Registration-based Method Research Articles

Registration-based nonlinear model reduction of parametrized aerodynamics problems with applications to transonic Euler and RANS flows

We develop a registration-based nonlinear model-order reduction (MOR) method for partial differential equations (PDEs) with applications to transonic Euler and Reynolds-averaged Navier–Stokes (RANS) equations in aerodynamics. These PDEs exhibit discontinuous features, namely shocks, whose location depends on problem configuration parameters, and the associated parametric solution manifold exhibits a slowly decaying Kolmogorov N-width. As a result, conventional linear MOR methods, which use linear reduced approximation spaces, do not yield accurate low-dimensional approximations. We present a registration-based nonlinear MOR method to overcome this challenge. Our formulation builds on the following key ingredients: (i) a geometrically transformable parametrized PDE discretization; (ii) localized spline-based parametrized transformations which warp the domain to align discontinuities; (iii) an efficient dilation-based shock sensor and metric to compute optimal transformation parameters; (iv) hyperreduction and online-efficient output-based error estimates; and (v) simultaneous transformation and adaptive finite element training. Compared to existing methods in the literature, our formulation is efficiently scalable to larger problems and is equipped with error estimates and hyperreduction. We demonstrate the effectiveness of the method on two-dimensional inviscid and turbulent flows modeled by the Euler and RANS equations, respectively.

Mesh registration-based boundary element method of head-related transfer function: unification of hair impedance boundary conditions

In the calculation of Head-Related Transfer Functions (HRTFs) using the Boundary Element Method (BEM), the head surface of a subject needs to be discretized into boundary elements with specific impedance. To simplify HRTF calculation, a method for coupling Mesh Registration and BEM (MR-BEM) is proposed in this work, which means that a template mesh for calculation is established to register and generate the calculation mesh of a new head model, to replace the tedious operations of boundary conditions configuration. To validate the proposed method, the widely-used KEMAR artificial head model was adopted to compare the HRTFs of two groups of calculation meshes manually assigned and automatically registered impedance boundary conditions, respectively. Based on the inherent similarities in head shape and hair regions across individuals, the non-rigid impedance was set only for the hair region. Although the reflections from the non-rigid impedance of hair and clothes were shielded by pinnae in practice, this work just aims to validate the feasibility of the MR-BEM, which is significant for the simplification of BEM-based HRTF calculation.

Geometric Constraints and Rough-Fine Registration-Based Localization Method for Social Intelligent Transportation Systems

Geometric Constraints and Rough-Fine Registration-Based Localization Method for Social Intelligent Transportation Systems

A surface registration-based approach for assessment of 3D angles in guided growth interventions in the growing femur.

Postoperative assessment of surgical interventions for correcting femoral rotational deformities necessitates a comparative analysis of femoral rotation pre- and post-surgery. While 2D assessment methods are commonly employed, ongoing debate surrounds their accuracy and reliability. To address the limitations associated with 2D analysis, we introduced and validated a 3D model-based analysis method for quantifying the angular and rotational impact of corrective rotational osteotomy in the growing femur. The method is based on surface registration of the pre- and post-intervention 3D femoral models. To this end, 3D triangulated surface models were generated using CT images for the right femurs of 11 skeletally immature pigs, each scanned at two distinct time points with a 12-week interval between scans. In our validation procedures, femoral corrective rotational osteotomy of the post-12-week femur was simulated at varying angles of 5, 10, 15and 20 degrees in three dimensions. Subsequently, a surface 3D/3D registration-based approach was applied to determine the 3D femoral angulation and rotation between the two modelsto assess the method's detection accuracy of the predefined twist angles as ground truth references. The results document the precision and accuracy of the registration-based method in evaluating rotation angles. Consistently high accuracy was observed across all angles, with an accuracy rate of 92.97% and a coefficient of variance of 8.14%. This study has showcased the potential for improving post-operative assessments with significant implications for experimental studies evaluating the effects of correcting rotational deformities in the growing femur. Not applicable.

