macJNet: weakly-supervised multimodal image deformable registration using joint learning framework and multi-sampling cascaded MIND.

Deformable multimodal image registration plays a key role in medical image analysis. It remains a challenge to find accurate dense correspondences between multimodal images due to the significant intensity distortion and the large deformation. macJNet is proposed to align the multimodal medical images, which is a weakly-supervised multimodal image deformable registration method using a joint learning framework and multi-sampling cascaded modality independent neighborhood descriptor (macMIND). The joint learning framework consists of a multimodal image registration network and two segmentation networks. The proposed macMIND is a modality-independent image structure descriptor to provide dense correspondence for registration, which incorporates multi-orientation and multi-scale sampling patterns to build self-similarity context. It greatly enhances the representation ability of cross-modal features in the registration network. The semi-supervised segmentation networks generate anatomical labels to provide semantics correspondence for registration, and the registration network helps to improve the performance of multimodal image segmentation by providing the consistency of anatomical labels. 3D CT-MR liver image dataset with 118 samples is built for evaluation, and comprehensive experiments have been conducted to demonstrate that macJNet achieves superior performance over state-of-the-art multi-modality medical image registration methods.

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

PURPOSE: 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.

Cascading Affine and B-spline Registration Method for Large Deformation Registration of Lung X-rays.

Accurate registration of lung X-rays is an important task in medical image analysis. However, the conventional methods usually cost a lot in running time, and the existing deep learning methods are hard to deal with the large deformation caused by respiratory and cardiac motion. In this paper, we attempt to use deep learning methods to deal with large deformation and enable it to achieve the accuracy of conventional methods. We proposed the cascading affine and B-spline network (CABN), which consists of convolutional cross-stitch affine block (CCAB) and B-splines U-net-like block (BUB) for large lung motion. CCAB makes use of the convolutional cross-stitch model to learn global features among images. And BUB adopts the idea of cubic B-splines which is suitable for large deformation. We separately demonstrated CCAB, BUB, and CABN on two chest X-ray datasets. The experimental results indicate that our methods are highly competitive both in accuracy and runtime when compared to both other deep learning methods and iterative conventional approaches. Moreover, CCAB also can be used for the preprocessing of non-rigid registration methods, replacing affine in conventional methods.

Varian ethos online adaptive radiotherapy for prostate cancer: Early results of contouring accuracy, treatment plan quality, and treatment time.

The Varian Ethos system allows for online adaptive treatments through the utilization of artificial intelligence (AI) and deformable image registration which automates large parts of the anatomical contouring and plan optimization process. In this study, treatments of intact prostate and prostate bed, with and without nodes, were simulated for 182 online adaptive fractions, and then a further 184 clinical fractions were delivered on the Ethos system. Frequency and magnitude of contour edits were recorded, as well as a range of plan quality metrics. From the fractions analyzed, 11% of AI generated contours, known as influencer contours, required no change, and 81% required minor edits in any given fraction. The frequency of target and noninfluencer organs at risk (OAR) contour editing varied substantially between different targets and noninfluencer OARs, although across all targets 72% of cases required no edits. The adaptive plan was the preference in 95% of fractions. The adaptive plan met more goals than the scheduled plan in 78% of fractions, while in 15% of fractions the number of goals met was the same. The online adaptive recontouring and replanning process was carried out in 19 min on average. Significant improvements in dosimetry are possible with the Ethos online adaptive system in prostate radiotherapy.

Onboard cone-beam CT-based replan evaluation for head and neck proton therapy.

