Non-rigid Registration Framework Research Articles

In-silico heart model phantom to validate cardiac strain imaging

The quantification of cardiac strains as structural indices of cardiac function has a growing prevalence in clinical diagnosis. However, the highly heterogeneous four-dimensional (4D) cardiac motion challenges accurate “regional” strain quantification and leads to sizable differences in the estimated strains depending on the imaging modality and post-processing algorithm, limiting the translational potential of strains as incremental biomarkers of cardiac dysfunction. There remains a crucial need for a feasible benchmark that successfully replicates complex 4D cardiac kinematics to determine the reliability of strain calculation algorithms. In this study, we propose an in-silico heart phantom derived from finite element (FE) simulations to validate the quantification of 4D regional strains. First, as a proof-of-concept exercise, we created synthetic magnetic resonance (MR) images for a hollow thick-walled cylinder under pure torsion with an exact solution and demonstrated that “ground-truth” values can be recovered for the twist angle, which is also a key kinematic index in the heart. Next, we used mouse-specific FE simulations of cardiac kinematics to synthesize dynamic MR images by sampling various sectional planes of the left ventricle (LV). Strains were calculated using our recently developed non-rigid image registration (NRIR) framework in both problems. Moreover, we studied the effects of image quality on distorting regional strain calculations by conducting in-silico experiments for various LV configurations. Our studies offer a rigorous and feasible tool to standardize regional strain calculations to improve their clinical impact as incremental biomarkers.

In-silico heart model phantom to validate cardiac strain imaging.

The quantification of cardiac strains as structural indices of cardiac function has a growing prevalence in clinical diagnosis. However, the highly heterogeneous four-dimensional (4D) cardiac motion challenges accurate "regional" strain quantification and leads to sizable differences in the estimated strains depending on the imaging modality and post-processing algorithm, limiting the translational potential of strains as incremental biomarkers of cardiac dysfunction. There remains a crucial need for a feasible benchmark that successfully replicates complex 4D cardiac kinematics to determine the reliability of strain calculation algorithms. In this study, we propose an in-silico heart phantom derived from finite element (FE) simulations to validate the quantification of 4D regional strains. First, as a proof-of-concept exercise, we created synthetic magnetic resonance (MR) images for a hollow thick-walled cylinder under pure torsion with an exact solution and demonstrated that "ground-truth" values can be recovered for the twist angle, which is also a key kinematic index in the heart. Next, we used mouse-specific FE simulations of cardiac kinematics to synthesize dynamic MR images by sampling various sectional planes of the left ventricle (LV). Strains were calculated using our recently developed non-rigid image registration (NRIR) framework in both problems. Moreover, we studied the effects of image quality on distorting regional strain calculations by conducting in-silico experiments for various LV configurations. Our studies offer a rigorous and feasible tool to standardize regional strain calculations to improve their clinical impact as incremental biomarkers.

SUGAR: Spherical ultrafast graph attention framework for cortical surface registration

Cortical surface registration plays a crucial role in aligning cortical functional and anatomical features across individuals. However, conventional registration algorithms are computationally inefficient. Recently, learning-based registration algorithms have emerged as a promising solution, significantly improving processing efficiency. Nonetheless, there remains a gap in the development of a learning-based method that exceeds the state-of-the-art conventional methods simultaneously in computational efficiency, registration accuracy, and distortion control, despite the theoretically greater representational capabilities of deep learning approaches. To address the challenge, we present SUGAR, a unified unsupervised deep-learning framework for both rigid and non-rigid registration. SUGAR incorporates a U-Net-based spherical graph attention network and leverages the Euler angle representation for deformation. In addition to the similarity loss, we introduce fold and multiple distortion losses to preserve topology and minimize various types of distortions. Furthermore, we propose a data augmentation strategy specifically tailored for spherical surface registration to enhance the registration performance. Through extensive evaluation involving over 10,000 scans from 7 diverse datasets, we showed that our framework exhibits comparable or superior registration performance in accuracy, distortion, and test-retest reliability compared to conventional and learning-based methods. Additionally, SUGAR achieves remarkable sub-second processing times, offering a notable speed-up of approximately 12,000 times in registering 9,000 subjects from the UK Biobank dataset in just 32 min. This combination of high registration performance and accelerated processing time may greatly benefit large-scale neuroimaging studies.