Automatic cortical surface parcellation in the fetal brain using attention-gated spherical U-net.

Cortical surface parcellation for fetal brains is essential for the understanding of neurodevelopmental trajectories during gestations with regional analyses of brain structures and functions. This study proposes the attention-gated spherical U-net, a novel deep-learning model designed for automatic cortical surface parcellation of the fetal brain. We trained and validated the model using MRIs from 55 typically developing fetuses [gestational weeks: 32.9 ± 3.3 (mean ± SD), 27.4-38.7]. The proposed model was compared with the surface registration-based method, SPHARM-net, and the original spherical U-net. Our model demonstrated significantly higher accuracy in parcellation performance compared to previous methods, achieving an overall Dice coefficient of 0.899 ± 0.020. It also showed the lowest error in terms of the median boundary distance, 2.47 ± 1.322 (mm), and mean absolute percent error in surface area measurement, 10.40 ± 2.64 (%). In this study, we showed the efficacy of the attention gates in capturing the subtle but important information in fetal cortical surface parcellation. Our precise automatic parcellation model could increase sensitivity in detecting regional cortical anomalies and lead to the potential for early detection of neurodevelopmental disorders in fetuses.

L-PCM: Localization and Point Cloud Registration-Based Method for Pose Calibration of Mobile Robots

The autonomous navigation of mobile robots contains three parts: map building, global localization, and path planning. Precise pose data directly affect the accuracy of global localization. However, the cumulative error problems of sensors and various estimation strategies cause the pose to have a large gap in data accuracy. To address these problems, this paper proposes a pose calibration method based on localization and point cloud registration, which is called L-PCM. Firstly, the method obtains the odometer and IMU (inertial measurement unit) data through the sensors mounted on the mobile robot and uses the UKF (unscented Kalman filter) algorithm to filter and fuse the odometer data and IMU data to obtain the estimated pose of the mobile robot. Secondly, the AMCL (adaptive Monte Carlo localization) is improved by combining the UKF fusion model of the IMU and odometer to obtain the modified global initial pose of the mobile robot. Finally, PL-ICP (point to line-iterative closest point) point cloud registration is used to calibrate the modified global initial pose to obtain the global pose of the mobile robot. Through simulation experiments, it is verified that the UKF fusion algorithm can reduce the influence of cumulative errors and the improved AMCL algorithm can optimize the pose trajectory. The average value of the position error is about 0.0447 m, and the average value of the angle error is stabilized at about 0.0049 degrees. Meanwhile, it has been verified that the L-PCM is significantly better than the existing AMCL algorithm, with a position error of about 0.01726 m and an average angle error of about 0.00302 degrees, effectively improving the accuracy of the pose.

Adaptable cascaded registration for personalized maxilla completion and cleft defect volume estimation.

