Search

Significance: Analysis of modern large-scale, multicenter or diseased data requires deformable registration algorithms that can cope with data of diverse nature. Objective: We propose a novel deformable registration method, which is based on a cue-aware deep regression network, to deal with multiple databases with minimal parameter tuning. Methods: Our method learns and predicts the deformation field between a reference image and a subject image. Specifically, given a set of training images, our method learns the displacement vector associated with a pair of reference–subject patches. To achieve this, we first introduce a key-point truncated-balanced sampling strategy to facilitate accurate learning from the image database of limited size. Then, we design a cue-aware deep regression network, where we propose to employ the contextual cue, i.e., the scale-adaptive local similarity, to more apparently guide the learning process. The deep regression network is aware of the contextual cue for accurate prediction of local deformation. Results and Conclusion: Our experiments show that the proposed method can tackle various registration tasks on different databases, giving consistent good performance without the need of manual parameter tuning, which could be applicable to various clinical applications. [ABSTRACT FROM AUTHOR]

Deformable image registration is a fundamental problem in computer vision and medical image computing. In this paper we investigate the use of graphical models in the context of a particular type of image registration problem, known as slice-to-volume registration. We introduce a scalable, modular and flexible formulation that can accommodate low-rank and high order terms, that simultaneously selects the plane and estimates the in-plane deformation through a single shot optimization approach. The proposed framework is instantiated into different variants seeking either a compromise between computational efficiency (soft plane selection constraints and approximate definition of the data similarity terms through pair-wise components) or exact definition of the data terms and the constraints on the plane selection. Simulated and real-data in the context of ultrasound and magnetic resonance registration (where both framework instantiations as well as different optimization strategies are considered) demonstrate the potentials of our method. [ABSTRACT FROM AUTHOR]

Purpose To analyse the influence of the image registration method on the adaptive radiotherapy of an IMRT prostate treatment, and to compare the dose accumulation according to 3 different image registration methods with the planned dose. Material and methods The IMRT prostate patient was CT imaged 3 times throughout his treatment. The prostate, PTV, rectum and bladder were segmented on each CT. A Rigid, a deformable (DIR) B-spline and a DIR with landmarks registration algorithms were employed. The difference between the accumulated doses and planned doses were evaluated by the gamma index. The Dice coefficient and Hausdorff distance was used to evaluate the overlap between volumes, to quantify the quality of the registration. Results When comparing adaptive vs no adaptive RT, the gamma index calculation showed large differences depending on the image registration method (as much as 87.6% in the case of DIR B-spline). The quality of the registration was evaluated using an index such as the Dice coefficient. This showed that the best result was obtained with DIR with landmarks compared with the rest and it was always above 0.77, reported as a recommended minimum value for prostate studies in a multi-centre review. Conclusions Apart from showing the importance of the application of an adaptive RT protocol in a particular treatment, this work shows that the election of the registration method is decisive in the result of the adaptive radiotherapy and dose accumulation. [ABSTRACT FROM AUTHOR]

Introduction The application of deformable image registration ( DIR) to megavoltage computed tomography ( MVCT) images benefits adaptive radiotherapy. This study aims to quantify the accuracy of DIR for MVCT images when using different deformation methods assessed in a cubic phantom and nasopharyngeal carcinoma ( NPC) patients. Methods In the control studies, the DIR accuracy in air-tissue and tissue-tissue interface areas was observed using twelve shapes of acrylic and tissue-equivalent material inserted in the phantom. In the clinical studies, the 1st and 20th fraction MVCT images of seven NPC patients were used to evaluate application of DIR. The eight DIR methods used in the DIRART software varied in (i) transformation framework (asymmetric or symmetric), (ii) DIR registration algorithm (Demons or Optical Flow) and (iii) mapping direction (forward or backward). The accuracy of the methods was compared using an intensity-based criterion (correlation coefficient, CC) and volume-based criterion (Dice's similarity coefficient, DSC). Results The asymmetric transformation with Optical Flow showed the best performance for air-tissue interface areas, with a mean CC and DSC of 0.97 ± 0.03 and 0.79 ± 0.11 respectively. The symmetric transformation with Optical Flow showed good agreement for tissue-tissue interface areas with a CC of (0.99 ± 0.01) and DSC of (0.89 ± 0.03). The sequences of target domains were significantly different in tissue-tissue interface areas. Conclusions The deformation method and interface area affected the accuracy of DIR. The validation techniques showed satisfactory volume matching of greater than 0.7 with DSC analysis. The methods can yield acceptable results for clinical applications. [ABSTRACT FROM AUTHOR]

