Non-rigid Image Registration Method Research Articles

Deformable image registration based on elastodynamics

This paper presents a novel method for 2D inter-subject non-rigid image registration. It is motivated by the ideas derived from elastodynamics which is the subclass of linear elastic theory. We propose to model the non-rigid deformations as elastic waves which are characterized by elastodynamics wave equation. Our registration method is formulated in a multi-resolution manner such that it is able to recover significant deformations. The proposed scheme recovers local (non-linear) as well as global deformations. The results of image registration by the proposed technique were validated via similarity measures for real MR brain images, BrainWeb dataset and MR prostate images. We have also used overlap measures (Jaccard distance, Dice coefficient and Overlap coefficient) over the segmented deep-brain structures including: lateral and third ventricles, putamen and caudate nucleus for real image dataset to further validate our proposed registration scheme. The proposed scheme was also compared with demons, Level set and free-form deformations (cubic B-spline) algorithms implemented in ITK toolkit and symmetric normalization method available in ANTs software package. Our proposed algorithm shows marked improvement of the inter-subject non-rigid registration, both qualitatively and quantitatively, over the four above-mentioned methods. This comparison was performed on all the three types of datasets mentioned above. 2D synthetic experiments comprising of Patch-`C', Square---Rectangle and Circle-`C' were also performed with our algorithm and compared with other four methods. Both qualitative and quantitative results show that our method performs better than the other four methods. Results suggest that our proposed algorithm has improved accuracy over lemons, level set and free-form deformations (ITK implemented) and symmetric normalization method (ANTs based), tested over two types of brain and one prostate MRI. The commonly used synthetic experiments also suggest the superiority of our proposed scheme.

Improved dosimetry for targeted radionuclide therapy using nonrigid registration on sequential SPECT images.

Voxel-level and patient-specific 3D dosimetry for targeted radionuclide therapy (TRT) typically involves serial nuclear medicine scans. Misalignment of the images can result in reduced dosimetric accuracy. Since the scans are typically performed over a period of several days, there will be patient movement between scans and possible nonrigid organ deformation. This work aims to implement and evaluate the use of nonrigid image registration on a series of quantitative SPECT (QSPECT) images for TRT dosimetry. A population of 4D extended cardiac torso phantoms, comprised of three In-111 Zevalin biokinetics models and three anatomical variations, was generated based on the patient data. The authors simulated QSPECT acquisitions at five time points. At each time point, individual organ and whole-body deformation between scans were modeled by translating/rotating organs and the body up to 5°/voxels, keeping ≤5% difference in organ volume. An analytical projector was used to generate realistic noisy projections for a medium energy general purpose collimator. Projections were reconstructed using OS-EM algorithm with geometric collimator detector response, attenuation, and scatter corrections. The QSPECT images were registered using organ-based nonrigid image registration method. The cumulative activity in each voxel was obtained by integrating the activity over time. Dose distribution images were obtained by convolving the cumulative activity images with a Y-90 dose kernel. Dose volume histograms (DVHs) for organs-of-interest were analyzed. After nonrigid registration, the mean differences in organ doses compared to the case without misalignment were improved from (-15.50 ± 5.59)% to (-2.12 ± 1.05)% and (-7.28 ± 2.30)% to (-0.23 ± 0.71)% for the spleen and liver, respectively. For all organs, the cumulative DVHs showed improvement after nonrigid registration and the normalized absolute error of differential DVHs ranged from 6.79% to 22.70% for liver and 26.00% to 39.70% for spleen with different segmentation methods. These results demonstrated that nonrigid registration of sequential QSPECT images is feasible for TRT and improves the accuracy of 3D dosimetry.

A Combination of the Total Variation Filter and a Fourth-Order Filter for Image Registration

We introduce a novel method for nonrigid image registration which combines the total variation filter and a fourth-order filter. We decompose the deformation field into two components, that is, a piecewise constant component and a smooth component. The total variation filter is used for the first component and the fourth-order filter is used for the second one. Then, we present a new PDE-based image registration model suitable for both smooth and nonsmooth deformation problem. Meanwhile, the local-global similarity measure is used in our method to improve the accuracy and robustness for image matching. By applying the split Bregman algorithm and dual algorithm, we present a fast and stable numerical scheme. The numerical experiments and comparisons on both synthetic images and real images demonstrate the effectiveness of our method in nonrigid image registration.

