Proposed Registration Framework Research Articles

Non-rigid point set registration based on Gaussian mixture model with integrated feature divergence

PurposeThis paper aims to propose a robust method for non-rigid point set registration, using the Gaussian mixture model and accommodating non-rigid transformations. The posterior probabilities of the mixture model are determined through the proposed integrated feature divergence.Design/methodology/approachThe method involves an alternating two-step framework, comprising correspondence estimation and subsequent transformation updating. For correspondence estimation, integrated feature divergences including both global and local features, are coupled with deterministic annealing to address the non-convexity problem of registration. For transformation updating, the expectation-maximization iteration scheme is introduced to iteratively refine correspondence and transformation estimation until convergence.FindingsThe experiments confirm that the proposed registration approach exhibits remarkable robustness on deformation, noise, outliers and occlusion for both 2D and 3D point clouds. Furthermore, the proposed method outperforms existing analogous algorithms in terms of time complexity. Application of stabilizing and securing intermodal containers loaded on ships is performed. The results demonstrate that the proposed registration framework exhibits excellent adaptability for real-scan point clouds, and achieves comparatively superior alignments in a shorter time.Originality/valueThe integrated feature divergence, involving both global and local information of points, is proven to be an effective indicator for measuring the reliability of point correspondences. This inclusion prevents premature convergence, resulting in more robust registration results for our proposed method. Simultaneously, the total operating time is reduced due to a lower number of iterations.

Automatic registration framework for multi-platform point cloud data in natural forests

ABSTRACT The use of light detection and ranging (LiDAR) for investigating forest parameters has gained attention in recent years. However, the occlusion of trees in natural forests makes it difficult for LiDAR on a single platform to capture complete point clouds of trees. In order to solve this problem, it is crucial to combine multi-platform LiDAR data. Because of the complexity of natural forests and the small difference between the geometric characteristics of trees, current multi-platform LiDAR data fusion remains an ongoing challenge in natural forests. In this paper, an automatic registration framework for multi-platform point cloud data in natural forests based on tree distribution pattern was proposed. It consists of five steps, namely segmenting trees, generating feature descriptors, matching trees and registering coarsely and finely. The proposed registration framework can determine the same and accurate location information of matching trees from multi-platform LiDAR data, and a large number of correct matching trees can be obtained through two rounds of a single tree matching process. The proposed framework was validated by fusing airborne laser scanner (ALS) and backpack laser scanner (BLS) data in natural forest. According to experimental results, the proposed framework has a high registration accuracy (root-mean-square error (RMSE) = 0.133 m, mean absolute error (MAE) = 0.126 m). In addition, when the single tree segmentation accuracy exceeds 0.85, the proposed framework is less affected by segmentation errors. In natural forests, the proposed framework can effectively improve the accuracy and efficiency of multi-platform LiDAR data registration.

Robust Multimodal Remote Sensing Image Registration Based on Local Statistical Frequency Information

Multimodal remote sensing image registration is a prerequisite for comprehensive application of remote sensing image data. However, inconsistent imaging environment and conditions often lead to obvious geometric deformations and significant contrast differences between multimodal remote sensing images, which makes the common feature extraction extremely difficult, resulting in their registration still being a challenging task. To address this issue, a robust local statistics-based registration framework is proposed, and the constructed descriptors are invariant to contrast changes and geometric transformations induced by imaging conditions. Firstly, maximum phase congruency of local frequency information is performed by optimizing the control parameters. Then, salient feature points are located according to the phase congruency response map. Subsequently, the geometric and contrast invariant descriptors are constructed based on a joint local frequency information map that combines Log-Gabor filter responses over multiple scales and orientations. Finally, image matching is achieved by finding the corresponding descriptors; image registration is further completed by calculating the transformation between the corresponding feature points. The proposed registration framework was evaluated on four different multimodal image datasets with varying degrees of contrast differences and geometric deformations. Experimental results demonstrated that our method outperformed several state-of-the-art methods in terms of robustness and precision, confirming its effectiveness.