SPaM: soft patch matching for non-rigid pointcloud registration.

3d reconstruction of deformable objects in dynamic scenes forms the fundamental basis of many robotic applications. Existing mesh-based approaches compromise registration accuracy, and lose important details due to interpolation and smoothing. Additionally, existing non-rigid registration techniques struggle with unindexed points and disconnected manifolds. We propose a novel non-rigid registration framework for raw, unstructured, deformable point clouds purely based on geometric features. The global non-rigid deformation of an object is formulated as an aggregation of locally rigid transformations. The concept of locality is embodied in soft patches described by geometrical properties based on SHOT descriptor and its neighborhood. By considering the confidence score of pairwise association between soft patches of two scans (not necessarily consecutive), a computed similarity matrix serves as the seed to grow a correspondence graph which leverages rigidity terms defined in As-Rigid-As-Possible for pruning and optimization. Experiments on simulated and publicly available datasets demonstrate the capability of the proposed approach to cope with large deformations blended with numerous missing parts in the scan process.

Facial optical flow estimation via neural non-rigid registration

Optical flow estimation in human facial video, which provides 2D correspondences between adjacent frames, is a fundamental pre-processing step for many applications, like facial expression capture and recognition. However, it is quite challenging as human facial images contain large areas of similar textures, rich expressions, and large rotations. These characteristics also result in the scarcity of large, annotated real-world datasets. We propose a robust and accurate method to learn facial optical flow in a self-supervised manner. Specifically, we utilize various shape priors, including face depth, landmarks, and parsing, to guide the self-supervised learning task via a differentiable nonrigid registration framework. Extensive experiments demonstrate that our method achieves remarkable improvements for facial optical flow estimation in the presence of significant expressions and large rotations.

PlantMove: A tool for quantifying motion fields of plant movements from point cloud time series

• A progressive coarse-to-fine nonrigid point cloud registration framework for movement quantification in plants. • PlantMove accurately estimated point-wise 3D motion fields of movements in plants. • PlantMove is capable of processing point cloud time series recorded over hours to years. The mechanisms involved in organ motions are central to our understanding of how plants develop and respond to environmental stimuli such as light quality, gravity, and water availability throughout time. Recent studies have shown that motions in plants such as circadian rhythms and growth patterns, can be recorded and quantified from time series of terrestrial laser scans (TLS). However, most works monitored the changes of certain functional traits such as height and volume to detect and analyze structural dynamics. A generic method for retrieving fine-scale three-dimensional (3D) motion fields of plant structural movements is still missing. We present PlantMove , a new fully automatic tool to quantify 3D motion fields of plant structural movements with varied magnitudes using TLS point clouds acquired over different time periods. The method uses spatio-temporal point cloud registration embedded in a progressive and coarse-to-fine framework, enabling an efficient processing of large datasets with complex structures. PlantMove was first demonstrated on synthetic plant datasets, displaying millimeter to centimeter level accuracy of retrieved motion fields. In addition, PlantMove was used to assess circadian rhythms on a birch tree from TLS data acquired over the course of one night with about one-hour time intervals, and growth patterns on an English oak from a four-year TLS survey. PlantMove can help to better monitor plant phenotypic plasticity with fine level of details, and can contribute to improve our understanding in plant dynamics across various spatial and temporal scales.

