Image registration with auto‐mapped control volumes

Purpose: Image registration is important for determining correlations of tumor phenotypes to assess and to modify biologically‐guided therapies. Such correlations may vary significantly with different registration algorithms. The sensitivity of phenotype correlations to rigid versus deformable registrations was investigated. Methods: PET/CT images often canine patients with sinonasal cancer were acquired using [F‐18]FDG, [F‐ 18]FLT, and [Cu‐61]Cu‐ATSM prior to and 2–3 fractions into radiotherapy. Post‐treatment FDG‐PET/CT images were acquired 3 months after therapy. CTimages were registered to the planning CT using rigid and fast‐free‐form deformable registrations. The resulting transformations/deformation fields were applied to corresponding PET images. Correlation coefficients between FDG, FLT, Cu‐ATSM were calculated over the GTV at different imaging timepoints (pre:pre, pre:mid, and pre:post treatment). Paired t‐test and the relative differences of Pearson's R were used to investigate the sensitivity of the phenotype correlations to rigid and deformable registrations. Results: The difference between rigid and deformable registrations for pre:pre (Diff=2%, p>0.05) and pre:mid (Diff=−6%, p>0.05) phenotype correlations was insignificant. However, pre:pre phenotype correlations were observed to be very sensitive in dogs with osteoscarcinoma (Diff= 46%) or small tumors (Diff=−20%) due to errors in bony deformations and partial volume effects. Despite not reaching statistical significant, the relative difference in pre:post [18F]FDG correlation of more than −50% indicated that the correlation is very sensitive to registration algorithms. Conclusions: The study demonstrated that canine sinonasal tumors do not deform severely in the early treatment, while substantial variation between the registration algorithms was observed in pre:post phenotype correlation. Therefore, rigid registration is sufficient for determining the phenotype correlations in early treatment assessment. Deformable registration should be considered for correlations with the post‐ treatment imaging data. Future works include repeating the study on human patients and using different deformable registration algorithms to fully investigate the sensitivity of phenotype correlations.

Landmark-guided deformable image registration for accurate cumulative dose evaluation in lung reirradiation.

Purpose: To enhance the speed and accuracy of certain treatment plan in radiation therapy, a real‐time dose calculation strategy is performed based on Fast Fourier Transformation (FFT) and CT image registration. For this purpose, different registration methods are achieved by using Insight Segmentation and Registration Toolkit (ITK) in MATLAB. Method and materials: Our group developed an efficient method for kernel calculation for pencil beam convolution‐superposition based on FFT. In this paper, different image registration methods are developed in MATLAB by using ITK, such as rigid 3D, similarity 3D, Demons deformation and BSpline based Free Form. As ITK is written and used in a C++ template, smart pointer and generic structure, an open source wrapper MATITK is modified to facilitate the use of its image processing capabilities while working in the high‐level environment of MATLAB. The image registration methods are demonstrated on head and neck (H&N) CT image sets of 6 patients. The results of evaluation and visualization for the registration are presented. Results and discussion: Transformation similarity and computation complexity as evaluation criteria are compared between rigid and deformable registration methods. Judging from the mutual information histogram and mean square metric, the deformable registration will get more improvement on similarity than the rigid registration. Checkerboard composites of the reference and registered images are displayed. The computational time of deformable registration are 10∼20 times longer with the whole set of images because of the pre‐processing, complicated transformation matrix and more parameters. A similarity3D registration method is adopted for the image registration of H&N radiation therapy to trade off between registration effect and the time consumption. Conclusion: The image registration can greatly contribute to the automatic contour adjustment and dose deformation for adaptive radiation therapy. A GUI program will be designed for the customized deformation region to speed up deformable registration.