PURPOSE: Quality assurance computed tomography (QACT) is the current clinical practice in proton therapy to evaluate the needs for replan. QACT could falsely indicate replan because of setup issues that would be solved on the treatment machine. Deforming the treatment planning CT (TPCT) to the pretreatment CBCT may eliminate this issue. We investigated the performance of replan evaluation based on deformed TPCT (TPCTdir) for proton head and neck (H&N) therapy. METHODS AND MATERIALS: Twenty-eight H&N datasets along with pretreatment CBCT and QACT were used to validate the method. The changes in body volume were analyzed between the no-replan and replan groups. The dose on the TPCTdir, the deformed QACT (QACTdir), and the QACT were calculated by applying the clinical plans to these image sets. Dosimetric parameters' changes, including ΔD95, ΔDmean, and ΔD1 for the clinical target volumes (CTVs) were calculated. Receiver operating characteristic curves for replan evaluation based on ΔD95 on QACT and TPCTdir were calculated, using ΔD95 on QACTdir as the reference. A threshold for replan based on ΔD95 on TPCTdir is proposed. The specificities for the proposed method were calculated. RESULTS: The changes in the body contour were 95.8 ± 83.8 cc versus 305.0 ± 235.0 cc (p < 0.01) for the no-replan and replan groups, respectively. The ΔD95, ΔDmean, and ΔD1 are all comparable for all the evaluations. The differences between TPCTdir and QACTdir evaluations were 0.30% ± 0.86%, 0.00 ± 0.22 Gy, and -0.17 ± 0.61 Gy for CTV ΔD95, ΔDmean, and ΔD1, respectively. The corresponding differences between the QACT and QACTdir were 0.12% ± 1.1%, 0.02 ± 0.32 Gy, and -0.01 ± 0.71 Gy. CTV ΔD95 > 2.6% in TPCTdir was chosen as the threshold to trigger QACT/replan. The corresponding specificity was 94% and 98% for the clinical practice and the proposed method, respectively. CONCLUSIONS: The replan evaluation based on TPCTdir provides better specificity than that based on the QACT.

Spatial correspondence of spinal cord white matter tracts using diffusion tensor imaging, fibre tractography, and atlas-based segmentation.

PURPOSE: Neuroimaging provides great utility in complex spinal surgeries, particularly when anatomical geometry is distorted by pathology (tumour, degeneration, etc.). Spinal cord MRI diffusion tractography can be used to generate streamlines; however, it is unclear how well they correspond with white matter tract locations along the cord microstructure. The goal of this work was to evaluate the spatial correspondence of DTI tractography with anatomical MRI in healthy anatomy (where anatomical locations can be well defined in T1-weighted images). METHODS: Ten healthy volunteers were scanned on a 3T system. T1-weighted (1 × 1 × 1 mm) and diffusion-weighted images (EPI readout, 2 × 2 × 2 mm, 30 gradient directions) were acquired and subsequently registered (Spinal Cord Toolbox (SCT)). Atlas-based (SCT) anatomic label maps of the left and right lateral corticospinal tracts were identified for each vertebral region (C2-C6) from T1 images. Tractography streamlines were generated with a customized approach, enabling seeding of specific spinal tract regions corresponding to individual vertebral levels. Spatial correspondence of generated fibre streamlines with anatomic tract segmentations was compared in unseeded regions of interest (ROIs). RESULTS: Spatial correspondence of the lateral corticospinal tract streamlines was good over a single vertebral ROI (Dice's similarity coefficient (DSC) = 0.75 ± 0.08, Hausdorff distance = 1.08 ± 0.17 mm). Over larger ROI, fair agreement between tractography and anatomical labels was achieved (two levels: DSC = 0.67 ± 0.13, three levels: DSC = 0.52 ± 0.19). CONCLUSION: DTI tractography produced good spatial correspondence with anatomic white matter tracts, superior to the agreement between multiple manual tract segmentations (DSC ~ 0.5). This supports further development of spinal cord tractography for computer-assisted neurosurgery.

Estimating the accumulative dose uncertainty for intracavitary and interstitial brachytherapy.