A robust nonrigid point set registration framework based on global and intrinsic topological constraints

The problem of registering nonrigid point sets, with the aim of estimating the correspondences and learning the transformation between two given sets of points, often arises in computer vision tasks. This paper proposes a novel method for performing nonrigid point set registration on data with various types of degradation, in which the registration problem is formulated as a Gaussian mixture model (GMM)-based density estimation problem. Specifically, two complementary constraints are jointly considered for optimization in a GMM probabilistic framework. The first is a thin-plate spline-based regularization constraint that maintains global spatial motion consistency, and the second is a spectral graph-based regularization constraint that preserves the intrinsic structure of a point set. Moreover, the correspondences and the transformation are alternately optimized using the expectation maximization algorithm to obtain a closed-form solution. We first utilize local descriptors to construct the initial correspondences and then estimate the underlying transformation under the GMM-based framework. Experimental results on contour images and real images show the effectiveness and robustness of the proposed method.

Biomechanically constrained non-rigid MR-TRUS prostate registration using deep learning based 3D point cloud matching.

A non-rigid MR-TRUS image registration framework is proposed for prostate interventions. The registration framework consists of a convolutional neural networks (CNN) for MR prostate segmentation, a CNN for TRUS prostate segmentation and a point-cloud based network for rapid 3D point cloud matching. Volumetric prostate point clouds were generated from the segmented prostate masks using tetrahedron meshing. The point cloud matching network was trained using deformation field that was generated by finite element analysis. Therefore, the network implicitly models the underlying biomechanical constraint when performing point cloud matching. A total of 50 patients' datasets were used for the network training and testing. Alignment of prostate shapes after registration was evaluated using three metrics including Dice similarity coefficient (DSC), mean surface distance (MSD) and Hausdorff distance (HD). Internal point-to-point registration accuracy was assessed using target registration error (TRE). Jacobian determinant and strain tensors of the predicted deformation field were calculated to analyze the physical fidelity of the deformation field. On average, the mean and standard deviation were 0.94±0.02, 0.90±0.23 mm, 2.96±1.00 mm and 1.57±0.77 mm for DSC, MSD, HD and TRE, respectively. Robustness of our method to point cloud noise was evaluated by adding different levels of noise to the query point clouds. Our results demonstrated that the proposed method could rapidly perform MR-TRUS image registration with good registration accuracy and robustness.

Motion correction of respiratory-gated PET images using deep learning based image registration framework

Artifacts caused by patient breathing and movement during PET data acquisition affect image quality. Respiratory gating is commonly used to gate the list-mode PET data into multiple bins over a respiratory cycle. Non-rigid registration of respiratory-gated PET images can reduce motion artifacts and preserve count statistics, but it is time consuming. In this work, we propose an unsupervised non-rigid image registration framework using deep learning for motion correction. Our network uses a differentiable spatial transformer layer to warp the moving image to the fixed image and uses a stacked structure for deformation field refinement. Estimated deformation fields were incorporated into an iterative image reconstruction algorithm to perform motion compensated PET image reconstruction. We validated the proposed method using simulation and clinical data and implemented an iterative image registration approach for comparison. Motion compensated reconstructions were compared with ungated images. Our simulation study showed that the motion compensated methods can generate images with sharp boundaries and reveal more details in the heart region compared with the ungated image. The resulting normalized root mean square error (NRMS) was 24.3 ± 1.7% for the deep learning based motion correction, 31.1 ± 1.4% for the iterative registration based motion correction, and 41.9 ± 2.0% for ungated reconstruction. The proposed deep learning based motion correction reduced the bias compared with the ungated image without increasing the noise level and outperformed the iterative registration based method. In the real data study, both motion compensated images provided higher lesion contrast and sharper liver boundaries than the ungated image and had lower noise than the reference gate image. The contrast of the proposed method based on the deep neural network was higher than the ungated image and iterative registration method at any matched noise level.