PurposeProton CT (pCT) has the ability to reduce inherent uncertainties in proton treatment by directly measuring the relative proton stopping power with respect to water, thereby avoiding the uncertain conversion of X‐ray CT Hounsfield unit to relative stopping power and the deleterious effect of X‐ ray CT artifacts. The purpose of this work was to further evaluate the potential of pCT for pretreatment positioning using experimental pCT data of a head phantom.MethodsThe performance of a 3D image registration algorithm was tested with pCT reconstructions of a pediatric head phantom. A planning pCT simulation scan of the phantom was obtained with 200 MeV protons and reconstructed with a 3D filtered back projection (FBP) algorithm followed by iterative reconstruction and a representative pretreatment pCT scan was reconstructed with FBP only to save reconstruction time. The pretreatment pCT scan was rigidly transformed by prescribing random errors with six degrees of freedom or deformed by the deformation field derived from a head and neck cancer patient to the pretreatment pCT reconstruction, respectively. After applying the rigid or deformable image registration algorithm to retrieve the original pCT image before transformation, the accuracy of the registration was assessed. To simulate very low‐dose imaging for patient setup, the proton CT images were reconstructed with 100%, 50%, 25%, and 12.5% of the total number of histories of the original planning pCT simulation scan, respectively.ResultsThe residual errors in image registration were lower than 1 mm and 1° of magnitude regardless of the anatomic directions and imaging dose. The mean residual errors ranges found for rigid image registration were from −0.29 ± 0.09 to 0.51 ± 0.50 mm for translations and from −0.05 ± 0.13 to 0.08 ± 0.08 degrees for rotations. The percentages of sub‐millimetric errors found, for deformable image registration, were between 63.5% and 100%.ConclusionThis experimental head phantom study demonstrated the potential of low‐dose pCT imaging for 3D image registration. Further work is needed to confirm the value pCT for pretreatment image‐guided proton therapy.

Background[18F]fluoro-2-deoxy-D-glucose ([18F]FDG) positron emission tomography (PET) is a valuable tool for monitoring response to therapy in oncology. In longitudinal studies, however, patients are not scanned in exactly the same position. Rigid and non-rigid image registration can be applied in order to reuse baseline volumes of interest (VOI) on consecutive studies of the same patient. The purpose of this study was to investigate the impact of various image registration strategies on standardized uptake value (SUV) and metabolic volume test-retest variability (TRT).MethodsTest-retest whole-body [18F]FDG PET/CT scans were collected retrospectively for 11 subjects with advanced gastrointestinal malignancies (colorectal carcinoma). Rigid and non-rigid image registration techniques with various degrees of locality were applied to PET, CT, and non-attenuation corrected PET (NAC) data. VOI were drawn independently on both test and retest scans. VOI drawn on test scans were projected onto retest scans and the overlap between projected VOI and manually drawn retest VOI was quantified using the Dice similarity coefficient (DSC). In addition, absolute (unsigned) differences in TRT of SUVmax, SUVmean, metabolic volume and total lesion glycolysis (TLG) were calculated in on one hand the test VOI and on the other hand the retest VOI and projected VOI. Reference values were obtained by delineating VOIs on both scans separately.ResultsNon-rigid PET registration showed the best performance (median DSC: 0.82, other methods: 0.71-0.81). Compared with the reference, none of the registration types showed significant absolute differences in TRT of SUVmax, SUVmean and TLG (p > 0.05). Only for absolute TRT of metabolic volume, significant lower values (p < 0.05) were observed for all registration strategies when compared to delineating VOIs separately, except for non-rigid PET registrations (p = 0.1). Non-rigid PET registration provided good volume TRT (7.7%) that was smaller than the reference (16%).ConclusionIn particular, non-rigid PET image registration showed good performance similar to delineating VOI on both scans separately, and with smaller TRT in metabolic volume estimates.