The purpose of this study is to evaluate the effect of nonrigid and fractionation-corrected dose summation on total doses in radiotherapy and to demonstrate the benefits of such dose summation on clinical decision-making for planning of retreatments. Dose summation of organs at risk (OARs) was investigated for 3 clinical cases with need of retreatment to the same site: head and neck, brain, and mediastinum. Three different summation methods over old and new radiotherapy treatment plans are presented and compared: (1) rigid raw sum with rigid registration of the planning images and direct dose summing; (2) deformable raw sum with deformable image registration and direct dose summing; and (3) deformable biological sum with deformable registration and takes into account the dose per fraction in biological manner in certain critical organs. In 2 cases, a user-defined dose downscaling is applied to take into account the time between the treatments and the healing from the radiation-induced effects. Of the 3 summation methods presented, the deformable biological sum was considered to offer the most biologically plausible account of the treatment. There were remarkable differences between near-maximum doses (D0.1cc) and dose-volume histogram (DVH) curves for OARs between different summation methods. The differences between deformable raw sum and rigid raw sum D0.1cc doses are in the range from −8 Gy to 2 Gy. Similarly, the deviation was from −14 Gy to 5 Gy for the deformable biological sum compared with the rigid raw sum. These differences come from incorrect summation of doses in the rigid raw sum case, and from the dose per fraction effect in biological summation. We conclude that computing the 3-dimensional deformable biological summation could be a valuable tool for treating patients with complex retreatments. It has the potential to assist the oncologist in refining plans for maximally curative doses while respecting appropriate tissue tolerances. [ABSTRACT FROM AUTHOR]

Rationale and Objectives: This study aimed to assess a novel method of three-dimensional (3D) co-registration of prostate magnetic resonance imaging (MRI) examinations performed before and after prostate cancer focal therapy.Materials and Methods: We developed a software platform for automatic 3D deformable co-registration of prostate MRI at different time points and applied this method to 10 patients who underwent focal ablative therapy. MRI examinations were performed preoperatively, as well as 1 week and 6 months post treatment. Rigid registration served as reference for assessing co-registration accuracy and precision.Results: Segmentation of preoperative and postoperative prostate revealed a significant postoperative volume decrease of the gland that averaged 6.49 cc (P = .017). Applying deformable transformation based on mutual information from 120 pairs of MRI slices, we refined by 2.9 mm (max. 6.25 mm) the alignment of the ablation zone, segmented from contrast-enhanced images on the 1-week postoperative examination, to the 6-month postoperative T2-weighted images. This represented a 500% improvement over the rigid approach (P = .001), corrected by volume. The dissimilarity by Dice index of the mapped ablation zone using deformable transformation vs rigid control was significantly (P = .04) higher at the ablation site than in the whole gland.Conclusions: Our findings illustrate our method's ability to correct for deformation at the ablation site. The preliminary analysis suggests that deformable transformation computed from mutual information of preoperative and follow-up MRI is accurate in co-registration of MRI examinations performed before and after focal therapy. The ability to localize the previously ablated tissue in 3D space may improve targeting for image-guided follow-up biopsy within focal therapy protocols. [ABSTRACT FROM AUTHOR]