Non-rigid retinal image registration using an unsupervised structure-driven regression network

Retinal image registration is clinically significant to help clinicians obtain more complete details of the retinal structure by correlating the properties of the retina. However, existing methods suffer from great challenges due to time-consuming optimization and lack of ground truth. In this paper, we propose an unsupervised learning framework for non-rigid retinal image registration, which directly learns the mapping from a retinal image pair to their corresponding deformation field without any supervision such as ground truth registration fields. Specifically, we formulate the complex mapping as a parameterized deformation function, which can be represented and optimized by a deep neural network. Furthermore, the Structure-Driven Regression Network (SDRN) framework is applied to compute the multi-scale similarity combined with contextual structures (e.g., vessel distribution, optic disk appearance, and edge information) to guide the end-to-end learning procedure more effectively with unlabeled data. Given a new pair of images, our method can quickly register images by directly evaluating the parametric function using the learned parameters, which runs faster than traditional registration algorithms. Experimental results, performed on the public challenging dataset (FIRE), show that our method achieves an average Dice similarity coefficient (DSC) of 0.753 with short execution times (0.021 s), which is more accurate and robust than existing approaches and promises to significantly speed up retinal image analysis and processing.

Nonrigid registration for tracking incompressible soft tissues with sliding motion.

Respiration causes the deformation and sliding motion of the soft tissues, and affects the accuracy of the assessment of minimally invasive abdominal surgery. Nonrigid registration is used to eliminate the effects of respiration for the assessment. Because the soft tissues with high water content are volume preserving during deformation, incompressibility has to be considered when tracking soft tissues for nonrigid registration. The purpose of the study was to develop an incompressible nonrigid registration for tracking deformable soft tissues with sliding motion. The nonrigid registration framework proposed in the present study includes two main steps: (a) The solution in the subspace of diffeomorphisms is searched and encoded to stationary velocity field in the log domain. (b) The divergence-free component and harmonic remainder are extracted by Fourier-based Helmholtz-Hodge decomposition (FHHD) and further integrated by an adaptive weight to simultaneously retain the incompressibility of deformation and compensate the sliding motion. The method was evaluated on 11 groups of synthetic datasets and five groups of clinical images. Registration accuracy is evaluated by using four quantitative measures, including mean surface distance (MSD), Hausdorff distance (HD), mean corresponding distance (MCD), and Dice similarity coefficient (DSC). Incompressibility is evaluated by using two quantitative measures, including relative volume change (RVC) and Jacobian determinant (J). Compared with three state-of-the-art nonrigid registration methods, the proposed method shows an advantage in handling the incompressible deformation of images with large sliding motion. The lowest (MSD, 0.631mm), (HD, 6.000mm), and (MCD, 3.555mm) and the highest (DSC, 0.970) are obtained proving the high registration accuracy with sliding motion compensation of the proposed method. The (RVC, 0.006) and Jacobian determinant (J, 1.008±0.070) are nearly close to 0 and 1, respectively, showing the strong incompressibility of the proposed method. The proposed method improves registration accuracy in nearly all cases, which maintains the incompressibility of tissue transformation while simultaneously compensating the sliding motion on clinical datasets. The proposed method improves the registration accuracy of incompressible tissues when dealing with large sliding motion, and thus has the potential to improve current minimally invasive abdominal surgery.

Generalised coherent point drift for group-wise multi-dimensional analysis of diffusion brain MRI data.

A probabilistic framework for registering generalised point sets comprising multiple voxel-wise data features such as positions, orientations and scalar-valued quantities, is proposed. It is employed for the analysis of magnetic resonance diffusion tensor image (DTI)-derived quantities, such as fractional anisotropy (FA) and fibre orientation, across multiple subjects. A hybrid Student's t-Watson-Gaussian mixture model-based non-rigid registration framework is formulated for the joint registration and clustering of voxel-wise DTI-derived data, acquired from multiple subjects. The proposed approach jointly estimates the non-rigid transformations necessary to register an unbiased mean template (represented as a 7-dimensional hybrid point set comprising spatial positions, fibre orientations and FA values) to white matter regions of interest (ROIs), and approximates the joint distribution of voxel spatial positions, their associated principal diffusion axes, and FA. Specific white matter ROIs, namely, the corpus callosum and cingulum, are analysed across healthy control (HC) subjects (K = 20 samples) and patients diagnosed with mild cognitive impairment (MCI) (K = 20 samples) or Alzheimer's disease (AD) (K = 20 samples) using the proposed framework, facilitating inter-group comparisons of FA and fibre orientations. Group-wise analyses of the latter is not afforded by conventional approaches such as tract-based spatial statistics (TBSS) and voxel-based morphometry (VBM).