Cone-beam computed tomography (CBCT) images provide high-resolution insights into the underlying craniofacial anomaly in patients with cleft lip and palate (CLP), requiring non-negligible annotation costs to measure the cleft defect for the guidance of the clinical secondary alveolar bone graft procedures. Considering the cumbersome volumetric image acquisition, there is a lack of paired CLP CBCTs and normal CBCTs for learning-based anatomical structure restoration models. Nowadays, the registration-based method relieves the annotation burden, though one-shot registration and the regular mask are limited to handling fine-grained shape variations and harmony between restored bony tissues and the defectedmaxilla. This study aimed to design and evaluate a novel method for deformable partial registration of the CLP CBCTs and normal CBCTs, enabling personalized maxilla completion and cleft defect volume prediction from CLPCBCTs. We proposed an adaptable deep registration framework for personalized maxilla completion and cleft defect volume prediction from CLP CBCTs. The key ingredient was a cascaded partial registration to exploit the maxillary morphology prior and attribute transfer. Cascaded registration with coarse-to-fine registration fields handled morphological variations of cleft defects and fine-grained maxillary restoration. We designed an adaptable cleft defect mask and volumetric Boolean operators for reliable voxel filling of the defected maxilla. A total of 36 clinically obtained CLP CBCTs were used to train and validate the proposed model, among which 22 CLP CBCTs were used to generate a training dataset with 440 synthetic CBCTs by B-spline deformation-based data augmentation and the remaining for testing. The proposed model was evaluated on maxilla completion and cleft defect volume prediction from clinically obtained unilateral and bilateral CLPCBCTs. Extensive experiments demonstrated the effectiveness of the adaptable cleft defect mask and the cascaded partial registration on maxilla completion and cleft defect volume prediction. The proposed method achieved state-of-the-art performances with the Dice similarity coefficient of 0.90 0.02 on the restored maxilla and 0.84 0.04 on the estimated cleft defect, respectively. The average Hausdorff distance between the estimated cleft defect and the manually annotated ground truth was 0.30 0.08 mm. The relative volume error of the cleft defect was 0.08. The proposed model allowed for the prediction of cleft defect maps that were in line with the ground truth in the challenging unilateral and bilateral CLP CBCTs. The results suggest that the proposed adaptable deep registration model enables patient-specific maxilla completion and automatic annotation of cleft defects, relieving tedious voxel-wise annotation and image acquisitionburdens.

An image registration-based self-supervised Su-Net for carotid plaque ultrasound image segmentation

Background and ObjectivesTotal Plaque Area (TPA) measurement is critical for early diagnosis and intervention of carotid atherosclerosis in individuals with high risk for stroke. The delineation of the carotid plaques is necessary for TPA measurement, and deep learning methods can automatically segment the plaque and measure TPA from carotid ultrasound images. A large number of labeled images is essential for training a good deep learning model, but it is very difficult to collect such large labeled datasets for carotid image segmentation in clinical practice. Self-supervised learning can provide a possible solution to improve the deep-learning models on small labeled training datasets by designing a pretext task to pre-train the models without using the segmentation masks. However, the existing self-supervised learning methods do not consider the feature presentations of object contours. MethodsIn this paper, we propose an image registration-based self-supervised learning method and a stacked U-Net (SSL-SU-Net) for carotid plaque ultrasound image segmentation, which can better exploit the semantic features of carotid plaque contours in self-supervised task training. ResultsOur network was trained on different numbers of labeled images (n = 10, 33, 50 and 100 subjects) and tested on 44 subjects from the SPARC dataset (n = 144, London, Canada). The network trained on the entire SPARC dataset was then directly applied to an independent dataset collected in Zhongnan hospital (n = 497, Wuhan, China). For the 44 subjects tested on the SPARC dataset, our method yielded a DSC of 80.25-89.18% and the produced TPA measurements, which were strongly correlated with manual segmentation (r = 0.965-0.995, ρ< 0.0001). For the Zhongnan dataset, the DSC was 90.3% and algorithm TPAs were strongly correlated with manual TPAs (r = 0.985, ρ< 0.0001). ConclusionsThe results demonstrate that our proposed method yielded excellent performance and good generalization ability when trained on a small labeled dataset, facilitating the use of deep learning in carotid ultrasound image analysis and clinical practice. The code of our algorithm is available https://github.com/a610lab/Registration-SSL.

Patient-Adaptive Automated Segmentation in Daily kVCT Images for Radiotherapy of Head and Neck and Prostate Cancer