Optical Flow with Learning Feature for Deformable Medical Image Registration

Deformable medical image registration plays a vital role in medical image applications, such as placing different temporal images at the same time point or different modality images into the same coordinate system. Various strategies have been developed to satisfy the increasing needs of deformable medical image registration. One popular registration method is estimating the displacement field by computing the optical flow between two images. The motion field (flow field) is computed based on either gray-value or handcrafted descriptors such as the scale-invariant feature transform (SIFT). These methods assume that illumination is constant between images. However, medical images may not always satisfy this assumption. In this study, we propose a metric learning-based motion estimation method called Siamese Flow for deformable medical image registration. We train metric learners using a Siamese network, which produces an image patch descriptor that guarantees a smaller feature distance in two similar anatomical structures and a larger feature distance in two dissimilar anatomical structures. In the proposed registration framework, the flow field is computed based on such features and is close to the real deformation field due to the excellent feature representation ability of the Siamese network. Experimental results demonstrate that the proposed method outperforms the Demons, SIFT Flow, Elastix, and VoxelMorph networks regarding registration accuracy and robustness, particularly with large deformations.

A Robust Two-Stage Registration Algorithm for Large Optical and SAR Images

Accurate optical and synthetic aperture radar (SAR) image registration is crucial to multisensor remote sensing applications. Though several algorithms have been proposed, the practical implementation that directly matches large and high-resolution optical and SAR images remains underexplored by the community. Equipped with the satellite positioning parameters, optical and SAR images can be roughly registered based on geographic coordinates. However, the relative positioning accuracy is still dozens, even hundreds of pixels due to the inaccuracies of sensor parameters and elevation. Consequently, we propose a robust registration algorithm, which consists of two stages, where the horizontal positioning errors can be reduced in the first stage, and then, we fine-tune the correspondences in the second stage. Specifically, we propose a novel template matching method based on the dilated convolutional feature (DCF) and epipolar-oriented phase correlation. DCF is constructed by a depthwise-separable dilated convolution with multichannel gradients, which are generated by the Sobel operator for optical images and a ratio of exponentially weighted averages (ROEWA) operator for SAR images. Due to the large reception field of dilated convolution, DCF can retain invariance even for large relative positioning errors. The epipolar-oriented rectangle template, which stretches along the epipolar line, is then proposed to capture more overlapping areas compared to square templates. Furthermore, the outlier removal is implemented in the coordinate system of optical images to avoid the effect of range compression in SAR images. Inliers are finally used to refine the rational polynomial coefficients (RPCs) based on the bundle adjustment technique. Experimental results on high-resolution optical and SAR image products of various scenarios demonstrate the effectiveness of the proposed registration framework. The relative positioning errors of the refined RPCs can be reduced from hundreds of pixels to the subpixel level.

An Unsupervised Learning Approach to 3D Rectal MRI Volume Registration

Accurate alignment of multi-session medical imaging is essential to the analysis of disease progression. By comparing the magnetic resonance imaging (MRI) data captured before and after a course of neoadjuvant chemoradiation (nCRT) treatment, physicians are able to evaluate the tumor response for further treatment of the disease. However, rectal MRI data captured in multi-session are often misaligned and not guaranteed to have one-to-one correspondence, making it challenging for physicians to observe the treatment response of tumor. To address this issue, we propose an unsupervised learning based volume registration framework, which enables accurate alignment even under a high degree of deformation between multi-session rectal data. Moreover, it works without the assumption of one-to-one correspondence between multi-session data, and hence is a general solution to rectal MRI volume registration. The experimental results show that the proposed registration framework accurately aligns rectal cancer images and outperforms other state-of-the-art methods in medical image registration. By providing accurate registration, it can potentially increase the efficiency and reduce the workload for physicians to evaluate the rectal tumor response to nCRT.