Non-rigid registration of serial dedicated breast CT, longitudinal dedicated breast CT and PET/CT images using the diffeomorphic demons method

Rationale and objectivesDedicated breast CT and PET/CT scanners provide detailed 3D anatomical and functional imaging data sets and are currently being investigated for applications in breast cancer management such as diagnosis, monitoring response to therapy and radiation therapy planning. Our objective was to evaluate the performance of the diffeomorphic demons (DD) non-rigid image registration method to spatially align 3D serial (pre- and post-contrast) dedicated breast computed tomography (CT), and longitudinally-acquired dedicated 3D breast CT and positron emission tomography (PET)/CT images. MethodsThe algorithmic parameters of the DD method were optimized for the alignment of dedicated breast CT images using training data and fixed. The performance of the method for image alignment was quantitatively evaluated using three separate data sets; (1) serial breast CT pre- and post-contrast images of 20 women, (2) breast CT images of 20 women acquired before and after repositioning the subject on the scanner, and (3) dedicated breast PET/CT images of 7 women undergoing neo-adjuvant chemotherapy acquired pre-treatment and after 1 cycle of therapy. ResultsThe DD registration method outperformed no registration (p < 0.001) and conventional affine registration (p ≤ 0.002) for serial and longitudinal breast CT and PET/CT image alignment. In spite of the large size of the imaging data, the computational cost of the DD method was found to be reasonable (3–5 min). ConclusionsCo-registration of dedicated breast CT and PET/CT images can be performed rapidly and reliably using the DD method. This is the first study evaluating the DD registration method for the alignment of dedicated breast CT and PET/CT images.

Long-term time-lapse multimodal intravital imaging of regeneration and bone-marrow-derived cell dynamics in skin

A major challenge for translating cell-based therapies is understanding the dynamics of cells and cell populations in complex in vivo environments. Intravital microscopy has shown great promise for directly visualizing cell behavior in vivo. However, current methods are limited to relatively short imaging times (hours), by ways to track cell and cell population dynamics over extended time-lapse periods (days to weeks to months), and by relatively few imaging contrast mechanisms that persist over extended investigations. We present technology to visualize and quantify complex, multifaceted dynamic changes in natural deformable skin over long time periods using novel multimodal imaging and a non-rigid image registration method. These are demonstrated in green fluorescent protein (GFP) bone marrow (BM) transplanted mice to study dynamic skin regeneration. This technology provides a novel perspective for studying dynamic biological processes and will enable future studies of stem, immune, and tumor cell biology in vivo.

Two Phase Non-Rigid Multi-Modal Image Registration Using Weber Local Descriptor-Based Similarity Metrics and Normalized Mutual Information

Non-rigid multi-modal image registration plays an important role in medical image processing and analysis. Existing image registration methods based on similarity metrics such as mutual information (MI) and sum of squared differences (SSD) cannot achieve either high registration accuracy or high registration efficiency. To address this problem, we propose a novel two phase non-rigid multi-modal image registration method by combining Weber local descriptor (WLD) based similarity metrics with the normalized mutual information (NMI) using the diffeomorphic free-form deformation (FFD) model. The first phase aims at recovering the large deformation component using the WLD based non-local SSD (wldNSSD) or weighted structural similarity (wldWSSIM). Based on the output of the former phase, the second phase is focused on getting accurate transformation parameters related to the small deformation using the NMI. Extensive experiments on T1, T2 and PD weighted MR images demonstrate that the proposed wldNSSD-NMI or wldWSSIM-NMI method outperforms the registration methods based on the NMI, the conditional mutual information (CMI), the SSD on entropy images (ESSD) and the ESSD-NMI in terms of registration accuracy and computation efficiency.

A non-rigid cardiac image registration method based on an optical flow model

According to non-rigid medical image registration, new method of classification registration is proposed. First, Feature points are extracted based on SIFT (Scale Invariant Feature Transform) from reference images and floating images to match feature points. And the coarse registration is performed using the least square method. Then the precise registration is achieved using the optical flow model algorithm. SIFT algorithm is based on local image features that are with good scale, rotation and illumination invariance. Optical flow algorithm does not extract features and use the image gray information directly, and its registration speed is faster. The both algorithms are complementary. SIFT algorithm is used for improving the convergence speed of optical flow algorithm, and optical flow algorithm makes the registration result more accurate. The experimental results prove that the algorithm can improve the accuracy of the non-rigid medical image registration and enhance the convergence speed. Therefore, the algorithm has some advantages in the image registration.