Robust motion correction for cardiac T1 and ECV mapping using a T1 relaxation model approach.

T1 and ECV mapping are quantitative methods for myocardial tissue characterization using cardiac MRI, and are highly relevant for the diagnosis of diffuse myocardial diseases. Since the maps are calculated pixel-by-pixel from a set of MRI images with different T1-weighting, it is critical to assure exact spatial correspondence between these images. However, in practice, different sources of motion e.g. cardiac motion, respiratory motion or patient motion, hamper accurate T1 and ECV calculation such that retrospective motion correction is required. We propose a new robust non-rigid registration framework combining a data-driven initialization with a model-based registration approach, which uses a model for T1 relaxation to avoid direct registration of images with highly varying contrast. The registration between native T1 and enhanced T1 to obtain a motion free ECV map is also calculated using information from T1 model-fitting. The method was validated on three datasets recorded with two substantially different acquisition protocols (MOLLI (dataset 1 (n=15) and dataset 2 (n=29)) and STONE (dataset 3 (n = 210))), one in breath-hold condition and one free-breathing. The average Dice coefficient increased from 72.6 ± 12.1% to 82.3 ± 7.4% (P < 0.05) and mean boundary error decreased from 2.91 ± 1.51mm to 1.62 ± 0.80mm (P < 0.05) for motion correction in a single T1-weighted image sequence (3 datasets) while average Dice coefficient increased from 63.4 ± 22.5% to 79.2 ± 8.5% (P < 0.05) and mean boundary error decreased from 3.26 ± 2.64mm to 1.77 ± 0.86mm (P < 0.05) between native and enhanced sequences (dataset 1 and 2). Overall, the native T1 SD error decreased from 67.32 ± 32.57ms to 58.11 ± 21.59ms (P < 0.05), enhanced SD error from 30.15 ± 25ms to 22.74 ± 8.94ms (P < 0.05) and ECV SD error from 10.08 ± 9.59% to 5.42 ± 3.21% (P < 0.05) (dataset 1 and 2).

The same modality medical image registration with large deformation and clinical application based on adaptive diffeomorphic multi-resolution demons

BackgroundDiffeomorphic demons can not only guarantee smooth and reversible deformation, but also avoid unreasonable deformation. However, the number of iterations which has great influence on the registration result needs to be set manually.MethodsThis study proposed a novel method to exploit the adaptive diffeomorphic multi-resolution demons algorithm to the non-rigid registration of the same modality medical images with large deformation. Firstly an optimized non-rigid registration framework and the diffeomorphism strategy were used, and then a similarity energy function based on the grey value was designed as registration metric, lastly termination condition was set based on the variation of this metric and iterations can be stopped adaptively. Quantitative analyses based on the registration evaluation indexes were conducted to prove the validity of this method.ResultsRegistration result of synthetic image and the same modality MRI and CT image was compared with those obtained by other demons algorithms. Quantitative analyses demonstrated the proposed method’s superiority. Medical image with large deformation was produced by rotational distortion and extrusion transform, and the same modality image registration with large deformation was performed successfully. Quantitative analyses showed that the registration evaluation indexes remained stable with an increase in transform strength. This method can be also applied to pulmonary medical image registration with large deformation successfully, and it showed the clinical application value. The influence of different driving forces and parameters on the registration result was analysed, and the result demonstrated that the proposed method is effective and robust.ConclusionsThis method can solve the non-rigid registration problem of the same modality medical image with large deformation showing promise for diagnostic pulmonary imaging applications.