Purpose: The contour‐based evaluation is crucial in the radiotherapy and one popular parameter is the dice similarity coefficient (DSC). The DSC alone is insufficient in some situation and additional evaluation parameters are required. The purpose of this study is to create a minimum point distance histogram (mPDH) for contour‐based deformable image registration evaluation and to investigate the clinical dosimetric endpoints related to the mPDH in organs at risk for gastric patients with 4DCT images. Methods: The mPDH was created and tested in 4DCT images. The 0% phase (P0) and the 50% phase (P5) image data sets from 4DCT of 5 gastric cancer patients with contours delineated by a radiation oncologist were transferred to the VelocityVI image registration package. The contours on the P5 were rigidly transferred (rigid registration) and warped (deformable registration) to the P0. All contours were export to a homemade Matlab program for calculating the mPDH. The mPDHs were obtained for the rigid‐manual (RM) and the deformed‐manual (DM) contours. Furthermore, the original treatment plan was applied to the P0 for dose calculation and the dosimetry‐based investigation related to the mPDH was performed. Results: The mPDH provides a useful data for quantifying the agreement of the contours. The mean DI95%(the distance includes more than 95% of the points) and P3mm (the percent of points within 3mm distance) from mPDH show significant difference between the DM and RM (p&lt;0.05). For dosimetric evaluation, there is no dose check point has difference larger than 3% if the DI95% is within 4mm. Conclusion: A new informative image registration evaluation tool is created. The mPDH provides a useful data for quantifying the agreement of the contours. The clinical validation of mPDH in the gastric cancer shows the feasibility of apply this tool in the radiotherapy for evaluation the clinical accuracy of deformable registration.

To improve the effectiveness of dose distributions in radiotherapy planning and treatment, we investigated a robust image registration algorithm based on control volumes. It auto-mapps control volumes into Thin Plate Spline deformable transformation. The control volumes are introduced to increase the accuracy for the deformable registration. We also developed a bi-directional mapping method to choose the effective control volumes, which furthermore increase the registration accuracy. The clinical images are simulated using our two-step image registration algorithm. The simulation results indicate that the registration algorithm is robust and universal, even in great deformation cases. The algorithm provides a more convenient and robust resolution as compared to manual landmark based methods. The proposed method will help towards realizing the goal of automatic image registration in radiation therapy.

Conventional computed tomography-magnetic resonance imaging (CT-MRI) fusion for head and neck radiotherapy is often limited by registration uncertainty from inconsistent positioning and immobilization between diagnostic MRI and CT simulation. This study evaluates the practicality of using MRI positioning plates for head and neck tumors through image registration. A total of 35 patients with head and neck tumors were retrospectively included. Two sets of MRI data were obtained, with and without the positioning plate. These scans were fused with simulated CT images using either rigid registration (RIR) or deformable registration, generating four image combinations: CT/MRI positioning plate_RIR, CT/MRI positioning plate_DIR, CT/MRI_RIR, and CT/MRI_DIR (referred to as SETS1-4). Gross tumor volume (GTV) and organs at risk (OARs) were delineated on each image set. GTVs, OARs, and dose distributions from SET1 were used as reference values, and the overlap of GTV with OAR and dose variations were compared with SETS2-4. Image registration accuracy was assessed using geometric evaluation metrics, including the dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), Hausdorff distance (HD), and mean distance to agreement (MDA). Compared with the reference registration method, all registration methods for GTVs and most OARs showed statistically significant differences in DSC, JSC, HD, and MDA (p&lt;0.05), except for the brainstem. Notably, compared with MRI images without the positioning plate, the GTV and OAR volumes in SETS1 and SETS2 demonstrated high three-dimensional overlap (DSC &gt; 0.7) and close margin agreement (MDA &lt; 2 mm). For head and neck tumors, MRI images obtained with the positioning plate in the treatment position showed substantial geometric similarity to simulated CT scans through RIR. This similarity enables the use of MRI for radiotherapy target delineation, providing a significant advantage for clinical practice in hospitals without MRI simulators.

Deformable Registration between Pre-Operative PET-CT and Post-Operative Simulation CT Images Aiming to Improve the Accuracy of the Tumor Bed Definition.