An Image Registration Method for Colposcopic Images

A nonrigid body image registration method for spatiotemporal alignment of image sequences obtained from colposcopy examinations to detect precancerous lesions of the cervix is proposed in this paper. The approach is based on time series calculation for those pixels in the first image of the sequence and a division of such image into small windows. A search process is then carried out to find the window with the highest affinity in each image of the sequence and replace it with the window in the reference image. The affinity value is based on polynomial approximation of the time series computed and the search is bounded by a search radius which defines the neighborhood of each window. The proposed approach is tested in ten 310-frame real cases in two experiments: the first one to determine the best values for the window size and the search radius and the second one to compare the best obtained results with respect to four registration methods found in the specialized literature. The obtained results show a robust and competitive performance of the proposed approach with a significant lower time with respect to the compared methods.

Transform-invariant feature based functional MR image registration and neural activity modelling

In this paper, a set of non-rigid image registration and neural activity modelling methods using functional MR Images (fMRI) are proposed based on transform-invariant feature representations. Our work made two contributions. First, we propose to use a transform-invariant feature to improve image registration performance of Iterative Closest Point (ICP) based methods. The proposed feature utilises Gaussian Mixture Models (GMM) to describe the local topological structure of fMRI data. Second, we propose to use a 3-dimensional Scale-Invariant Feature Transform (SIFT) based descriptor to represent neural activities related to drinking behaviour. As a result, neural activities patterns of different subjects drinking water or intaking glucose can be recognised, with strong robustness against various artefacts.

A non-rigid medical image registration method based on improved linear elastic model

Non-rigid medical image registration is an important research project of medical image processing; it is the basis of medical image fusion. Relative to rigid image, the deformation of non-rigid image is more serious and more complicated. According to the characteristics of non-rigid medical image deformation, this paper proposes an adaptive non-rigid medical image registration algorithm. Firstly, it is based on global registration; secondly, it is about extracting feature points of global registration image and the reference image, and then generating irregular triangle grid according to extracted feature points. Finally, local accurate image registration is achieved using the minimum potential energy as a similar measure. Experimental results show that relative to the traditional non-rigid registration algorithm, this algorithm not only ensures the registration accuracy but also enhances the robustness and anti-noise of registration algorithm.

Left ventricle wall motion quantification from echocardiographic images by non-rigid image registration

The aim of this study is to evaluate the efficiency of applying a new non-rigid image registration method on two-dimensional echocardiographic images for computing the left ventricle (LV) myocardial motion field over a cardiac cycle. The key feature of our method is to register all images in the sequence to a reference image (end-diastole image) using a hierarchical transformation model, which is a combination of an affine transformation for modeling the global LV motion and a free-form deformation (FFD) transformation based on B-splines for modeling the local LV deformation. Registration is done by minimizing a cost function associated with the image similarity based on a global pixel-based matching and the smoothness of transformation. The algorithm uses a fast and robust optimization strategy using a multiresolution approach for the estimation of parameters of the deformation model. The proposed algorithm is evaluated for calculating the displacement curves of two expert-identified anatomical landmarks in apical views of the LV for 10 healthy volunteers and 14 subjects with pathology. The proposed algorithm is also evaluated for classifying the regional LV wall motion abnormality using the calculation of the strain value at the end of systole in 288 segments as scored by two consensual experienced echocardiographers in a three-point scale: 1: normokinesia, 2: hypokinesia, and 3: akinesia. Moreover, we compared the results of the proposed registration algorithm to those previously obtained using the other image registration methods. Regarding to the reference two experienced echocardiographers, the results demonstrate the proposed algorithm more accurately estimates the displacement curve of the two anatomical landmarks in apical views than the other registration methods in all data set. Moreover, the p values of the t test for the strain value of each segment at the end of systole measured by the proposed algorithm show higher differences than the other registration method. These differences are between each pair of scores in all segments and in three segments of septum independently. The clinical results show that the proposed algorithm can improve both the calculation of the displacement curve of every point of LV during a cardiac cycle and the classification of regional LV wall motion abnormality. Therefore, this diagnostic system can be used as a useful tool for clinical evaluation of the regional LV function.