Dynamic Non-Rigid Objects Reconstruction with a Single RGB-D Sensor.

This paper deals with the 3D reconstruction problem for dynamic non-rigid objects with a single RGB-D sensor. It is a challenging task as we consider the almost inevitable accumulation error issue in some previous sequential fusion methods and also the possible failure of surface tracking in a long sequence. Therefore, we propose a global non-rigid registration framework and tackle the drifting problem via an explicit loop closure. Our novel scheme starts with a fusion step to get multiple partial scans from the input sequence, followed by a pairwise non-rigid registration and loop detection step to obtain correspondences between neighboring partial pieces and those pieces that form a loop. Then, we perform a global registration procedure to align all those pieces together into a consistent canonical space as guided by those matches that we have established. Finally, our proposed model-update step helps fixing potential misalignments that still exist after the global registration. Both geometric and appearance constraints are enforced during our alignment; therefore, we are able to get the recovered model with accurate geometry as well as high fidelity color maps for the mesh. Experiments on both synthetic and various real datasets have demonstrated the capability of our approach to reconstruct complete and watertight deformable objects.

Nonrigid registration of multimodal medical images based on hybrid model

ABSTRACT Background and Objectives: Multimodal image registration is a crucial step in prostate cancer radiation therapy scheme. However, it can be challenging due to the obvious appearance difference between computed tomography (CT) and magnetic resonance imaging (MRI) and unavoidable organ motion. Accordingly, a nonrigid registration framework for precisely registering multimodal prostate images is proposed in this paper. Materials and Methods: In this work, multimodal prostate image registration between CT and MRI is achieved using a hybrid model that integrates multiresolution strategy and Demons algorithm. Furthermore, to precisely describe the deformation of prostate, B-spline-based registration is utilized to refine the initial registration result of multiresolution Demons algorithm. Results: To evaluate our method, experiments on clinical prostate data sets of nine participants and comparison with the conventional Demons algorithm are conducted. Experimental results demonstrate that the proposed registration method outperforms the Demons algorithm by a large margin in terms of mutual information and correlation coefficient. Conclusions: These results show that our method outperforms the Demons algorithm and can achieve excellent performance on multimodal prostate images even the appearances of prostate change significantly. In addition, the results demonstrate that the proposed method can help to localize the prostate accurately, which is feasible in clinical.

Semiautomated registration of pre- and intraoperative CT for image-guided percutaneous liver tumor ablation interventions.

In CT-guided liver tumor ablation interventions, registration of a preoperative contrast-enhanced CT image to the intraoperative CT image is hypothesized to improve guidance. This is a highly challenging registration task due to differences in patient poses and large deformations, and therefore high registration errors are expected. In this study, our objective is to develop a method that enables users to locally improve the registration where the registration fails, with minimal user interaction. The method is based on a conventional nonrigid intensity-based registration framework, extended with a novel point-to-surface penalty. The point-to-surface penalty serves to improve the alignment of the liver boundary, while requiring minimal user interaction during the intervention: annotating some points on the liver surface at those regions where the conventional registration seems inaccurate. The method is evaluated on 18 clinical datasets. It improves registration accuracy compared with the conventional nonrigid registration in terms of average surface distance (from 2.75 to 2.05mm) and target registration error (from 6.92 to 5.8mm). In this study, we introduce a semiautomated registration algorithm that improves the accuracy of image registration.

Robust universal nonrigid motion correction framework for first-pass cardiac MR perfusion imaging.