Purpose: In interstitial high-dose rate brachytherapy, liver cancer is treated by internal radiation, requiring percutaneous placement of applicators within or close to the tumor. To maximize utility, the optimal applicator configuration is pre-planned on magnetic resonance images. The pre-planned configuration is then implemented via a magnetic resonance-guided intervention. Mapping the pre-planning information onto interventional data would reduce the radiologist's cognitive load during the intervention and could possibly minimize discrepancies between optimally pre-planned and actually placed applicators. Methods: We propose a fast and robust two-step registration framework suitable for interventional settings: first, we utilize a multi-resolution rigid registration to correct for differences in patient positioning (rotation and translation). Second, we employ a novel iterative approach alternating between bias field correction and Markov random field deformable registration in a multi-resolution framework to compensate for non-rigid movements of the liver, the tumors and the organs at risk. In contrast to existing pre-correction methods, our multi-resolution scheme can recover bias field artifacts of different extents at marginal computational costs. Results: We compared our approach to deformable registration via B-splines, demons and the SyN method on 22 registration tasks from eleven patients. Results showed that our approach is more accurate than the contenders for liver as well as for tumor tissues. We yield average liver volume overlaps of 94.0 ± 2.7% and average surface-to-surface distances of 2.02 ± 0.87 mm and 3.55 ± 2.19 mm for liver and tumor tissue, respectively. The reported distances are close to (or even below) the slice spacing (2.5 - 3.0 mm) of our data. Our approach is also the fastest, taking 35.8 ± 12.8 s per task. Conclusion: The presented approach is sufficiently accurate to map information available from brachytherapy pre-planning onto interventional data. It is also reasonably fast, providing a starting point for computer-aidance during intervention. [ABSTRACT FROM AUTHOR]

Accurate measurement of local strain in heterogeneous and anisotropic bone tissue is fundamental to understand the pathophysiology of musculoskeletal diseases, to evaluate the effect of interventions from preclinical studies, and to optimize the design and delivery of biomaterials. Digital volume correlation (DVC) can be used to measure the three-dimensional displacement and strain fields from micro-computed tomography (μCT) images of loaded specimens. However, this approach is affected by the quality of the input images, by the morphology and density of the tissue under investigation, by the correlation scheme, and by the operational parameters used in the computation. Therefore, for each application, the precision of the method should be evaluated. In this paper, we present the results collected from datasets analyzed in previous studies as well as new data from a recent experimental campaign for characterizing the relationship between the precision of two different DVC approaches and the spatial resolution of the outputs. Different bone structures scanned with laboratory source μCT or synchrotron light μCT (SRμCT) were processed in zero-strain tests to evaluate the precision of the DVC methods as a function of the subvolume size that ranged from 8 to 2,500 µm. The results confirmed that for every microstructure the precision of DVC improves for larger subvolume size, following power laws. However, for the first time, large differences in the precision of both local and global DVC approaches have been highlighted when SRμCT or in vivo μCT images were used instead of conventional ex vivo μCT. These findings suggest that in situ mechanical testing protocols applied in SRμCT facilities should be optimized to allow DVC analyses of localized strain measurements. Moreover, for in vivo μCT applications, DVC analyses should be performed only with relatively course spatial resolution for achieving a reasonable precision of the method. In conclusion, we have extensively shown that the precision of both tested DVC approaches is affected by different bone structures, different input image resolution, and different subvolume sizes. Before each specific application, DVC users should always apply a similar approach to find the best compromise between precision and spatial resolution of the measurements.