BACKGROUND: Image-guided adaptive brachytherapy shows the ability to deliver high doses to tumors while sparing normal tissues. However, interfraction dose delivery introduces uncertainties to high dose estimation, which relates to normal tissue toxicity. The purpose of this study was to investigate the high-dose regions of two applicator approaches in brachytherapy. METHOD: For 32 cervical cancer patients, the CT images from each fraction were wrapped to a reference image, and the displacement vector field (DVF) was calculated with a hybrid intensity-based deformable registration algorithm. The fractional dose was then accumulated to calculate the position and the overlap of high dose (D2cc) during multiple fractions. RESULT: The overall Dice similarity coefficient (DSC) of the deformation algorithm for the bladder and the rectum was (0.97 and 0.91). No significant difference was observed between the two applicators. However, the location of the intracavitary brachytherapy (ICBT) high-dose region was relatively concentrated. The overlap volume of bladder and rectum D2cc was 0.42 and 0.71, respectively, which was higher than that of interstitial brachytherapy (ISBT) (0.26 and 0.31). The cumulative dose was overestimated in ISBT cases when using the GEC-recommended method. The ratio of bladder and rectum D2cc to the GEC method was 0.99 and 1, respectively, which was higher than that of the ISBT method (0.96 and 0.94). CONCLUSION: High-dose regions for brachytherapy based on different applicator types were different. The 3D-printed ICBT has better high-dose region consistency than freehand ISBT and hence is more predictable.

Validation of accuracy deformable image registration contour propagation using a benchmark virtual HN phantom dataset.

Virtual anatomic phantoms offer precise voxel mapping of the variation of anatomy with ground truth deformation vector fields (DVFs). Dice similarity coefficient (DSC) and mean distance to agreement (MDA) are the standard metrics for evaluating geometric contour congruence when testing deformable registration (DIR) algorithms. A HN virtual patient phantom data set was used for a kVCT-kVCT automatic propagation contour validation study employing the Accuray DIR algorithm. Furthermore, since TomoTherapy uses MVCT images of the relevant anatomy for adaptive monitoring, the kVCT image data set quality was transformed to an MVCT image data set quality to study intermodal kVCT-MVCT DIR accuracy. The results of the study indicate that the Accuray DIR algorithm can be expected to autopropagate HN contours adequately, on average, within tolerances recommended by TG-132 (DSC 0.8-0.9, MDA within voxel width). However, contours critical to dosimetric planning should always be visually proofed for accuracy. Using standard reconstruction MVCT image quality causes slightly less, but acceptable, agreement with ground truth contours.

Deformable registration of chest CT images using a 3D convolutional neural network based on unsupervised learning.

PURPOSE: The deformable registration of 3D chest computed tomography (CT) images is one of the most important tasks in the field of medical image registration. However, the nonlinear deformation and large-scale displacement of lung tissues caused by respiratory motion cause great challenges in the deformable registration of 3D lung CT images. MATERIALS AND METHODS: We proposed an end-to-end fast registration method based on unsupervised learning, optimized the classic U-Net, and added inception modules between skip connections. The inception module attempts to capture and merge information at different spatial scales to generate a high-precision dense displacement vector field. To solve the problem of voxel folding in flexible registration, we put the Jacobian regularization term into the loss function to directly penalize the singularity of the displacement field during training to ensure a smooth displacement vector field. In the stage of data preprocessing, we segmented the lung fields to eliminate the interference of irrelevant information in the network during training. The existing publicly available datasets cannot implement model training. To alleviate the problem of overfitting caused by limited data resources being available, we proposed a data augmentation method based on the 3D-TPS (3D thin plate spline) transform to expand the training data. RESULTS: Compared with the experimental results obtained by using the VoxelMorph deep learning method and registration packages, such as ANTs and Elastix, we achieved a competitive target registration error of 2.09 mm, an optimal Dice score of 0.987, and almost no folding voxels. Additionally, the proposed method was much faster than the traditional methods. CONCLUSIONS: In this study, we have shown that the proposed method was efficient in 3D chest image registration. The promising results demonstrated that our method showed strong robustness in the deformable registration of 3D chest CT images.

