelvic anatomy but requires the inclusion of anatomical contours to improve organ correspondence. High variability in the estimation of the accumulated dose depending on the deformable strategy suggests further investigation of DL-based techniques before clinical deployment.

Deep‐learning‐based joint rigid and deformable contour propagation for magnetic resonance imaging‐guided prostate radiotherapy

“…Most deformable registration methods for prostate MRgRT rely on U‐Net, 13,14,16,17 but there are limited comparisons to other CNN architectures. We investigated three promising 3D architectures for deformable registration: a U‐Net, a mixed‐scale dense (MS‐D) network, and a Laplacian pyramid image registration network (LapIRN).…”

“…Furthermore, which network architecture is optimal for contour propagation in online adaptive MRgRT needs to be clarified. Many existing registration approaches rely on encoder–decoder network architectures such as the U‐Net 13,14,16,17 . Other promising network architectures have yet to be thoroughly investigated for prostate MRgRT 18,19 .…”