To present and assess an automatic nonrigid image registration framework that compensates motion in cardiac magnetic resonance imaging (MRI) perfusion series and auxiliary images acquired under a wide range of conditions to facilitate myocardial perfusion quantification. Our framework combines discrete feature matching for large displacement estimation with a dense variational optical flow formulation in a multithreaded architecture. This framework was evaluated on 291 clinical subjects to register 1.5T and 3.0T steady-state free-precession (FISP) and fast low-angle shot (FLASH) dynamic contrast myocardial perfusion images, arterial input function (AIF) images, and proton density (PD)-weighted images acquired under breath-hold (BH) and free-breath (FB) settings. Our method significantly improved frame-to-frame appearance consistency compared to raw series, expressed in correlation coefficient (R2 = 0.996 ± 3.735E-3 vs. 0.978 ± 2.024E-2, P < 0.0001) and mutual information (3.823 ± 4.098E-1 vs. 2.967 ± 4.697E-1, P < 0.0001). It is applicable to both BH (R2 = 0.998 ± 3.217E-3 vs. 0.990 ± 7.527E-3) and FB (R2 = 0.995 ± 3.410E-3 vs. 0.968 ± 2.257E-3) paradigms as well as FISP and FLASH sequences. The method registers PD images to perfusion T1 series (9.70% max increase in R2 vs. no registration, P < 0.001) and also corrects motion in low-resolution AIF series (R2 = 0.987 ± 1.180E-2 vs. 0.964 ± 3.860E-2, P < 0.001). Finally, we showed the myocardial perfusion contrast dynamic was preserved in the motion-corrected images compared to the raw series (R2 = 0.995 ± 6.420E-3). The critical step of motion correction prior to pixel-wise cardiac MR perfusion quantification can be performed with the proposed universal system. It is applicable to a wide range of perfusion series and auxiliary images with different acquisition settings. 3 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2017;46:1060-1072.

Lung tumor boundary tracking in MRI with moving mesh correspondences for adaptive radio therapy.

Delineation of lung tumor regions from magnetic resonance imaging (MRI) poses many difficulties due to MR signal similarities of the region of interest and surrounding area as well as the influence of respiration. However, accurate segmentation of the tumor region is of utmost importance in planning a radiation therapy since a small error can result in some healthy tissues to receive excessive radiation. This study presents a semi-automated method to delineate lung tumor regions from a sequence of MRIs. The proposed method uses a non-rigid image registration framework to propagate the boundaries of the tumor region in MRI acquired during a radiation treatment stage, given manual segmentation on frames acquired during pretreatment stage. We investigate two approaches: 1) the first one utilizes manual segmentation of the first frame during the pretreatment stage; and 2) the second one utilizes manual segmentation of all the frames during the pretreatment stage. We evaluated the proposed approaches over a sequence of 400 images acquired from 4 patients. The proposed method based on the utilization of all the frames yielded a Dice score of 0.90 ± 0.04 and a Hausdorff distance of 1.17 ± 0.35 pixels (2.83 ± 0.79 mm) in comparison to expert manual segmentation.

Registration of Pre- and Postresection Ultrasound Volumes With Noncorresponding Regions in Neurosurgery.

Brain tissue deforms significantly after opening the dura and during tumor resection, invalidating preoperative imaging data. Ultrasound is a popular imaging modality for providing the neurosurgeon with real-time updated images of brain tissue. Interpretation of postresection ultrasound images is difficult due to large brain shift and tissue resection. Furthermore, several factors degrade the quality of postresection ultrasound images such as the strong reflection of waves at the interface of saline water and brain tissue in resection cavities, air bubbles, and the application of blood-clotting agents around the edges of resection. Image registration allows the comparison of postresection ultrasound images with higher quality preresection images, assists in interpretation of postresection images and may help identify residual tumor, and, as such, is of significant clinical importance. In this paper, we propose a nonrigid symmetric registration (NSR) framework for accurate alignment of pre- and postresection volumetric ultrasound images in near real time. We first formulate registration as minimization of a regularized cost function and analytically derive its derivative to efficiently optimize the cost function. An outlier detection algorithm is proposed and utilized in this framework to identify noncorresponding regions (outliers) and therefore improve the robustness and accuracy of registration. We use an efficient second-order minimization method for fast and robust optimization. Furthermore, we exploit a symmetric and inverse-consistent method to generate realistic deformation fields. The results show that NSR significantly improves the quality of the alignment between pre- and postresection ultrasound images.