Deformable image registration is a basic image processing task, especially widely used in medical image processing and analysis. Different from rigid registration, its purpose is to find the optimal nonlinear transformation between two images and establish corresponding relationship, so as to achieve image consistency. In recent years, deformable registration methods based on deep learning have been studied a lot. Compared with traditional methods, they show great advantages in registration performance. This paper proposes an attention-based residual neural network for deformable image registration, which utilizes the U-Net encoder-decoder structure to design a convolutional neural network to predict the deformation field, and uses the residual module and attention mechanism enhances the ability of the model to extract features, and finally uses the spatial transformation function to obtain the registered image, and the entire network is trained in an unsupervised manner. We conducted experiments on the MNIST dataset and 2D brain magnetic resonance images (MRI) respectively. The experimental results show that the deformable registration network proposed in this paper has good performance and shows good results in registration accuracy.

In Additive Manufacturing (AM), precise rigid three-dimensional (3D) image registration between X-ray Computed Tomography (XCT) scans and Computer-Aided Design (CAD) models is an important step for the quantification of distortions in produced parts. Given the absence of standardized benchmarks for image registration in AM, we introduce a gold standard for 3D image registration, using a reference base plate beneath the build structure. This gold standard is used to quantify the accuracy of rigid registration, with a proof of concept demonstrated in PBF-LB/M. In this study, we conduct a comparative analysis of various rigid 3D registration methods useful for quality assurance of PBF-LB/M parts including feature-based, intensity-based, and point cloud-based approaches. The performance of each registration method is evaluated using measures of alignment accuracy based on the gold standard and computational efficiency. Our results indicate significant differences in the efficacy of these methods, with point cloud based Coherent Point Drift (CPD) showing superior performance in both alignment and computational efficiency. The rigidly registered 3D volumes are used to estimate the deformation field of the printed parts relative to the nominal CAD design using Digital Volume Correlation (DVC). The quality of the estimated deformation field is assessed using the Dice score metric. This study provides insights into methods for enhancing the precision and reliability of AM process.

Purpose. Mobile C-arms capable of 2D fluoroscopy and 3D cone-beam CT (CBCT) are finding application in guidance of transbronchial lung biopsy, but unresolved deformable motion presents challenges to accurate target localization and guidance. We report the initial implementation of a method to resolve deformations via locally rigid / globally deformable 3D-2D registration for motion-compensated overlay of planning data in fluoroscopically-guided pulmonary interventions. Methods. The algorithm proceeds in 3 steps: (1) initialization by 3D-2D rigid registration of CBCT to fluoroscopy (driven by bone gradients); (2) local rigid 3D-2D registration of lung-thresholded CBCT to fluoroscopy within a region of interest (ROI) about each target location; and (3) aggregation of local rigid registrations to estimate global deformation. Several objective functions and optimizers were evaluated for soft-tissue target registration. Phantom studies were performed to determine operating parameters and assess performance with simulated lung deformation. Results. Soft-tissue thresholding and contrast enhancement improved target registration error (TRE) from 10.3 mm for conventional 3D-2D registration (driven primarily by rib gradients) to 3.8 mm using locally rigid 3D-2D registration in regions of interest about each target. The soft-tissue gradient orientation (GO) objective function was found to be superior to alternative similarity measures by de-emphasizing gradient magnitude (in favor of gradient orientation), permitting the algorithm to be better driven by soft-tissue edges. Conclusions. Registration driven by soft-tissue targets is achievable via a novel processing framework to de-emphasize non-target gradients. The proposed method could improve the accuracy of guidance in pulmonary interventions by updating target overlay in fluoroscopy.

