RESUMEN
Background and Purpose: Deformable image registration (DIR) is a core element of adaptive radiotherapy workflows, integrating daily contour propagation and/or dose accumulation in their design. Propagated contours are usually manually validated and may be edited, thereby locally invalidating the registration result. This means the registration cannot be used for dose accumulation. In this study we proposed and evaluated a novel multi-modal DIR algorithm that incorporated contour information to guide the registration. This integrates operator-validated contours with the estimated deformation vector field and warped dose. Materials and Methods: The proposed algorithm consisted of both a normalized gradient field-based data-fidelity term on the images and an optical flow data-fidelity term on the contours. The Helmholtz-Hodge decomposition was incorporated to ensure anatomically plausible deformations. The algorithm was validated for same- and cross-contrast Magnetic Resonance (MR) image registrations, Computed Tomography (CT) registrations, and CT-to-MR registrations for different anatomies, all based on challenging clinical situations. The contour-correspondence, anatomical fidelity, registration error, and dose warping error were evaluated. Results: The proposed contour-guided algorithm considerably and significantly increased contour overlap, decreasing the mean distance to agreement by a factor of 1.3 to 13.7, compared to the best algorithm without contour-guidance. Importantly, the registration error and dose warping error decreased significantly, by a factor of 1.2 to 2.0. Conclusions: Our contour-guided algorithm ensured that the deformation vector field and warped quantitative information were consistent with the operator-validated contours. This provides a feasible semi-automatic strategy for spatially correct warping of quantitative information even in difficult and artefacted cases.
RESUMEN
BACKGROUND: Deformable image registration is increasingly used in radiotherapy to adapt the treatment plan and accumulate the delivered dose. Consequently, clinical workflows using deformable image registration require quick and reliable quality assurance to accept registrations. Additionally, for online adaptive radiotherapy, quality assurance without the need for an operator to delineate contours while the patient is on the treatment table is needed. Established quality assurance criteria such as the Dice similarity coefficient or Hausdorff distance lack these qualities and also display a limited sensitivity to registration errors beyond soft tissue boundaries. PURPOSE: The purpose of this study is to investigate the existing intensity-based quality assurance criteria structural similarity and normalized mutual information for their ability to quickly and reliably identify registration errors for (online) adaptive radiotherapy and compare them to contour-based quality assurance criteria. METHODS: All criteria were tested using synthetic and simulated biomechanical deformations of 3D MR images as well as manually annotated 4D CT data. The quality assurance criteria were scored for classification performance, for their ability to predict the registration error, and for their spatial information. RESULTS: We found that besides being fast and operator-independent, the intensity-based criteria have the highest area under the receiver operating characteristic curve and provide the best input for models to predict the registration error on all data sets. Structural similarity furthermore provides spatial information with a higher gamma pass rate of the predicted registration error than commonly used spatial quality assurance criteria. CONCLUSIONS: Intensity-based quality assurance criteria can provide the required confidence in decisions about using mono-modal registrations in clinical workflows. They thereby enable automated quality assurance for deformable image registration in adaptive radiotherapy treatments.