The purpose of this study was to examine the use of transfer learning in deep learning-based auto-segmentation of daily kilovoltage computed tomography (kVCT) images for patient-specific adaptive radiotherapy. Using data from the first cohort of patients treated with the innovative BgRT system, the objective of this study was to evaluate the potential benefits of this approach in facilitating efficient and effective adaptive radiotherapy. For the head and neck (HaN) site and pelvic site, we first trained a deep convolutional segmentation network using a population dataset, consisting of 67 and 56 patient cases, respectively. This population network was then fine-tuned for a specific patient using a transfer learning approach, adapting the network weights. The auto-segmentation network utilized in this study was a 23-layer U-Net with batch normalization, a dropout rate of 0.5, and four skip connections between the encoder and decoder at different levels. We used initial planning CT and 5-26 sets of daily kVCT scans with a total of 8,039 images for patient-specific learning in the 6 HaN cases and 4 pelvic cases, particularly analyzing the relationship between the number of sequential patient-specific training data and the performance of the auto-segmentation. We compared the performance of the patient-specific network with the population network and the clinical rigid registration method, using the Dice similarity coefficient (DSC) as the evaluation metric. Additionally, we investigated the corresponding dosimetric impacts of the different auto-segmentation and registration methods. The patient-specific network showed improved mean DSC scores of 0.88 and 0.90 for three HaN organs at risk (OARs) and eight pelvic targets and OARs, respectively, compared to the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network steadily improved as the number of longitudinal training cases increased, reaching near saturation after 6 training cases. The use of the patient-specific auto-segmentation resulted in a reduction of the mean discrepancy in target and OAR doses between delivery and planning from 5.5% with the clinical rigid registration to 1.1%. The use of patient-specific transfer learning in auto-segmenting kVCT images showed higher accuracy compared to a conventional population network and clinical registration-based method. This approach holds promise for enhancing dose evaluation accuracy in adaptive radiotherapy.

Deep Learning and Registration-Based Mapping for Analyzing the Distribution of Nodal Metastases in Head and Neck Cancer Cohorts: Informing Optimal Radiotherapy Target Volume Design.

We introduce a deep-learning- and a registration-based method for automatically analyzing the spatial distribution of nodal metastases (LNs) in head and neck (H/N) cancer cohorts to inform radiotherapy (RT) target volume design. The two methods are evaluated in a cohort of 193 H/N patients/planning CTs with a total of 449 LNs. In the deep learning method, a previously developed nnU-Net 3D/2D ensemble model is used to autosegment 20 H/N levels, with each LN subsequently being algorithmically assigned to the closest-level autosegmentation. In the nonrigid-registration-based mapping method, LNs are mapped into a calculated template CT representing the cohort-average patient anatomy, and kernel density estimation is employed to estimate the underlying average 3D-LN probability distribution allowing for analysis and visualization without prespecified level definitions. Multireader assessment by three radio-oncologists with majority voting was used to evaluate the deep learning method and obtain the ground-truth distribution. For the mapping technique, the proportion of LNs predicted by the 3D probability distribution for each level was calculated and compared to the deep learning and ground-truth distributions. As determined by a multireader review with majority voting, the deep learning method correctly categorized all 449 LNs to their respective levels. Level 2 showed the highest LN involvement (59.0%). The level involvement predicted by the mapping technique was consistent with the ground-truth distribution (p for difference 0.915). Application of the proposed methods to multicenter cohorts with selected H/N tumor subtypes for informing optimal RT target volume design is promising.

Performance of an automated registration-based method for longitudinal lesion matching and comparison to inter-reader variability

Objective. Patients with metastatic disease are followed throughout treatment with medical imaging, and accurately assessing changes of individual lesions is critical to properly inform clinical decisions. The goal of this work was to assess the performance of an automated lesion-matching algorithm in comparison to inter-reader variability (IRV) of matching lesions between scans of metastatic cancer patients. Approach. Forty pairs of longitudinal PET/CT and CT scans were collected and organized into four cohorts: lung cancers, head and neck cancers, lymphomas, and advanced cancers. Cases were also divided by cancer burden: low-burden (<10 lesions), intermediate-burden (10–29), and high-burden (30+). Two nuclear medicine physicians conducted independent reviews of each scan-pair and manually matched lesions. Matching differences between readers were assessed to quantify the IRV of lesion matching. The two readers met to form a consensus, which was considered a gold standard and compared against the output of an automated lesion-matching algorithm. IRV and performance of the automated method were quantified using precision, recall, F1-score, and the number of differences. Main results. The performance of the automated method did not differ significantly from IRV for any metric in any cohort (p > 0.05, Wilcoxon paired test). In high-burden cases, the F1-score (median [range]) was 0.89 [0.63, 1.00] between the automated method and reader consensus and 0.93 [0.72, 1.00] between readers. In low-burden cases, F1-scores were 1.00 [0.40, 1.00] and 1.00 [0.40, 1.00], for the automated method and IRV, respectively. Automated matching was significantly more efficient than either reader (p < 0.001). In high-burden cases, median matching time for the readers was 60 and 30 min, respectively, while automated matching took a median of 3.9 min Significance. The automated lesion-matching algorithm was successful in performing lesion matching, meeting the benchmark of IRV. Automated lesion matching can significantly expedite and improve the consistency of longitudinal lesion-matching.