A preliminary investigation of re-evaluating the irradiation dose in hepatocellular carcinoma radiotherapy applying 4D CT and deformable registration.

PURPOSE: To investigate the effect of breathing motion on dose distribution for hepatocellular carcinoma (HCC) patients using four-dimensional (4D) CT and deformable registration. METHODS: Fifty HCC patients who were going to receive radiotherapy were enrolled in this study. All patients had been treated with transarterial chemoembolization beforehand. Three-dimensional (3D) and 4D CT scans in free breathing were acquired sequentially. Volumetric modulated arc therapy (VMAT) was planned on the 3D CT images and maximum intensity projection (MIP) images. Thus, the 3D dose (Dose-3D ) and MIP dose (Dose-MIP ) were obtained, respectively. Then, the Dose-3D and Dose-MIP were recalculated on 10 phases of 4D CT images, respectively, in which the end-inhale and end-exhale phase doses were defined as Dose-3D-EI , Dose-3D-EE , Dose-MIP-EI , and Dose-MIP-EE . The 4D dose (Dose-4D-3D and Dose-4D-MIP ) were obtained by deforming 10 phase doses to the end-exhale CT to accumulate. The dosimetric difference in Dose-3D , Dose-EI3D , Dose-EE3D , Dose-4D-3D , Dose-MIP , Dose-EIMIP , Dose-EEMIP , and Dose-4D-MIP were compared to evaluate the motion effect on dose delivery to the planning target volume (PTV) and normal liver. RESULTS: Compared with Dose-3D , PTV D99 in Dose-EI3D , Dose-EE3D and Dose-4D-3D decreased by an average of 6.02%, 1.32%, 2.43%, respectively (P < 0.05); while PTV D95 decreased by an average of 3.34%, 1.51%, 1.93%, respectively (P < 0.05). However, CI and HI of the PTV in Dose-3D was superior to the other three distributions (P < 0.05). There was no significant differences for the PTV between Dose-EI and Dose-EE , and between the two extreme phase doses and Dose-4D (P> 0.05). Negligible difference was observed for normal liver in all dose distributions (P> 0.05). CONCLUSIONS: Four-dimensional dose calculations potentially ensure target volume coverage when breathing motion may affect the dose distribution. Dose escalation can be considered to improve the local control of HCC on the basis of accurately predicting the probability of radiation-induced liver disease.

Performance of a deformable image registration algorithm for CT and cone beam CT using physical multi-density geometric and digital anatomic phantoms.

PURPOSE: To study the accuracy of deformable registration algorithm for CT and cone beam CT (CBCT) using a combination of physical and digital phantoms. MATERIALS AND METHODS: The physical phantoms consisted of objects over a range of electron densities, shape and sizes. The system was tested for simple and complex scenarios including performance in the presence of metallic artefacts. Clinically present deformations were simulated using a set of five geometric and anatomic virtual phantoms. RESULTS: The system could not account for large changes in size, shape and Hounsfield units. Deformations of low intensity structures and small objects were highly inaccurate, and errors were prominent for volume reduction scenario than volume growth. The presence of artefacts did alter the performance of the algorithm. Objects of low density and that close to artefacts were affected the most. Overall, deformations to CBCT were poor. In virtual phantoms, the system could not handle gas pockets and deformation errors in inverse direction were higher than that in forward direction. CONCLUSION: The algorithm was tested for several non-clinical and clinical scenarios. The performance was acceptable for realistic and clinically present deformations. However, it is necessary to tread cautiously for structures with small volumes and large reductions in volume.

Quantification of myocardial strain in patients with isolated left ventricular non-compaction and healthy subjects using deformable registration algorithm: comparison with feature tracking.