Automatic registration of a single SAR image and GIS building footprints in a large-scale urban area

Existing techniques of 3-D reconstruction of buildings from SAR images are mostly based on multibaseline SAR interferometry, such as PSI and SAR tomography (TomoSAR). However, these techniques require tens of images for a reliable reconstruction, which limits the application in various scenarios, such as emergency response. Therefore, alternatives that use a single SAR image and the building footprints from GIS data show their great potential in 3-D reconstruction. The combination of GIS data and SAR images requires a precise registration, which is challenging due to the unknown terrain height, and the difficulty in finding and extracting the correspondence. In this paper, we propose a framework to automatically register GIS building footprints to a SAR image by exploiting the features representing the intersection of ground and visible building facades, specifically the near-range boundaries in the building polygons, and the double bounce lines in the SAR image. Based on those features, the two data sets are registered progressively in multiple resolutions, allowing the algorithm to cope with variations in the local terrain. The proposed framework was tested in Berlin using one TerraSAR-X High Resolution SpotLight image and GIS building footprints of the area. Comparing to the ground truth, the proposed algorithm reduced the average distance error from 5.91 m before the registration to −0.08 m, and the standard deviation from 2.77 m to 1.12 m. Such accuracy, better than half of the typical urban floor height (3 m), is significant for precise building height reconstruction on a large scale. The proposed registration framework has great potential in assisting SAR image interpretation in typical urban areas and building model reconstruction from SAR images.

Feature-Guided Nonrigid 3-D Point Set Registration Framework for Image-Guided Liver Surgery: From Isotropic Positional Noise to Anisotropic Positional Noise

Registration is an essential problem in image-guided surgery (IGS) since it brings different involved coordinate frames together. Nonrigid or deformable registration still faces many challenges, such as two point sets (PSs) are partially overlapped. To tackle the challenges in the nonrigid registration, we introduce a new two-step point-based registration pipeline that includes two steps. In the first step, the rigid transformation between the two spaces is recovered where the orientation vectors are adopted. In the second step, built on the nonrigid coherent point drift (CPD) approach, the anisotropic positional noise is also assumed. Registration results on the human liver verify the proposed approach' great improvements over the other methods. First, the rotation and translation are recovered with smaller error values than the existing methods. Second, our registration method's performance is much more robust to the partial overlapping between two PSs. Third, the two-step registration framework achieves the best performances in most test cases when there is a localization error in acquiring the intraoperative data. Note to Practitioners-A novel registration approach is presented for image-guided liver surgery (LGLS). Compared with existing nonrigid registration methods, two significant changes (or improvements) exist in the proposed registration framework: 1) the normal vectors are extracted and utilized in the rigid registration step and 2) the anisotropic positional uncertainties are considered. In both steps, the registration problems are formulated as a maximum likelihood (ML) problems and dealt with the expectation-maximization (EM) technique. In both steps, the matrix form of the updated positional covariance is provided and can speed up the computational process. The readers are reminded that with extra information and a more general positional error assumption, our approach demonstrates improved performances in the case of partial-to-full alignment.

Registration of vascular structures using a hybrid mixture model.

Morphological changes to anatomy resulting from invasive surgical procedures or pathology, typically alter the surrounding vasculature. This makes it useful as a descriptor for feature-driven image registration in various clinical applications. However, registration of vasculature remains challenging, as vessels often differ in size and shape, and may even miss branches, due to surgical interventions or pathological changes. Furthermore, existing vessel registration methods are typically designed for a specific application. To address this limitation, we propose a generic vessel registration approach useful for a variety of clinical applications, involving different anatomical regions. A probabilistic registration framework based on a hybrid mixture model, with a refinement mechanism to identify missing branches (denoted as HdMM+) during vasculature matching, is introduced. Vascular structures are represented as 6-dimensional hybrid point sets comprising spatial positions and centerline orientations, using Student's t-distributions to model the former and Watson distributions for the latter. The proposed framework is evaluated for intraoperative brain shift compensation, and monitoring changes in pulmonary vasculature resulting from chronic lung disease. Registration accuracy is validated using both synthetic and patient data. Our results demonstrate, HdMM+ is able to reduce more than [Formula: see text] of the initial error for both applications, and outperforms the state-of-the-art point-based registration methods such as coherent point drift and Student's t-distribution mixture model, in terms of mean surface distance, modified Hausdorff distance, Dice and Jaccard scores. The proposed registration framework models complex vascular structures using a hybrid representation of vessel centerlines, and accommodates intricate variations in vascular morphology. Furthermore, it is generic and flexible in its design, enabling its use in a variety of clinical applications.