MRI-Based Nonrigid Motion Correction in Simultaneous PET/MRI

Respiratory and cardiac motion is the most serious limitation to whole-body PET, resulting in spatial resolution close to 1 cm. Furthermore, motion-induced inconsistencies in the attenuation measurements often lead to significant artifacts in the reconstructed images. Gating can remove motion artifacts at the cost of increased noise. This paper presents an approach to respiratory motion correction using simultaneous PET/MRI to demonstrate initial results in phantoms, rabbits, and nonhuman primates and discusses the prospects for clinical application. Studies with a deformable phantom, a free-breathing primate, and rabbits implanted with radioactive beads were performed with simultaneous PET/MRI. Motion fields were estimated from concurrently acquired tagged MR images using 2 B-spline nonrigid image registration methods and incorporated into a PET list-mode ordered-subsets expectation maximization algorithm. Using the measured motion fields to transform both the emission data and the attenuation data, we could use all the coincidence data to reconstruct any phase of the respiratory cycle. We compared the resulting SNR and the channelized Hotelling observer (CHO) detection signal-to-noise ratio (SNR) in the motion-corrected reconstruction with the results obtained from standard gating and uncorrected studies. Motion correction virtually eliminated motion blur without reducing SNR, yielding images with SNR comparable to those obtained by gating with 5-8 times longer acquisitions in all studies. The CHO study in dynamic phantoms demonstrated a significant improvement (166%-276%) in lesion detection SNR with MRI-based motion correction as compared with gating (P < 0.001). This improvement was 43%-92% for large motion compared with lesion detection without motion correction (P < 0.001). CHO SNR in the rabbit studies confirmed these results. Tagged MRI motion correction in simultaneous PET/MRI significantly improves lesion detection compared with respiratory gating and no motion correction while reducing radiation dose. In vivo primate and rabbit studies confirmed the improvement in PET image quality and provide the rationale for evaluation in simultaneous whole-body PET/MRI clinical studies.

WE-E-213CD-03: Inverse-Consistent Symmetric Registration of Inner Colon Surfaces Derived from Prone and Supine CT Colonography.

Robust registration of prone and supine colonie surfaces acquired during CT colonography may lead to faster and more accurate detection of colorectal cancer and polyps. Any directional bias when registering one surface to the other could precipitate incorrect anatomical correspondence and engender reader error. Despite this, non-rigid registration methods are often implemented asymmetrically, which could negatively influence the registration. We aimed to reduce directional bias and so increase robustness by adapting a cylindrical registration algorithm to be both symmetric and inverse-consistent. The registration task can be simplified by mapping both prone and supine colonie surfaces onto regular cylinders. Spatial correspondence can then be established in cylindrical space using the original surfaces' local shape indices. We implemented a symmetric formulation of the popular non-rigid B-spline image registration method in cylindrical space. A symmetric similarity measure computes the sum of squared differences between both cylindrical representations of prone-to-supine and supine-to-prone directions simultaneously. Inverse consistency of the transformation is enforced by adding an appropriately weighted penalty term to the optimisation function. We selected 8 CT colonography patient cases with marked variation in luminal distension and surface morphology. We randomly allocated 4 of these for tuning an optimal set of registration parameters and 4 for validation. The mean inverse-consistency error was reduced by 32% from 4.8mm to 3.2mm by the new symmetric formulation. The mean registration error improved from 8.2mm to 7.3mm for 330 manually chosen reference points on the 4 validation sets. A symmetric formulation of prone and supine surface registration improves the quality of registration. Information from both prone-to-supine and supine-to-prone directions helps enforce convergence towards a more accurate solution due to reduced directional bias. A more robust and accurate registration will facilitate interpretation of CT colonography and has the potential to improve existing computer-aided detection methods. The authors gratefully acknowledge financial support for this work from the NIHR program: “Imaging diagnosis of colorectal cancer: Interventions for efficient and acceptable diagnosis in symptomatic and screening populationsâ€.

Rigid and non-rigid medical image registration methods

Image registration is an important and usually necessary step in multi-dimensional multi-modality medical image analysis. Moreover, images from the same modality may be registered to study and analyse variability of a specific structure or information among a group of subjects to develop physiological models and computerised atlases. Multi-dimensional image registration is also an important step in therapeutic protocols including radiation treatment and evaluation. Recent advances in medical imaging and image analysis have accompanied with a number of rigid-body and non-rigidbody image registration methods and algorithms. This paper first briefly reviews some of the rigid and non-rigid image registration methods and then presents an integrated approach of rigid and elastic deformation methods suitable for dealing with registration of partially deformed and incomplete image datasets.

Hybrid deformable image registration using a closed-form Free Form Deformation approach

This paper describes an efficient non-rigid image registration method using a B-spline based Free Form Deformation (FFD) model. The proposed method is very efficient, in that it utilises sparse feature correspondences to estimate an elastic deformation field in a closed form. In a multi-resolution manner, the method is able to recover small to large nonrigid deformations, and the resulting deformation field is globally smooth and guarantees one-to-one mapping between the two registered images.