Purpose: Accurate deformable image registration is necessary for longitudinal studies. The error associated with commercial systems has been evaluated using computed tomography (CT). Several in-house algorithms have been evaluated for use with magnetic resonance imaging (MRI), but there is still relatively little information about MRI deformable image registration. This work presents an evaluation of two deformable image registration systems, one commercial (Velocity) and one in-house (demons-based algorithm), with MRI using two different metrics to quantify the registration error. Methods: The registration error was analyzed with synthetic MR images. These images were generated from interpatient and intrapatient variation models trained on 28 patients. Four synthetic post-treatment images were generated for each of four synthetic pretreatment images, resulting in 16 image registrations for both the T1- and T2-weighted images. The synthetic post-treatment images were registered to their corresponding synthetic pretreatment image. The registration error was calculated between the known deformation vector field and the generated deformation vector field from the image registration system. The registration error was also analyzed using a porcine phantom with ten implanted 0.35-mm diameter gold markers. The markers were visible on CT but not MRI. CT, T1-weighted MR, and T2-weighted MR images were taken in four different positions. The markers were contoured on the CT images and rigidly registered to their corresponding MR images. The MR images were deformably registered and the distance between the projected marker location and true marker location was measured as the registration error. Results: The synthetic images were evaluated only on Velocity. Root mean square errors (RMSEs) of 0.76 mm in the left-right (LR) direction, 0.76 mm in the anteroposterior (AP) direction, and 0.69 mm in the superior-inferior (SI) direction were observed for the T1-weighted MR images. RMSEs of 1.1 mm in the LR direction, 0.75 mm in the AP direction, and 0.81 mm in the SI direction were observed for the T2-weighted MR images. The porcine phantom MR images, when evaluated with Velocity, had RMSEs of 1.8, 1.5, and 2.7 mm in the LR, AP, and SI directions for the T1-weighted images and 1.3, 1.2, and 1.6 mm in the LR, AP, and SI directions for the T2-weighted images. When the porcine phantom images were evaluated with the in-house demons-based algorithm, RMSEs were 1.2, 1.5, and 2.1 mm in the LR, AP, and SI directions for the T1-weighted images and 0.81, 1.1, and 1.1 mm in the LR, AP, and SI directions for the T2-weighted images. Conclusions: The MRI registration error was low for both Velocity and the in-house demons-based algorithm according to both image evaluation methods, with all RMSEs below 3 mm. This implies that both image registration systems can be used for longitudinal studies using MRI. [ABSTRACT FROM AUTHOR]

Deformable registration is ubiquitous in medical image analysis. Many deformable registration methods minimize sum of squared difference (SSD) as the registration cost with respect to deformable model parameters. In this work, we construct a tight upper bound of the SSD registration cost by using a fully convolutional neural network (FCNN) in the registration pipeline. The upper bound SSD (UB-SSD) enhances the original deformable model parameter space by adding a heatmap output from FCNN. Next, we minimize this UB-SSD by adjusting both the parameters of the FCNN and the parameters of the deformable model in coordinate descent. Our coordinate descent framework is end-to-end and it can work with any deformable registration method that uses SSD. We demonstrate experimentally that our method enhances the accuracy of deformable registration algorithms significantly on two publicly available 3D brain MRI data sets. [ABSTRACT FROM AUTHOR]

Background and purpose Differential baseline shifts between primary tumor and involved lymph nodes in locally advanced lung cancer patients compromise the accuracy of radiotherapy. The purpose of this study was to evaluate the performance of an average anatomy model ( AAM) derived from repeat imaging and deformable registration to reduce these geometrical uncertainties. Methods and materials An in-house implementation of a B-Spline deformable image registration ( DIR) algorithm was first validated using three different validation approaches: (a) a circle method to test the consistency of the DIR, (b) fiducial marker target registration error, and (c) the recovery of a known deformation vector field ( DVF). Subsequently, AAM was generated by first averaging five DVFs resulting from cone beam CT ( CBCT) to planning CT ( pCT) DIR and second by applying the inverse of the average DVF to the pCT. The proposed method was evaluated on 15 locally advanced lung cancer patients receiving daily motion compensated CBCT and a repeat CT ( rCT) for adaptive radiotherapy. Reduction of systematic baseline shifts of the primary tumor were quantified for the fractions used to build the AAM as well as over the whole treatment and compared to the performance of the rCT. Results The deformable registration accuracy was ≤ 2 mm vector length for the first two validation methods and about 3 mm for the third method. The systematic baseline shifts over the five fractions prior to the rCT used to build the AAM reduced from 5.9 mm vector length relative to the pCT to 2.3 and 4.2 mm relative to the AAM and rCT, respectively. The overall systematic errors in the left-right, cranio-caudal, and anterior-posterior directions were [3.4, 3.8, 3.3] mm, [2.3, 2.9, 2.6] mm, and [2.3, 3.1, 2.7] mm for the pCT, AAM, and rCT, respectively. Conclusions The AAM mitigates systematic errors occurring during treatment due to differential baseline shifts between the primary tumor and involved lymph nodes similar to (or even better than) rCT. The superior performance of the AAM in terms of the systematic error derived from the initial fractions indicates that further analysis of the optimum intervention time is required. This model has the potential to be used as an efficient and accurate alternative for rCT in adaptive radiotherapy of locally advanced lung cancer patients, obviating the need for rescanning and recontouring. [ABSTRACT FROM AUTHOR]

