Accuracy and consistency of intensity-based deformable image registration in 4DCT for tumor motion estimation in liver radiotherapy planning.
Ontology highlight
ABSTRACT:
SUBMITTER: Tascon-Vidarte JD
PROVIDER: S-EPMC9269460 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:We present INSPIRE, a top-performing general-purpose method for deformable image registration. INSPIRE brings distance measures which combine intensity and spatial information into an elastic B-splines-based transformation model and incorporates an inverse inconsistency penalization supporting symmetric registration performance. We introduce several theoretical and algorithmic solutions which provide high computational efficiency and thereby applicability of the proposed framework in a wide range of real scenarios. We show that INSPIRE delivers highly accurate, as well as stable and robust registration results. We evaluate the method on a 2D dataset created from retinal images, characterized by presence of networks of thin structures. Here INSPIRE exhibits excellent performance, substantially outperforming the widely used reference methods. We also evaluate INSPIRE on the Fundus Image Registration Dataset (FIRE), which consists of 134 pairs of separately acquired retinal images. INSPIRE exhibits excellent performance on the FIRE dataset, substantially outperforming several domain-specific methods. We also evaluate the method on four benchmark datasets of 3D magnetic resonance images of brains, for a total of 2088 pairwise registrations. A comparison with 17 other state-of-the-art methods reveals that INSPIRE provides the best overall performance. Code is available at github.com/MIDA-group/inspire.
| S-EPMC9983883 | biostudies-literature
Project description:Deformable image registration (DIR) is a versatile tool used in many applications in radiotherapy (RT). DIR algorithms have been implemented in many commercial treatment planning systems providing accessible and easy-to-use solutions. However, the geometric uncertainty of DIR can be large and difficult to quantify, resulting in barriers to clinical practice. Currently, there is no agreement in the RT community on how to quantify these uncertainties and determine thresholds that distinguish a good DIR result from a poor one. This review summarises the current literature on sources of DIR uncertainties and their impact on RT applications. Recommendations are provided on how to handle these uncertainties for patient-specific use, commissioning, and research. Recommendations are also provided for developers and vendors to help users to understand DIR uncertainties and make the application of DIR in RT safer and more reliable.
| S-EPMC10725576 | biostudies-literature
Project description:PurposeThe accuracy of deformable image registration tools can vary widely between imaging modalities and specific implementations of the same algorithms. A biomechanical model-based algorithm initially developed in-house at an academic institution was translated into a commercial radiotherapy treatment planning system and validated for multiple imaging modalities and anatomic sites.MethodsBiomechanical deformable registration (Morfeus) is a geometry-driven algorithm based on the finite element method. Boundary conditions are derived from the model-based segmentation of controlling structures in each image which establishes a point-to-point surface correspondence. For each controlling structure, material properties and fixed or sliding interfaces are assigned. The displacements of internal volumes for controlling structures and other structures implicitly deformed are solved with finite element analysis. Registration was performed for 74 patients with images (mean vector resolution) of thoracic and abdominal 4DCT (2.8 mm) and MR (5.3 mm), liver CT-MR (4.5 mm), and prostate MR (2.6 mm). Accuracy was quantified between deformed and actual target images using distance-to-agreement (DTA) for structure surfaces and the target registration error (TRE) for internal point landmarks.ResultsThe results of the commercial implementation were as follows. The mean DTA was ≤ 1.0 mm for controlling structures and 1.0-3.5 mm for implicitly deformed structures on average. TRE ranged from 2.0 mm on prostate MR to 5.1 mm on lung MR on average, within 0.1 mm or lower than the image voxel sizes. Accuracy was not overly sensitive to changes in the material properties or variability in structure segmentations, as changing these inputs affected DTA and TRE by ≤ 0.8 mm. Maximum DTA > 5 mm occurred for 88% of the structures evaluated although these were within the inherent segmentation uncertainty for 82% of structures. Differences in accuracy between the commercial and in-house research implementations were ≤ 0.5 mm for mean DTA and ≤ 0.7 mm for mean TRE.ConclusionsAccuracy of biomechanical deformable registration evaluated on a large cohort of images in the thorax, abdomen and prostate was similar to the image voxel resolution on average across multiple modalities. Validation of this treatment planning system implementation supports biomechanical deformable registration as a versatile clinical tool to enable accurate target delineation at planning and treatment adaptation.