Combined manual and automatic landmark detection for enhanced surface registration of anatomical structures: an extensive parameter study for femur and clavicle

ABSTRACTSurface registration, in which a mapping between surfaces is calculated, is a powerful tool to create patient-specific musculoskeletal and statistical shape models. However, to create these models, surface registration must assure a one-to-one correspondence between both surfaces. To enhance this process, a surface registration framework that uses a combination of manual and automatic landmark detection is presented in this study. In addition, an extensive parameter study of the framework for a femur and a clavicle is conducted. The average correspondence quality of nine femur landmarks decreased from 15.6 mm using automatic point detection to 6.1 mm by combining manually and automatically indicated landmarks. For the clavicle, the average distance of five landmarks decreased from 2.8 to 0.9 mm. Combining manual and automatic landmark detection clearly improved correspondence quality. Results confirmed the applicability of the proposed registration framework for femur and clavicle, although with different parameter settings.

Registration of 3D underground parcel in Korean cadastral system

Economic growth and urbanization have reduced urban land resources to the point that such resources are now, in some cases severely, limited. In order to support sustainable development and to solve the problem of land shortages in urban areas, one practical solution is the shifting of land usage from above the surface to underground. However, in most countries, including Korea, the cadastral system cannot adequately handle the legal, administrative, and technical aspects of the registration and maintenance of underground parcels. The main purpose of this research, therefore, was to propose a conceptual registration framework for 3D underground parcels. In order to do that, issues of unregistered underground space were summarized, and the legal, administrative, and technical limitations were revealed. In consideration of these limitations, the registration framework for 3D underground parcels is herein proposed. This framework consists of four steps: 1) preparation of 3D underground parcel data with consideration for information regarding 3D underground cadastral surveying and building-components; 2) definition of 3D underground parcels, based on deep underground regulation in Korea and the registration extent, registration unit, absolute height and relative height of systems; 3) 3D underground cadastral registration according to the three types of cadastral maps and land registration; 4) registration of 3D underground rights, such as ownership and sectional superficies of the 3D underground parcel. Finally, in order to implement the proposed registration framework for a 3D underground parcel, legal, administrative, and technical improvements are proposed.

Generic and Automatic Markov Random Field-Based Registration for Multimodal Remote Sensing Image Using Grayscale and Gradient Information

The automatic image registration serves as a technical prerequisite for multimodal remote sensing image fusion. Meanwhile, it is also the technical basis for change detection, image stitching and target recognition. The demands of subpixel level registration accuracy can be rarely satisfied with a multimodal image registration method based on feature matching. In light of this, we propose a Generic and automatic Markov Random Field (MRF)-based registration framework of multimodal image using grayscale and gradient information. The proposed approach performs non-rigid registration and formulates an MRF model while grayscale and gradient statistical information of a multimodal image is employed for the evaluation of similarity while the spatial weighting function is optimized simultaneously. Besides, the value space is discretized to improve the convergence speed. The developed automatic approach was validated both qualitatively and quantitatively, demonstrating its potential for a variety of multimodal remote sensing datasets and scenes. As for the registration accuracy, the average target registration error of the proposed framework is less than 1 pixel, while the maximum displacement error is less than 1 pixel. Compared with the polynomial model registration based on manual selection, the registration accuracy has been significantly improved. In the meantime, the proposed approach had the partial applicability for the multimodal image registration of large deformation scenes. It is also proved that the proposed registration framework using grayscale and gradient information outperforms the MRF-based registration using only grayscale information and only gradient information while the proposed registration framework using Gaussian function as spatial weighting function is superior to that using distance inverse weight method.

Nonrigid Image Registration Using Spatially Region-Weighted Correlation Ratio and GPU-Acceleration.