BACKGROUND: Systolic dysfunction of the left ventricle is frequently associated with isolated left ventricular non-compaction (iLVNC). Clinically, the ejection fraction (EF) is the primary index of cardiac function. However, changes of EF usually occur later in the disease course. Feature tracking (FT) and deformable registration algorithm (DRA) have become appealing techniques for myocardial strain assessment. METHODS: Thirty patients with iLVNC (36.7 ± 13.3 years old) and fifty healthy volunteers (42.3 ± 13.6 years old) underwent cardiovascular magnetic resonance (CMR) examination on a 1.5 T MR scanner. Strain values in the radial, circumferential, longitudinal directions were analyzed based on the short-axis and long-axis cine images using FT and DRA methods. The iLVNC patients were further divided based on the ejection fraction, into EF ≥ 50% group (n = 11) and EF < 50% group (n = 19). Receiver-operating-characteristic (ROC) analysis was performed to assess the diagnostic performance of the global strain values. Intraclass correlation coefficient (ICC) analysis was used to evaluate the intra- and inter-observer agreement. RESULTS: Global radial strain (GRS) was statistically lower in EF ≥ 50% group compared with control group [GRS (DRA)/% vs. controls: 34.6 ± 7.0 vs. 37.6 ± 7.2, P < 0.001; GRS (FT)/% vs. controls: 37.4 ± 13.2 vs. 56.9 ± 16.4, P < 0.01]. ROC analysis of global strain values derived from DRA and FT demonstrated high area under curve (range, 0.743-0.854). DRA showed excellent intra- and inter-observer agreement of global strain in both iLVNC patients (ICC: 0.995-0.999) and normal controls (ICC: 0.934-0.996). While for FT analysis, global radial strain of normal controls showed moderate intra-observer (ICC: 0.509) and poor inter-observer agreement (ICC: 0.394). CONCLUSIONS: In patients with iLVNC, DRA can be used to quantitatively analyze the strain of left ventricle, with global radial strain being an earlier marker of LV systolic dysfunction. DRA has better reproducibility in evaluating both the global and segmental strain.

End-to-end unsupervised cycle-consistent fully convolutional network for 3D pelvic CT-MR deformable registration.

OBJECTIVE: To improve the efficiency of computed tomography (CT)-magnetic resonance (MR) deformable image registration while ensuring the registration accuracy. METHODS: Two fully convolutional networks (FCNs) for generating spatial deformable grids were proposed using the Cycle-Consistent method to ensure the deformed image consistency with the reference image data. In all, 74 pelvic cases consisting of both MR and CT images were studied, among which 64 cases were used as training data and 10 cases as the testing data. All training data were standardized and normalized, following simple image preparation to remove the redundant air. Dice coefficients and average surface distance (ASD) were calculated for regions of interest (ROI) of CT-MR image pairs, before and after the registration. The performance of the proposed method (FCN with Cycle-Consistent) was compared with that of Elastix software, MIM software, and FCN without cycle-consistent. RESULTS: The results show that the proposed method achieved the best performance among the four registration methods tested in terms of registration accuracy and the method was more stable than others in general. In terms of average registration time, Elastix took 64 s, MIM software took 28 s, and the proposed method was found to be significantly faster, taking <0.1 s. CONCLUSION: The proposed method not only ensures the accuracy of deformable image registration but also greatly reduces the time required for image registration and improves the efficiency of the registration process. In addition, compared with other deep learning methods, the proposed method is completely unsupervised and end-to-end.

The Effect of Registration on Voxel-Wise Tofts Model Parameters and Uncertainties from DCE-MRI of Early-Stage Breast Cancer Patients Using 3DSlicer.