A novel image registration-based dynamic photometric stereo method for online defect detection in aluminum alloy castings

The adoption of three-dimensional (3D) measurement technology for parts surface defect detection can improve inspection reliability. For online inspection purposes, 3D measurement technologies must possess the characteristics of high speed and high efficiency. The photometric stereo method is a potential 3D measurement method with high speed and low cost. However, the traditional photometric stereo method is unsuitable for dynamic scenes due to its initial design for static scenes. In this paper, we propose a novel dynamic photometric stereo method based on an image registration method. To achieve fast speed and high efficiency, we reduce the computational cost by automatically generating regions of interest (ROI). Additionally, we innovatively map the depth information (the surface normal vectors) to a mean curvature map of the surface and use it to detect defects, which combines the robustness of 3D methods and the fast speed of 2D methods. We designed experiments and the results showed that our method can detect defects on the surfaces of aluminum alloy castings accurately and robustly in an online manner. This paper also aims to reveal the importance of utilizing multidimensional information in high-speed online inspections.

Patient-Specific Auto-segmentation on Daily kVCT Images for Adaptive Radiation Therapy

This study explored deep-learning-based patient-specific auto-segmentation using transfer learning on daily RefleXion kilovoltage computed tomography (kVCT) images to facilitate adaptive radiation therapy, based on data from the first group of patients treated with the innovative RefleXion system. For head and neck (HaN) and pelvic cancers, a deep convolutional segmentation network was initially trained on a population data set that contained 67 and 56 patient cases, respectively. Then the pretrained population network was adapted to the specific RefleXion patient by fine-tuning the network weights with a transfer learning method. For each of the 6 collected RefleXion HaN cases and 4 pelvic cases, initial planning computed tomography (CT) scans and 5 to 26 sets of daily kVCT images were used for the patient-specific learning and evaluation separately. The performance of the patient-specific network was compared with the population network and the clinical rigid registration method and evaluated by the Dice similarity coefficient (DSC) with manual contours being the reference. The corresponding dosimetric effects resulting from different auto-segmentation and registration methods were also investigated. The proposed patient-specific network achieved mean DSC results of 0.88 for 3 HaN organs at risk (OARs) of interest and 0.90 for 8 pelvic target and OARs, outperforming the population network (0.70 and 0.63) and the registration method (0.72 and 0.72). The DSC of the patient-specific network gradually increased with the increment of longitudinal training cases and approached saturation with more than 6 training cases. Compared with using the registration contour, the target and OAR mean doses and dose-volume histograms obtained using the patient-specific auto-segmentation were closer to the results using the manual contour. Auto-segmentation of RefleXion kVCT images based on the patient-specific transfer learning could achieve higher accuracy, outperforming a common population network and clinical registration-based method. This approach shows promise in improving dose evaluation accuracy in RefleXion adaptive radiation therapy.

An End-to-end Pipeline for 3D Slide-wise Multi-stain Renal Pathology Registration.