Nonrigid image registration with high accuracy and efficiency remains a challenging task for medical image analysis. In this paper, we present the spatially region-weighted correlation ratio (SRWCR) as a novel similarity measure to improve the registration performance. SRWCR is rigorously deduced from a three-dimension joint probability density function combining the intensity channels with an extra spatial information channel. SRWCR estimates the optimal functional dependence between the intensities for each spatial bin, in which the spatial distribution modeled by a cubic B-spline function is used to differentiate the contribution of voxels. We also analytically derive the gradient of SRWCR with respect to the transformation parameters and optimize it using a quasi-Newton approach. Furthermore, we propose a GPU-based parallel mechanism to accelerate the computation of SRWCR and its derivatives. The experiments on synthetic images, public four-dimensional thoracic computed tomography (CT) dataset, retinal optical coherence tomography data, and clinical CT and positron emission tomography images confirm that SRWCR significantly outperforms some state-of-the-art techniques such as spatially encoded mutual information and Robust PaTch-based cOrrelation Ration. This study demonstrates the advantages of SRWCR in tackling the practical difficulties due to distinct intensity changes, serious speckle noise, or different imaging modalities. The proposed registration framework might be more reliable to correct the nonrigid deformations and more potential for clinical applications.

Multimodality registration of two-dimensional echocardiography and cardiac CT for mitral valve diagnosis and surgical planning.

A registration method to fuse two-dimensional (2-D) echocardiography images with cardiac computed tomography (CT) volume is presented. The method consists of two major procedures: temporal and spatial registrations. In temporal registration, the echocardiography frames at similar cardiac phases as the CT volume were interpolated based on electrocardiogram signal information, and the noise of the echocardiography image was reduced using the speckle reducing anisotropic diffusion technique. For spatial registration, an intensity-based normalized mutual information method was applied with a pattern search optimization algorithm to produce an interpolated cardiac CT image. The proposed registration framework does not require optical tracking information. Dice coefficient and Hausdorff distance for the left atrium assessments were [Formula: see text] and [Formula: see text], respectively; for left ventricle, they were [Formula: see text] and [Formula: see text], respectively. There was no significant difference in the mitral valve annulus diameter measurement between the manually and automatically registered CT images. The transformation parameters showed small deviations ([Formula: see text] deviation in translation and [Formula: see text] for rotation) between manual and automatic registrations. The proposed method aids the physician in diagnosing mitral valve disease as well as provides surgical guidance during the treatment procedure.

Robust point matching method for multimodal retinal image registration

In this paper, motivated by the problem of multimodal retinal image registration, we introduce and improve the robust registration framework based on partial intensity invariant feature descriptor (PIIFD), then present a registration framework based on speed up robust feature (SURF) detector, PIIFD and robust point matching, called SURF–PIIFD–RPM. Existing retinal image registration algorithms are unadaptable to any case, such as complex multimodal images, poor quality, and nonvascular images. Harris-PIIFD framework usually fails in correctly aligning color retinal images with other modalities when faced large content changes. Our proposed registration framework mainly solves the problem robustly. Firstly, SURF detector is useful to extract more repeatable and scale-invariant interest points than Harris. Secondly, a single Gaussian robust point matching model is based on the kernel method of reproducing kernel Hilbert space to estimate mapping function in the presence of outliers. Most importantly, our improved registration framework performs well even when confronted a large number of outliers in the initial correspondence set. Finally, multiple experiments on our 142 multimodal retinal image pairs demonstrate that our SURF–PIIFD–RPM outperforms existing algorithms, and it is quite robust to outliers.

Toward physiologically motivated registration of diagnostic CT and PET/CT of lung volumes