| S-EPMC5535790 | biostudies-literature
Project description:Percutaneous pelvic screw placement is challenging due to narrow bone corridors surrounded by vulnerable structures and difficult visual interpretation of complex anatomical shapes in 2D x-ray projection images. To address these challenges, a system for planning, guidance, and quality assurance (QA) is presented, providing functionality analogous to surgical navigation, but based on robust 3D-2D image registration techniques using fluoroscopy images already acquired in routine workflow. Two novel aspects of the system are investigated: automatic planning of pelvic screw trajectories and the ability to account for deformation of surgical devices (K-wire deflection). Atlas-based registration is used to calculate a patient-specific plan of screw trajectories in preoperative CT. 3D-2D registration aligns the patient to CT within the projective geometry of intraoperative fluoroscopy. Deformable known-component registration (dKC-Reg) localizes the surgical device, and the combination of plan and device location is used to provide guidance and QA. A leave-one-out analysis evaluated the accuracy of automatic planning, and a cadaver experiment compared the accuracy of dKC-Reg to rigid approaches (e.g. optical tracking). Surgical plans conformed within the bone cortex by 3-4?mm for the narrowest corridor (superior pubic ramus) and??>5?mm for the widest corridor (tear drop). The dKC-Reg algorithm localized the K-wire tip within 1.1?mm and 1.4° and was consistently more accurate than rigid-body tracking (errors up to 9?mm). The system was shown to automatically compute reliable screw trajectories and accurately localize deformed surgical devices (K-wires). Such capability could improve guidance and QA in orthopaedic surgery, where workflow is impeded by manual planning, conventional tool trackers add complexity and cost, rigid tool assumptions are often inaccurate, and qualitative interpretation of complex anatomy from 2D projections is prone to trial-and-error with extended fluoroscopy time.
| S-EPMC5868367 | biostudies-literature
Project description:Background and purposeHead-Neck (HN) patients may experience severe acute skin complications that can cause treatment interruption and increase the risk of late fibrosis. This study assessed a method for accurately monitoring skin dose changes during helical tomotherapy for HN cancer based on deformable image registration of planning computed tomography (CT) and mega-voltage CT (MVCT).Materials and methodsPlanning CTs of nine patients were deformably registered to mid-treatment MVCT (MV15) images resulting in CTdef images. The original plans were recalculated on both CTdef and mid-treatment kilo-voltage CT (CT15) taken as ground truth. Superficial layers (SL) of the body with thicknesses of 2, 3 and 5 mm (SL2, SL3, SL5) were considered as derma surrogates. SL V95%, V97%, V98%, V100%, V102%, V105% and V107% of the prescribed PTV dose were extracted for CT15/CTdef and compared (considering patients with skin dose > 95%). For comparison, doses were calculated directly on the calibrated MVCT and analyzed in the same way.ResultsDifferences between SL2/SL3/SL5 V95%-V107% in CT15/CTdef were very small: for eight of nine patients the difference between the considered SL2 Vd% computed on CTdef and CT15 was less than 1.4 cm3 for all d%. A larger value was found when using MVCT for skin dose calculation (4.8 cm3 for SL2), although CTdef body contour matched CT15 body with accuracy similar to that of MV15.ConclusionsDeforming the planning CT-to-MVCT was shown to be accurate considering external body contours and skin DVHs. The method was able to accurately identify superficial overdosing.
| S-EPMC7807680 | biostudies-literature
Project description:Quantification of myocardial T1 relaxation has potential value in the diagnosis of both ischemic and nonischemic cardiomyopathies. Image acquisition using the modified Look-Locker inversion recovery technique is clinically feasible for T1 mapping. However, respiratory motion limits its applicability and degrades the accuracy of T1 estimation. The robust registration of acquired inversion recovery images is particularly challenging due to the large changes in image contrast, especially for those images acquired near the signal null point of the inversion recovery and other inversion times for which there is little tissue contrast. In this article, we propose a novel motion correction algorithm. This approach is based on estimating synthetic images presenting contrast changes similar to the acquired images. The estimation of synthetic images is formulated as a variational energy minimization problem. Validation on a consecutive patient data cohort shows that this strategy can perform robust nonrigid registration to align inversion recovery images experiencing significant motion and lead to suppression of motion induced artifacts in the T1 map.
| S-EPMC4158317 | biostudies-literature
Project description:ObjectivesRigid image registration (RIR) and deformable image registration (DIR) are widely used in radiotherapy. This project aims to capture current international approaches to image registration.MethodsA survey was designed to identify variations in use, resources, implementation, and decision-making criteria for clinical image registration. This was distributed to radiotherapy centers internationally in 2018.ResultsThere were 57 responses internationally, from the Americas (46%), Australia/New Zealand (32%), Europe (12%), and Asia (10%). Rigid image registration and DIR were used clinically for computed tomography (CT)-CT registration (96% and 51%, respectively), followed by CT-PET (81% and 47%), CT-CBCT (84% and 19%), CT-MR (93% and 19%), MR-MR (49% and 5%), and CT-US (9% and 0%). Respondent centers performed DIR using dedicated software (75%) and treatment planning systems (29%), with 84% having some form of DIR software. Centers have clinically implemented DIR for atlas-based segmentation (47%), multi-modality treatment planning (65%), and dose deformation (63%). The clinical use of DIR for multi-modality treatment planning and accounting for retreatments was considered to have the highest benefit-to-risk ratio (69% and 67%, respectively).ConclusionsThis survey data provides useful insights on where, when, and how image registration has been implemented in radiotherapy centers around the world. DIR is mainly in clinical use for CT-CT (51%) and CT-PET (47%) for the head and neck (43-57% over all use cases) region. The highest benefit-risk ratio for clinical use of DIR was for multi-modality treatment planning and accounting for retreatments, which also had higher clinical use than for adaptive radiotherapy and atlas-based segmentation.