Tissue examination and quantification in a 3D context on serial section whole slide images (WSIs) were labor-intensive and time-consuming tasks. Our previous study proposed a novel registration-based method (Map3D) to automatically align WSIs to the same physical space, reducing the human efforts of screening serial sections from WSIs. However, the registration performance of our Map3D method was only evaluated on single-stain WSIs with large-scale kidney tissue samples. In this paper, we provide a Docker for an end-to-end 3D slide-wise registration pipeline on needle biopsy serial sections in a multi-stain paradigm. The contribution of this study is three-fold: (1) We release a containerized Docker for an end-to-end multi-stain WSI registration. (2) We prove that the Map3D pipeline is capable of sectional registration from multi-stain WSI. (3) We verify that the Map3D pipeline can also be applied to needle biopsy tissue samples. The source code and the Docker have been made publicly available at https://github.com/hrlblab/Map3D.

Automatic organ completion with image stitching for personalized radiation dosimetry in CT examinations.

Computed tomography (CT) image-based patient-specific voxel-based dosimetry has difficulties complementing missing tissues for organs located partially inside or completely outside the image volume. Previous studies constructed patient-specific whole-body models by rescaling reference phantoms or extending regional CT images with manually adjusted phantoms. This study proposes a methodology for automatic organ completion of regional CT images for CT dosimetry using a stitching approach. Virtual clinical trials were performed by truncating whole-body CT images to generate virtual clinical chest and abdominopelvic CT images. Corresponding anchor images for each patient were selected according to sex and similarity of the axial length and water equivalent diameter of the virtual regional CT images. Automatic image stitching was performed by transformation initialization and iteration, while the stitched CT images and organ atlas were used in GPU-based Geant4 Monte Carlo simulations to generate a radiation dose map and absorbed organ dose. To evaluate the performance of the stitching model in radiation dosimetry, organ mass differences and Jaccard's coefficient of stitched and rescaled anchor images were calculated, and the radiation doses were compared among the corresponding values from the VirtualDose®, original whole-body CT, stitching model, regional CT, registration-based rescaling method, and WED-based rescaling method. The anatomical accuracy of stitched images was significantly improved. For organs partially inside the image volume, organ dose estimation from the stitching model could be more accurate than that reported in previous studies. The absolute differences in effective dose from the stitched images were 6.55% and 4.81% for chest and abdominopelvic CT scans, respectively. The proposed automatic stitching model partially complements organs inside or outside the CT scan range and provides more accurate anatomical representations for radiation dosimetry than traditional phantom rescaling methods.

A Novel Point Set Registration-Based Hand-Eye Calibration Method for Robot-Assisted Surgery.

Pedicle screw insertion with robot assistance dramatically improves surgical accuracy and safety when compared with manual implantation. In developing such a system, hand-eye calibration is an essential component that aims to determine the transformation between a position tracking and robot-arm systems. In this paper, we propose an effective hand-eye calibration method, namely registration-based hand-eye calibration (RHC), which estimates the calibration transformation via point set registration without the need to solve the AX=XB equation. Our hand-eye calibration method consists of tool-tip pivot calibrations in two-coordinate systems, in addition to paired-point matching, where the point pairs are generated via the steady movement of the robot arm in space. After calibration, our system allows for robot-assisted, image-guided pedicle screw insertion. Comprehensive experiments are conducted to verify the efficacy of the proposed hand-eye calibration method. A mean distance deviation of 0.70 mm and a mean angular deviation of 0.68° are achieved by our system when the proposed hand-eye calibration method is used. Further experiments on drilling trajectories are conducted on plastic vertebrae as well as pig vertebrae. A mean distance deviation of 1.01 mm and a mean angular deviation of 1.11° are observed when the drilled trajectories are compared with the planned trajectories on the pig vertebrae.

