Deformable image registration for radiation therapy: principle, methods, applications and evaluation

Abstract

Background: Deformable image registration (DIR) is increasingly used in the field of radiation therapy (RT) to account for anatomical deformations. The aims of this paper are to describe the main applications of DIR in RT and discuss current DIR evaluation methods. Methods: Articles on DIR published from January 2000 to October 2018 were extracted from PubMed and Science Direct. Our search was restricted to articles that report data obtained from humans, were written in English, and address DIR methods for RT. A total of 207 articles were selected from among 2506 identified in the search process. Results: At planning, DIR is used for organ delineation using atlas-based segmentation, deformationbased planning target volume definition, functional planning and magnetic resonance imaging-based dose calculation. In image-guided RT, DIR is used for contour propagation and dose calculation on per-treatment imaging. DIR is also used to determine the accumulated dose from fraction to fraction in external beam RT and brachytherapy, both for dose reporting and adaptive RT. In the case of reirradiation, DIR can be used to estimate the cumulated dose of the two irradiations. Finally, DIR can be used to predict toxicity in voxel-wise population analysis. However, the evaluation of DIR remains an open issue, especially when dealing with complex cases such as the disappearance of matter. To quantify DIR uncertainties, most evaluation methods are limited to geometry-based metrics. Software companies have now integrated DIR tools into treatment planning systems for clinical use, such as contour propagation and fraction dose accumulation. Conclusions: DIR is increasingly important in RT applications, from planning to toxicity prediction. DIR is routinely used to reduce the workload of contour propagation. However, its use for complex dosimetric applications must be carefully evaluated by combining quantitative and qualitative analyses.

An international survey on the clinical use of rigid and deformable image registration in radiotherapy

“…Survey data inherently not robust enough for general validation 30 and use. 8 In scenarios where DIR is challenging (e.g., tissue appearance or disappearance 6,31 or large deformations 6 ), accurate use requires appropriate management of uncertainties. 4 Data on the use of RIR with multi-modality imaging show the rel- noise and streaking 32,33 for contour propagation, or image truncation 32,34 for synthetic CT generation 35 which may creep into the implementation of adaptive radiotherapy.…”

Comparison of CBCT‐based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning

“…Moreover, the registration step is complex owing to large anatomical variations, such as tumor shrinkage or weight loss. 17 d) Machine learning methods are based on patches or deep learning (DL), to generate a pCT (i.e., synthetic images) from CBCT. Machine learning methods require a large training cohort and most of these methods require coregistered data for the training step.…”

Cross-Domain Data Augmentation for Deep-Learning-Based Male Pelvic Organ Segmentation in Cone Beam CT

“…Currently, organ segmentation is classically performed by deformable image registration (DIR) algorithms between the planning CT and daily CBCT scans [7,8]. These algorithms include such clinical software packages as MIM [9] and RayStation [10].…”