We quantitatively investigate the influence of image registration, using open-source software (3DSlicer), on kinetic analysis (Tofts model) of dynamic contrast enhanced MRI of early-stage breast cancer patients. We also show that registration computation time can be reduced by reducing the percent sampling (PS) of voxels used for estimation of the cost function. DCE-MRI breast images were acquired on a 3T-PET/MRI system in 13 patients with early-stage breast cancer who were scanned in a prone radiotherapy position. Images were registered using a BSpline transformation with a 2 cm isotropic grid at 100, 20, 5, 1, and 0.5PS (BRAINSFit in 3DSlicer). Signal enhancement curves were analyzed voxel-by-voxel using the Tofts kinetic model. Comparing unregistered with registered groups, we found a significant change in the 90th percentile of the voxel-wise distribution of Ktrans. We also found a significant reduction in the following: (1) in the standard error (uncertainty) of the parameter value estimation, (2) the number of voxel fits providing unphysical values for the extracellular-extravascular volume fraction (ve > 1), and (3) goodness of fit. We found no significant differences in the median of parameter value distributions (Ktrans, ve) between unregistered and registered images. Differences between parameters and uncertainties obtained using 100PS versus 20PS were small and statistically insignificant. As such, computation time can be reduced by a factor of 2, on average, by using 20PS while not affecting the kinetic fit. The methods outlined here are important for studies including a large number of post-contrast images or number of patient images.

Deformable registration and region-of-interest image reconstruction in sparse repeat CT scanning.

BACKGROUND: Repeat CT scanning is ubiquitous in many clinical situations, e.g. to follow disease progression, to evaluate treatment efficacy, and to monitor interventional CT procedures. However, it incurs in cumulative radiation to the patient which can be significantly reduced by using a region of interest (ROI) and the existing baseline scan. OBJECTIVE: To obtain a high-quality reconstruction of a ROI with a significantly reduced X-ray radiation dosage that accounts for deformations. METHODS: We present a new method for deformable registration and image reconstruction inside an ROI in repeat CT scans with a highly reduced X-ray radiation dose based on sparse scanning. Our method uses the existing baseline scan data, a user-defined ROI, and a new sparse repeat scan to compute a high-quality repeat scan ROI image with a significantly reduced radiation dose. Our method first performs rigid registration between the densely scanned baseline and the sparsely scanned repeat CT scans followed by deformable registration with a low-order parametric model, both in 3D Radon space and without reconstructing the repeat scan image. It then reconstructs the repeat scan ROI without computing the entire repeat scan image. RESULTS: Our experimental results on clinical lung and liver CT scans yield a mean × 14 computation speedup and a × 7.6-12.5 radiation dose reduction, with a minor image quality loss of 0.0157 in the NRMSE metric. CONCLUSION: Our method is considerably faster than existing methods, thereby enabling intraoperative online repeat scanning that it is accurate and accounts for position, deformation, and structure changes at a fraction of the radiation dose required by existing methods.

Noise reduction and motion elimination in low-dose 4D myocardial computed tomography perfusion (CTP): preliminary clinical evaluation of the ASTRA4D algorithm.

OBJECTIVES: To propose and evaluate a four-dimensional (4D) algorithm for joint motion elimination and spatiotemporal noise reduction in low-dose dynamic myocardial computed tomography perfusion (CTP). METHODS: Thirty patients with suspected or confirmed coronary artery disease were prospectively included and underwent dynamic contrast-enhanced 320-row CTP. A novel deformable image registration method based on the principal component analysis (PCA) of the ante hoc temporally smoothed voxel-wise time-attenuation curves (ASTRA4D) is presented. Quantitative (standard deviation, signal-to-noise ratio (SNR), temporal variation, volumetric deformation) and qualitative (motion, contrast, contour sharpness [1, poor; 5, excellent]) measures of CTP quality were assessed for the original and motion-compensated sequences (without and with temporal filtering, PCA/ASTRA4D). Following myocardial perfusion deficit detection by two readers, diagnostic accuracy was evaluated using magnetic resonance myocardial perfusion imaging (MR-MPI) as the reference standard in 15 patients. RESULTS: Registration using ASTRA4D was successful in all 30 patients and resulted in comparison with the benchmark PCA in significantly (p < 0.001) reduced noise over time (- 83%, 178.5 vs 29.9) and spatially (- 34%, 21.4 vs 14.1) as well as improved SNR (+ 47%, 3.6 vs 5.3) and subjective image quality (motion, contrast, contour sharpness [+ 1.0, + 1.0, + 0.5]). ASTRA4D had significantly improved per-segment sensitivity of 91% (58/64) and similar specificity of 96% (429/446) compared with PCA (52%, 33/64; 98%, 435/446; p = 0.011) in the visual detection of perfusion deficits. CONCLUSIONS: The ASTRA4D registration algorithm improved the spatiotemporal noise profile and CTP sequence image quality, resulting in significantly improved sensitivity of 4D CTP in the detection of myocardial ischemia. KEY POINTS: • ASTRA4D combines local temporal regression and deformable image registration. • Quantitative and qualitative measures of CTP quality are improved compared to PCA. • Improved spatiotemporal differentiation of ischemic regions leads to an excellent perfusion deficit concordance of ASTRA4D with MRI.