Systematic Study of Patient-Specific Organs at Risk Auto-Segmentation on Daily kVCT Images for Adaptive Head and Neck Radiotherapy

<h3>Purpose/Objective(s)</h3> A newly developed biology-guided radiotherapy (BgRT) system has been set up in our institution, which enables high-quality kVCT imaging for each treatment fraction. This study explored deep learning-based patient-specific auto-segmentation to facilitate adaptive radiotherapy, based on data of the first head and neck patient case treated with this new system. <h3>Materials/Methods</h3> The esophagus, larynx, and pharynx were selected as the organs at risk (OAR) for auto-segmentation analysis. A population network was first learned on a population dataset, which contains 67 different patient cases from conventional intensity-modulated radiotherapy (IMRT). Then the pre-trained population network was adapted to this specific patient using a transfer learning method based on the longitudinal data from the initial treatment planning and 17 sets of daily image guidance kVCT images. The selected OARs were contoured by a radiation oncologist on 18 sets of images as the ground truth. The performance of the patient-specific network was compared with the population network as well as the clinical rigid registration method. The corresponding dosimetric impacts resulting from different segmentation and registration methods were also investigated. <h3>Results</h3> The initial Dice similarity coefficient (DSC) results of the population network on the patient-specific evaluation set were 0.821, 0.537, 0.739 for esophagus, larynx, and pharynx respectively, and they were markedly improved to 0.887, 0.889, 0.850 with the proposed patient-specific network. These results also outperformed the results of 0.670, 0.792, 0.709 with the registration-based method in current clinical practice. The contouring accuracy of the patient-specific network gradually increased with the increase of longitudinal training cases and approached saturation with more than six training cases. The qualification result also shows the population network was adapted to the specific manual contouring style after the patient-specific learning. Discrepancies of the mean doses by using the manual contour and the patient-specific auto-segmentation result were -1.29%, -1.05%, -0.13% for the three OARs respectively, better than the differences of 4.80%, -6.56%, -1.84% using the registration contour. The OAR dose underestimation in some treatment fractions based on the registration contour was markedly improved when using the patient-specific auto-segmentation result. <h3>Conclusion</h3> Auto-segmentation of daily kVCT images was studied based on patient-specific learning to facilitate future adaptive radiotherapy. Compared with the common population network and the clinical registration method, the patient-specific network could achieve a much better contouring and dosimetric accuracy and thus is promising to become a powerful tool in adaptive radiotherapy applications.

Mapping of thoracic aorta growth rate on serial self-navigated 3D whole-heart magnetic resonance angiographies by image registration

Abstract Introduction Accurate and reproducible assessment of aortic diameters and their growth rate is of key importance for the management of patients with thoracic aortic aneurysms [1,2]. It has been recently shown that image registration permits the assessment of progressive aortic dilation on ECG-gated contrast-enhanced CT angiography, outperforming manual quantification and allowing for 3D aortic size and growth mapping [3]. However, exposure to radiation makes it convenient to limit the use of CT for serial follow-up, especially in young patients. Self-navigated 3D whole-heart CMR acquisitions provides excellent image quality overcoming these limitations [4]. Purpose To evaluate the accuracy and reproducibility of registration-based assessment of aortic dilation using self-navigated 3D whole-heart CMR acquisitions. Methods Fifteen patients with two self-navigated 3D whole-heart CMR images obtained at least 1 year apart were included. Aortic root and thoracic aorta diameters were measured by 2 independent observers both manually (multiplanar reconstruction) and with the registration-based technique. To perform registration-based assessment, the aorta was semi-automatically segmented and typical anatomical landmarks were placed by each observer at baseline [3]. Geometrical mapping between baseline and follow-up acquisitions was obtained using deformable image registration, and applied to the baseline aortic surface points to obtain their location at follow-up. Finally, aortic diameters and their growth rate were automatically measured and used to calculated 3D aortic dilation maps. Agreement between techniques and their inter-observer reproducibility were calculated. Results Patients age was 27.2±14.5 years and 40% were male. Mean follow-up duration was 2.7±1.6 years. Compared to manual assessment, the registration-based technique presented low bias and excellent agreement for aortic diameters (Table 1), and low bias and moderate agreement for growth rates both in the aortic root and the thoracic aorta (Table, Fig. 1A). The techniques presented similar inter-observer reproducibility in the assessment of aortic diameters (Table 1), while the registration-based method demonstrated much higher inter-observer reproducibility in the assessment of growth rates in the aortic root and the thoracic aorta (Table 1, Fig. 1A and B). Three-dimensional mapping of thoracic aortic diameters and growth was highly reproducible (mean regional ICC=0.90 for diameters; 0.82 for growth rate). Conclusion The assessment of the dilation rate of the thoracic aorta via registration of serial self-navigated 3D whole-heart CMR acquisitions is accurate and reproducible in the aortic root and the thoracic aorta. Thus, it allows to assess local aortic growth without the drawbacks of CT. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Instituto de Salud Carlos III and Ministerio de Ciencia e Innovaciόn (Spain)