Nonrigid Brain MR Image Registration Using Uniform Spherical Region Descriptor

There are two main issues that make nonrigid image registration a challenging task. First, voxel intensity similarity may not be necessarily equivalent to anatomical similarity in the image correspondence searching process. Second, during the imaging process, some interferences such as unexpected rotations of input volumes and monotonic gray-level bias fields can adversely affect the registration quality. In this paper, a new feature-based nonrigid image registration method is proposed. The proposed method is based on a new type of image feature, namely, uniform spherical region descriptor (USRD), as signatures for each voxel. The USRD is rotation and monotonic gray-level transformation invariant and can be efficiently calculated. The registration process is therefore formulated as a feature matching problem. The USRD feature is integrated with the Markov random field labeling framework in which energy function is defined for registration. The energy function is then optimized by the α-expansion algorithm. The proposed method has been compared with five state-of-the-art registration approaches on both the simulated and real 3-D databases obtained from the BrainWeb and Internet Brain Segmentation Repository, respectively. Experimental results demonstrate that the proposed method can achieve high registration accuracy and reliable robustness behavior.

Non-rigid image registration of brain magnetic resonance images using graph-cuts

We present a graph-cuts based method for non-rigid medical image registration on brain magnetic resonance images. In this paper, the non-rigid medical image registration problem is reformulated as a discrete labeling problem. Based on a voxel-to-voxel intensity similarity measure, each voxel in the source image is assigned a displacement label, which represents a displacement vector indicating which position in the floating image it is spatially corresponding to. In the proposed method, a smoothness constraint based on the first derivative is used to penalize sharp changes in the adjacent displacement labels across voxels. The image registration problem is therefore modeled by two energy terms based on intensity similarity and smoothness of the displacement field. These energy terms are submodular and can be optimized by using the graph-cuts method via α‐expansions, which is a powerful combinatorial optimization tool and capable of yielding either a global minimum or a local minimum in a strong sense. Using the realistic brain phantoms obtained from the Simulated Brain Database, we compare the registration results of the proposed method with two state-of-the-art medical image registration approaches: free-form deformation based method and demons method. In addition, the registration results are also compared with that of the linear programming based image registration method. It is found that the proposed method is more robust against different challenging non-rigid registration cases with consistently higher registration accuracy than those three methods, and gives realistic recovered deformation fields.

Nonrigid registration based on projected joint entropy combined with gradient similarity

Our study proposes a nonrigid image registration method between different color channels in a color image sequence. It minimizes the entropy in a dominant subspace of the joint distribution of two or more images. The proposed algorithm is based on the observation that the displacement between color channels affects only the dominant subspace in the joint distribution of pixel values. We also propose the use of gradient direction to give extra robustness to our similarity function. Experiments estimating motion parameters for B-spline nonrigid deformation models demonstrate the effectiveness of the proposed registration technique.

Multichannel Image Registration by Feature-Based Information Fusion

This paper proposes a novel nonrigid inter-subject multichannel image registration method which combines information from different modalities/channels to produce a unified joint registration. Multichannel images are created using co-registered multimodality images of the same subject to utilize information across modalities comprehensively. Contrary to the existing methods which combine the information at the image/intensity level, the proposed method uses feature-level information fusion method to spatio-adaptively combine the complementary information from different modalities that characterize different tissue types, through Gabor wavelets transformation and Independent Component Analysis (ICA), to produce a robust inter-subject registration. Experiments on both simulated and real multichannel images illustrate the applicability and robustness of the proposed registration method that combines information across modalities. This inter-subject registration is expected to pave the way for subsequent unified population-based multichannel studies.

A robust hybrid method for nonrigid image registration

A nonrigid registration method is proposed to automatically align two images by registering two sets of sparse features extracted from the images. Motivated by the paradigm of Robust Point Matching (RPM) algorithms 1,2], which were originally proposed for shape registration, we develop Robust Hybrid Image Matching (RHIM) algorithm by alternatively optimizing feature correspondence and spatial transformation for image registration. Our RHIM algorithm is built to be robust to feature extraction errors. A novel dynamic outlier rejection approach is described for removing outliers and a local refinement technique is applied to correct non-exactly matched correspondences arising from image noise and deformations. Experimental results demonstrate the robustness and accuracy of our method.