Purpose Recent pulmonary imaging research has revealed that in patients with chronic obstructive pulmonary disease ( COPD) and asthma, structural and functional abnormalities are spatially heterogeneous. This novel information may help optimize treatment in individual patients, monitor interventional efficacy, and develop new treatments. Moreover, by automating the measurement of regional biomarkers for the 19 different anatomical lung segments, there is an opportunity to embed imaging biomarkers into clinically acceptable clinical workflows and improve lung disease clinical care. Therefore, to exploit the regional structure-function information provided by thoracic imaging, and as a first step toward this goal, our objective was to develop a fully automated registration pipeline for thoracic x-ray computed tomography ( CT) and inhaled gas functional magnetic resonance imaging ( MRI) whole lung and segmental structure-function biomarkers. Methods Thirty-five patients including 15 severe, poorly controlled asthmatics and 20 COPD patients [classified according to the global initiative for chronic obstructive lung disease ( GOLD) criteria)] provided written informed consent to a study protocol approved by Health Canada and underwent pulmonary function tests, MRI, and CT during a single 2-hour visit. Using this diverse patient dataset, we developed and evaluated a joint deformable registration approach to simultaneously coregister CT with both 1H and 3He MRI by enforcing the similarity of the deformation fields from the two individual registrations. We derived a simpler model that was equivalent to the original challenging optimization problem through variational analysis and the simpler model gave rise to an efficient numerical solver that was parallelized on a graphics processing unit. The coregistered CT-3He MRI and whole lung/segmental lung masks were used to generate whole lung and segmental 3He MRI ventilation defect percent ( VDP). To estimate fiducial localization reproducibility, a single observer manually identified 109 pairs of CT and 3He MRI fiducials for 35 patient images on five separate occasions and determined the fiducial localization error ( FLE). CT-3He MRI registration accuracy was evaluated using the target registration error ( TRE). Whole lung VDP generated using the algorithm was compared with VDP generated using a previously validated semiautomated approach and computational efficiency was evaluated using run time. Results In 35 patients including 15 with severe asthma and 20 with COPD, mean forced expiratory volume in 1 s ( FEV1) was 63±24%pred and FEV1/forced vital capacity ( FVC) was 54 ± 17%. FLE was 0.16 mm and 0.34 mm for 3He MRI and CT, respectively. TRE was 4.5 ± 2.0 mm, 4.0 ± 1.7 mm, 4.8 ± 2.3 mm for asthma, COPD GOLD II, and GOLD III groups, respectively, with a mean of 4.4 ± 2.0 mm for the entire dataset. TRE was significantly improved for joint CT-1H/3He MRI registration compared with CT-1H MRI rigid registration ( P < 0.0001). Whole lung VDP generated using the pipeline was not significantly different ( P = 0.37) compared to a semiautomated method with which it was strongly correlated (r = 0.93, P < 0.0001). The fully automated pipeline required 11 ± 0.4 min to generate whole lung and segmental VDP. Conclusions For a diverse group of patients with COPD and asthma, whole lung and segmental VDP was measured using an automated lung image analysis pipeline which provides a way to incorporate lung functional biomarkers into clinical research and patient care. [ABSTRACT FROM AUTHOR]