| S-EPMC7075391 | biostudies-literature
Project description:We adapted the deformable image registration (DIR) technique to accurately calculate the cumulative intracavitary brachytherapy (ICBT) and external beam radiotherapy (EBRT) rectal dose for treating uterine cervical cancer. A total of 14 patients with primary cervical cancer radically treated with ICRT and EBRT were analysed using the Velocity AI(TM) software. Computed tomography (CT) images were registered, and EBRT and ICBT dose distributions were determined. Cumulative D2cm (3), D1cm (3) and D0.1cm (3) were calculated by simple addition of fractional values or by DIR. The accuracy of DIR was evaluated by means of a virtual phantom mimicking the rectum. The dice similarity coefficient (DSC) was calculated to evaluate rectal contour concordance between CT images before and after DIR. Virtual phantom analysis revealed that the average difference between the DIR-based phantom Dmean and the simple phantom Dmean was 1.9 ± 2.5 Gy (EQD2), and the DIR method included an uncertainty of ∼8.0%. The mean DSC between reference CT and CT was significantly improved after DIR (EBRT: 0.43 vs 0.85, P < 0.005; ICBT: 0.60 vs 0.87, P < 0.005). The average simple rectal D2cm (3), D1cm (3) and D0.1cm (3) values were 77.6, 81.6 and 91.1 Gy (EQD2), respectively; the DIR-based values were 76.2, 79.5 and 87.6 Gy, respectively. The simple addition values were overestimated, on average, by 3.1, 3.7 and 5.5 Gy, respectively, relative to the DIR-based values. In conclusion, the difference between the simple rectal dose-volume histogram (DVH) parameter addition and DIR-based cumulative rectal doses increased with decreasing DVH parameters.
| S-EPMC4426921 | biostudies-literature
Project description:Purpose. Real-time three-dimensional (3D) magnetic resonance (MR) imaging is challenging because of slow MR signal acquisition, leading to highly under-sampled k-space data. Here, we proposed a deep learning-based, k-space-driven deformable registration network (KS-RegNet) for real-time 3D MR imaging. By incorporating prior information, KS-RegNet performs a deformable image registration between a fully-sampled prior image and on-board images acquired from highly-under-sampled k-space data, to generate high-quality on-board images for real-time motion tracking.Methods. KS-RegNet is an end-to-end, unsupervised network consisting of an input data generation block, a subsequent U-Net core block, and following operations to compute data fidelity and regularization losses. The input data involved a fully-sampled, complex-valued prior image, and the k-space data of an on-board, real-time MR image (MRI). From the k-space data, under-sampled real-time MRI was reconstructed by the data generation block to input into the U-Net core. In addition, to train the U-Net core to learn the under-sampling artifacts, the k-space data of the prior image was intentionally under-sampled using the same readout trajectory as the real-time MRI, and reconstructed to serve an additional input. The U-Net core predicted a deformation vector field that deforms the prior MRI to on-board real-time MRI. To avoid adverse effects of quantifying image similarity on the artifacts-ridden images, the data fidelity loss of deformation was evaluated directly in k-space.Results. Compared with Elastix and other deep learning network architectures, KS-RegNet demonstrated better and more stable performance. The average (±s.d.) DICE coefficients of KS-RegNet on a cardiac dataset for the 5- , 9- , and 13-spoke k-space acquisitions were 0.884 ± 0.025, 0.889 ± 0.024, and 0.894 ± 0.022, respectively; and the corresponding average (±s.d.) center-of-mass errors (COMEs) were 1.21 ± 1.09, 1.29 ± 1.22, and 1.01 ± 0.86 mm, respectively. KS-RegNet also provided the best performance on an abdominal dataset.Conclusion. KS-RegNet allows real-time MRI generation with sub-second latency. It enables potential real-time MR-guided soft tissue tracking, tumor localization, and radiotherapy plan adaptation.
| S-EPMC9309029 | biostudies-literature
Project description:To present a new approach to the problem of estimating errors in deformable image registration (DIR) applied to sequential phases of a 4DCT data set.A set of displacement vector fields (DVFs) are made by registering a sequence of 4DCT phases. The DVFs are assumed to display anatomical movement, with the addition of errors due to the imaging and registration processes. The positions of physical landmarks in each CT phase are measured as ground truth for the physical movement in the DVF. Principal component analysis of the DVFs and the landmarks is used to identify and separate the eigenmodes of physical movement from the error eigenmodes. By subtracting the physical modes from the principal components of the DVFs, the registration errors are exposed and reconstructed as DIR error maps. The method is demonstrated via a simple numerical model of 4DCT DVFs that combines breathing movement with simulated maps of spatially correlated DIR errors.The principal components of the simulated DVFs were observed to share the basic properties of principal components for actual 4DCT data. The simulated error maps were accurately recovered by the estimation method.Deformable image registration errors can have complex spatial distributions. Consequently, point-by-point landmark validation can give unrepresentative results that do not accurately reflect the registration uncertainties away from the landmarks. The authors are developing a method for mapping the complete spatial distribution of DIR errors using only a small number of ground truth validation landmarks.
| S-EPMC2973991 | biostudies-other