Study Protocol COVER-ALL: Clinical Impact of a Volumetric Image Method for Confirming Tumour Coverage with Ablation on Patients with Malignant Liver Lesions.

This study aims to evaluate the intra-procedural use of a novel ablation confirmation (AC) method, consisting of biomechanical deformable image registration incorporating AI-based auto-segmentation, and its impact on tumor coverage by quantitative three-dimensional minimal ablative margin (MAM) CT-generated assessment. This single-center, randomized, phase II, intent-to-treat trial is enrolling 100 subjects with primary and secondary liver tumors (≤ 3 tumors, 1-5cmin diameter) undergoing microwave or radiofrequency ablation with a goal of achieving ≥ 5mm MAM. For the experimental arm, the proposed novel AC method is utilized for ablation applicator(s) placement verification and MAM assessment. For the control arm, the same variables are assessed by visual inspection and anatomical landmarks-based quantitative measurements aided by co-registration of pre- and post-ablation contrast-enhanced CT images. The primary objective is to evaluate the impact of the proposed AC method on the MAM. Secondary objectives are 2-year LTP-free survival, complication rates, quality of life, liver function, other oncological outcomes, and impact of AC method on procedure workflow. The COVER-ALL trial will provide information on the role of a biomechanical deformable image registration-based ablation confirmation method incorporating AI-based auto-segmentation for improving MAM, which might translate in improvements of liver ablation efficacy. The COVER-ALL trial aims to provide information on the role of a novel intra-procedural AC method for improving MAM, which might translate in improvements of liver ablation efficacy. ClinicalTrials.gov identifier: NCT04083378.

Estimation of undistorted images in brain echo-planar images with distortions using the conjugate gradient method with anatomical regularization.

Although echo-planar imaging (EPI) is widely used for diffusion magnetic resonance (MR) imaging, EPI images suffer from susceptibility-induced geometric distortions. We herein propose a new estimation method for undistorted EPI images using anatomical T1 -weighted images (T1 WIs) based on the physics of MR imaging. Our proposed method estimates the undistorted EPI image in the image domain while estimating the magnetic field inhomogeneity map using the conjugate gradient method with anatomical regularization. Our method synthesizes the distorted image to match the measured EPI image containing geometric distortions by alternately updating the undistorted EPI image and the magnetic field inhomogeneity map. We evaluated our proposed method and compared it with a nonrigid registration-based distortion correction method using simulated data and using real data. In the evaluation of the estimation of the magnetic field inhomogeneity map, we used the normalized root-mean-squared error (NRMSE) between the estimated results and the ground truth. In the evaluation of the estimation of undistorted images, we used mutual information (MI) between the undistorted EPI image and the anatomical T1 WI. Using the simulated data, the means and standard deviations of the NRMSE values in the nonrigid registration-based method and proposed method were 1.29±0.63 and 0.64±0.30, respectively. The MI values in the proposed method were larger than those in the nonrigid registration-based method in all evaluated slices. For the real data, the proposed method improved the distortion, and the MI values in the proposed method were larger than those in the nonrigid registration-based method. In the estimation of the magnetic field inhomogeneity map, the NRMSE values in our method were smaller than those in the nonrigid registration-based method. We demonstrated that our proposed method can estimate the regions with compressed distortions that are not well represented by the nonrigid registration-based methods. The results suggest that the proposed method could be useful in analyses combining EPI images with T1 WIs.