Image Guided, Motion-free Patient Body Setup using 3D Volumetric Image Registration of Classified Stable Bony Landmarks

Background and purpose3D image registration is now common in many medical domains. Multimodal registration implies the use of different imaging modalities, which results in lower accuracy compared to monomodal registration. The aim of this study was to propose a novel approach for deformable image registration (DIR) that incorporates an unsupervised deep learning (DL)-based generation step. The objective was to reduce the challenge of multimodal registration to monomodal registration. Material and methodsTwo datasets from prostate radiotherapy patients were used to evaluate the proposed method. The first dataset consisted of Computed Tomography (CT)/ Cone Beam Computed Tomography (CBCT) pairs from 23 patients using different CBCT devices. The second dataset included Magnetic Resonance Imaging (MRI)/CT pairs from two different care centers, utilizing different MRI devices (0.35 T MRIdian MR-Linac, 1.5 T GE lightspeed MRI). Following a preprocessing step essential for ensuring DL synthesis accuracy and standardizing the database, synthetic CTs (sCTreg) were generated using an unsupervised conditional Generative Adversarial Network (cGAN). The generated sCTs from CBCT or MRI were then utilized for deformable registration with CT scans. This registration method was compared to three standard methods: rigid registration, Elastix registration based on BSplines, and VoxelMorph-based registration (applied exclusively to CBCT/CT). The endpoints of comparison were the dice coefficients calculated between delineated structures for both datasets. ResultsFor both datasets, intermediary sCT generation provided the highest dice coefficients. Dices reached 0.85, 0.85 and 0.75 for the prostate, bladder and rectum for the dataset 1 and 0.90, 0.95 and 0.87 respectively for the dataset 2. When the sCT were not used, dices reached 0.66, 0.78, 0.66 for the dataset 1 and 0.93, 0.87 and 0.84 for the dataset 2. Furthermore, the evaluation of the impact of registration on sCT generation showed that lower Mean Absolute Errors were obtained when the registration was conducted with a sCT. ConclusionsUsing unsupervised deep learning to synthesize intermediate sCT has led to improved registration accuracy in radiotherapy applications employing two distinct imaging modalities.

To commission and validate commercial deformable image registration (DIR) systems (SmartAdapt® and Velocity™) using task group 132 (TG-132) digital phantom datasets. Additionally, the study compares and verifies the DIR algorithms of the two systems. TG-132 digital phantoms were obtained from the American Association of Physicists in Medicine website and imported into SmartAdapt® and Velocity™ systems for commissioning and validation. The registration results were compared with known shifts using rigid registrations and deformable registrations. Virtual head and neck phantoms obtained online (DIR Evaluation Project) and some selected clinical data sets from the department were imported into the two DIR systems. For both of these datasets, DIR was carried out between the source and target images, and the contours were then propagated from the source to the target image data set. The dice similarity coefficient (DSC), mean distance to agreement (MDA), and Jacobian determinant measures were utilised to evaluate the registration results. The recommended criteria for commissioning and validation of DIR system from TG-132 was error <0.5*voxel dimension (vd). Translation only registration: Both systems met TG-132 recommendations except computed tomography (CT)-positron emission tomography registration in both systems (Velocity ~1.1*vd, SmartAdapt ~1.6*vd). Translational and rotational registration: Both systems failed the criteria for all modalities (For velocity, error ranged from 0.6*vd [CT-CT registration] to 3.4*vd [CT-cone-beam CT (CBCT) registration]. For SmartAdapt® the range was 0.6*vd [CT-CBCT] to 3.6*vd [CT-CT]). Mean ± standard deviation for DSC, MDA and Jacobian metrics were used to compare the DIR results between SmartAdapt® and Velocity™. The DIR algorithms of SmartAdapt® and Velocity™ were commissioned and their deformation results were compared. Both systems can be used for clinical purpose. While there were only minimal differences between the two systems, Velocity™ provided lower values for parotids, bladder, rectum, and prostate (soft tissue) compared to SmartAdapt. However, for mandible, spinal cord, and femoral heads (rigid structures), both systems showed nearly identical results.