Registration methods in radiotherapy.

PURPOSE: The aim of this study is to present a short and comprehensive review of the methods of medical image registration, their conditions and applications in radiotherapy. A particular focus was placed on the methods of deformable image registration. METHODS: To structure and deepen the knowledge on medical image registration in radiotherapy, a medical literature analysis was made using the Google Scholar browser and the medical database of the PubMed library. RESULTS: Chronological review of image registration methods in radiotherapy based on 34 selected articles. A particular attention was given to show: (i) potential regions of the application of different methods of registration, (ii) mathematical basis of the deformable methods and (iii) the methods of quality control for the registration process. CONCLUSIONS: The primary aim of the medical image registration process is to connect the contents of images. What we want to achieve is a complementary or extended knowledge that can be used for more precise localisation of pathogenic lesions and continuous improvement of patient treatment. Therefore, the choice of imaging mode is dependent on the type of clinical study. It is impossible to visualise all anatomical details or functional changes using a single modality machine. Therefore, fusion of various modality images is of great clinical relevance. A natural problem in analysing the fusion of medical images is geographical errors related to displacement. The registered images are performed not at the same time and, very often, at different respiratory phases.

Improved segmental myocardial strain reproducibility using deformable registration algorithms compared with feature tracking cardiac MRI and speckle tracking echocardiography.

BACKGROUND: Segmental myocardial strain using feature tracking (FT) cardiac MRI is not acceptable due to poor reproducibility. PURPOSE: To assess the reproducibility of left ventricle (LV) segmental myocardial strain measured by deformation registration algorithm (DRA). STUDY TYPE: Prospective clinical trial. SUBJECTS: Sixteen healthy volunteers and 28 hypertrophic cardiomyopathy (HCM) patients. FIELD STRENGTH/SEQUENCE: Retrospective ECG gating cardiac MRI imaging was performed at 3.0T with a steady-state free precession (SSFP) sequence. ASSESSMENT: LV global and segmental myocardial strains were analyzed by DRA, FT, and speckle tracking echocardiography (STE) by two experienced observers and the reproducibility of global and segmental strains were compared. STATISTICAL TESTS: Reproducibility was tested by coefficient of variation (COV) and intraclass correlation coefficient (ICC). Receiver operator curves as well as comparison of areas under the curve (AUC) were analyzed. RESULTS: DRA showed the best observer agreement on segmental strain evaluated by ICC, LS (longitudinal strain): intraobserver variability range (0.98,1.00), interobserver variability range (0.83,0.92), CS (circumferential strain): intraobserver variability range (0.90,0.99), interobserver variability range (0.80,0.97), RS (radial strain): intraobserver variability range (0.84,0.99), interobserver variability range (0.85,0.99). Segmental LS, CS, and RS agreements evaluated by COV for FT and STE were poor. LV global myocardial strain of HCM was significantly lower than controls for all applied techniques, but global CS by DRA had better accuracy compared to FT or STE for distinguishing HCM from healthy subjects: AUC 0.880 (DRA) vs. 0.577 (FT) or 0.736 (STE), P < 0.05. DATA CONCLUSIONS: DRA is a reliable and robust analysis tool for segmental myocardial strain. Global CS by DRA allows discrimination between HCM and normal controls with better accuracy compared with FT and STE. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. MAGN. RESON. IMAGING 2018;48:404-414.