In this paper, we extend our previous work on deformable image registration to inhomogenous tissues. Inhomogenous tissues include the tissues with embedded tumors, which is common in clinical applications. It is a very challenging task since the registration method that works for homogenous tissues may not work well with inhomogenous tissues. The maximum error normally occurs in the regions with tumors and often exceeds the acceptable error threshold. In this paper, we propose a new error correction method with adaptive weighting to reduce the maximum registration error. Our previous fast deformable registration method is used in the inner loop. We have also proposed a new evaluation metric average error of deformation field (AEDF) to evaluate the registration accuracy in regions between vessels and bifurcation points. We have validated the proposed method using liver MR images from human subjects. AEDF results show that the proposed method can greatly reduce the maximum registration errors when compared with the previous method with no adaptive weighting. The proposed method has the potential to be used in clinical applications to reduce registration errors in regions with tumors. [ABSTRACT FROM AUTHOR]

• Liver SBRT doses were accumulated to evaluate the impact of unexpected cone beam CT anatomic changes on dosimetry in patients treated with concurrent sorafenib. • Patients with reductions in liver volume on CBCT had larger increases in accumulated dose for normal liver and adjacent normal tissues, compared to patients with relatively stable anatomy. • The anatomic changes were dosimetrically and spatially associated with gastrointestinal toxicities in patients with higher baseline risk treated with SBRT and concurrent sorafenib. Unexpected liver volume reductions occurred during trials of liver SBRT and concurrent sorafenib. The aims were to accumulate liver SBRT doses to assess the impact of these anatomic variations on normal tissue dose parameters and toxicity. Thirty-two patients with hepatocellular carcinoma (HCC) or metastases treated on trials of liver SBRT (30–57 Gy, 6 fractions) and concurrent sorafenib were analyzed. SBRT doses were accumulated using biomechanical deformable registration of daily cone-beam CT. Dose deviations (accumulated-planned) for normal tissues were compared for patients with liver volume reductions > 100 cc versus stable volumes, and accumulated doses were reported for three patients with grade 3–5 luminal gastrointestinal toxicities. Patients with reduced (N = 12) liver volumes had larger mean deviations of 0.4–1.3 Gy in normal tissues, versus −0.2–0.4 Gy for stable cases (N = 20), P > 0.05. Deviations > 5% of the prescribed dose occurred in both groups. Two HCC patients with toxicities to small and large bowel had liver volume reductions and deviations to the maximum dose of 4% (accumulated 36.9 Gy) and 3% (accumulated 33.4 Gy) to these organs respectively. Another HCC patient with a toxicity of unknown location plus tumor rupture, had stable liver volumes and deviations to luminal organs of −6% to 4.5% (accumulated < 30.5 Gy). Liver volume reductions during SBRT and concurrent sorafenib were associated with larger increases in accumulated dose to normal tissues versus stable liver volumes. These dosimetric changes may have further contributed to toxicities in HCC patients who have higher baseline risks. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) deformable image registration is a fundamental technique in medical image analysis tasks. Although it has been extensively investigated, current deep-learning-based registration models may face the challenges posed by deformations with various degrees of complexity. This paper proposes an adaptive multi-level registration network (AMNet) to retain the continuity of the deformation field and to achieve high-performance registration for 3D brain MR images. First, we design a lightweight registration network with an adaptive growth strategy to learn deformation field from multi-level wavelet sub-bands, which facilitates both global and local optimization and achieves registration with high performance. Second, our AMNet is designed for image-wise registration, which adapts the local importance of a region in accordance with the complexity degrees of its deformation, and thereafter improves the registration efficiency and maintains the continuity of the deformation field. Experimental results from five publicly-available brain MR datasets and a synthetic brain MR dataset show that our method achieves superior performance against state-of-the-art medical image registration approaches. [Display omitted] • A lightweight deep model to estimate multi-level deformations with one forward pass. • Optimization of the model is accelerated by adaptive growth strategy. • Registration is focused from global to local by information importance adaptation. • Being constructed with wavelet transformation that enables information preservation. [ABSTRACT FROM AUTHOR]