Quantification of global myocardial function by cine MRI deformable registration-based analysis: Comparison with MR feature tracking and speckle-tracking echocardiography.

OBJECTIVES: To evaluate deformable registration algorithms (DRA)-based quantification of cine steady-state free-precession (SSFP) for myocardial strain assessment in comparison with feature-tracking (FT) and speckle-tracking echocardiography (STE). METHODS: Data sets of 28 patients/10 volunteers, undergoing same-day 1.5T cardiac MRI and echocardiography were included. LV global longitudinal (GLS), circumferential (GCS) and radial (GRS) peak systolic strain were assessed on cine SSFP data using commercially available FT algorithms and prototype DRA-based algorithms. STE was applied as standard of reference for accuracy, precision and intra-/interobserver reproducibility testing. RESULTS: DRA showed narrower limits of agreement compared to STE for GLS (-4.0 [-0.9,-7.9]) and GCS (-5.1 [1.1,-11.2]) than FT (3.2 [11.2,-4.9]; 3.8 [13.9,-6.3], respectively). While both DRA and FT demonstrated significant differences to STE for GLS and GCS (all p<0.001), only DRA correlated significantly to STE for GLS (r=0.47; p=0.006). However, good correlation was demonstrated between MR techniques (GLS:r=0.74; GCS:r=0.80; GRS:r=0.45, all p<0.05). Comparing DRA with FT, intra-/interobserver coefficient of variance was lower (1.6 %/3.2 % vs. 6.4 %/5.7 %) and intraclass-correlation coefficient was higher. DRA GCS and GRS data presented zero variability for repeated observations. CONCLUSIONS: DRA is an automated method that allows myocardial deformation assessment with superior reproducibility compared to FT. KEY POINTS: • Inverse deformable registration algorithms (DRA) allow myocardial strain analysis on cine MRI. • Inverse DRA demonstrated superior reproducibility compared to feature-tracking (FT) methods. • Cine MR DRA and FT analysis demonstrate differences to speckle-tracking echocardiography • DRA demonstrated better correlation with STE than FT for MR-derived global strain data.

Registration of in vivo prostate MRI and pseudo-whole mount histology using Local Affine Transformations guided by Internal Structures (LATIS).

PURPOSE: To present a novel registration approach called LATIS (Local Affine Transformation guided by Internal Structures) for coregistering post prostatectomy pseudo-whole mount (PWM) pathological sections with in vivo MRI (magnetic resonance imaging) images. MATERIALS AND METHODS: Thirty-five patients with biopsy-proven prostate cancer were imaged at 3T with an endorectal coil. Excised prostate specimens underwent quarter mount step-section pathologic processing, digitization, annotation, and assembly into a PWM. Manually annotated macro-structures on both pathology and MRI were used to assist registration using a relaxed local affine transformation approximation. Registration accuracy was assessed by calculation of the Dice similarity coefficient (DSC) between transformed and target capsule masks and least-square distance between transformed and target landmark positions. RESULTS: LATIS registration resulted in a DSC value of 0.991 ± 0.004 and registration accuracy of 1.54 ± 0.64 mm based on identified landmarks common to both datasets. Image registration performed without the use of internal structures led to an 87% increase in landmark-based registration error. Derived transformation matrices were used to map regions of pathologically defined disease to MRI. CONCLUSION: LATIS was used to successfully coregister digital pathology with in vivo MRI to facilitate improved correlative studies between pathologically identified features of prostate cancer and multiparametric MRI.