Current clinical practice for lung cancer diagnosis and staging requires the acquisition of a diagnostic computed tomography (CT) as well as positron emission tomography (PET)/CT volumes from a hybrid scanner, where the CT is used for attenuation correction (AC-CT). The PET and AC-CT images are implicitly aligned, however, image registration between the diagnostic CT and PET volumes is needed to relate the anatomical correspondences. This is an important but difficult task due to the absence of a direct or functional relationship between the intensities. Alternatively, here we propose the diagnostic CT can be aligned with the PET image through an indirect registration process that uses the AC-CT. The resultant deformation field can then be used to align the PET image to the diagnostic CT. The registration of the diagnostic CT to AC-CT registration still presents two major challenges: (a) it is a multimodal registration problem since the diagnostic CT is acquired after the injection of a contrast agent, and (b) the type and amplitude of the deformations require a registration process that includes physically motivated properties to achieve an accurate and physiologically plausible alignment. The authors propose a new framework based on fluid registration including three physiologically motivated properties: (i) sliding motion of the lungs against the pleura; (ii) preservation of rigid structures; (iii) preservation of topology. The sliding motion is modeled using direction dependent regularization that decouples the tangential and the normal components of the external force term. The rigid shape of the bones is preserved using a spatially varying filter for the deformations. Finally, the topology is maintained using the concept of log-unbiased deformations. To solve the multimodal problem, the authors use local cross correlation (LCC) as the similarity measure. The proposed framework is first evaluated on CT lung image pairs representing several phases of the respiratory cycle. The authors show that their proposed framework has a superior performance compared to the classic fluid registration, both in quantitative and qualitative terms. The authors then evaluate the framework using ten real patient scans, where the authors also demonstrate how their physiologically motivated registration framework can be successfully applied to the task of fusing diagnostic CT with the PET/CT image volumes. The proposed registration framework has better results for the fusion of diagnostic CT with PET images in comparison to the classic fluid registration framework.

Intraoperative Image-based Multiview 2D/3D Registration for Image-Guided Orthopaedic Surgery: Incorporation of Fiducial-Based C-Arm Tracking and GPU-Acceleration

Intraoperative patient registration may significantly affect the outcome of image-guided surgery (IGS). Image-based registration approaches have several advantages over the currently dominant point-based direct contact methods and are used in some industry solutions in image-guided radiation therapy with fixed X-ray gantries. However, technical challenges including geometric calibration and computational cost have precluded their use with mobile C-arms for IGS. We propose a 2D/3D registration framework for intraoperative patient registration using a conventional mobile X-ray imager combining fiducial-based C-arm tracking and graphics processing unit (GPU)-acceleration. The two-stage framework 1) acquires X-ray images and estimates relative pose between the images using a custom-made in-image fiducial, and 2) estimates the patient pose using intensity-based 2D/3D registration. Experimental validations using a publicly available gold standard dataset, a plastic bone phantom and cadaveric specimens have been conducted. The mean target registration error (mTRE) was 0.34 ± 0.04 mm (success rate: 100%, registration time: 14.2 s) for the phantom with two images 90° apart, and 0.99 ± 0.41 mm (81%, 16.3 s) for the cadaveric specimen with images 58.5° apart. The experimental results showed the feasibility of the proposed registration framework as a practical alternative for IGS routines.

Object‐constrained meshless deformable algorithm for high speed 3D nonrigid registration between CT and CBCT

High-speed nonrigid registration between the planning CT and the treatment CBCT data is critical for real time image guided radiotherapy (IGRT) to improve the dose distribution and to reduce the toxicity to adjacent organs. The authors propose a new fully automatic 3D registration framework that integrates object-based global and seed constraints with the grayscale-based "demons" algorithm. Clinical objects were segmented on the planning CT images and were utilized as meshless deformable models during the nonrigid registration process. The meshless models reinforced a global constraint in addition to the grayscale difference between CT and CBCT in order to maintain the shape and the volume of geometrically complex 3D objects during the registration. To expedite the registration process, the framework was stratified into hierarchies, and the authors used a frequency domain formulation to diffuse the displacement between the reference and the target in each hierarchy. Also during the registration of pelvis images, they replaced the air region inside the rectum with estimated pixel values from the surrounding rectal wall and introduced an additional seed constraint to robustly track and match the seeds implanted into the prostate. The proposed registration framework and algorithm were evaluated on 15 real prostate cancer patients. For each patient, prostate gland, seminal vesicle, bladder, and rectum were first segmented by a radiation oncologist on planning CT images for radiotherapy planning purpose. The same radiation oncologist also manually delineated the tumor volumes and critical anatomical structures in the corresponding CBCT images acquired at treatment. These delineated structures on the CBCT were only used as the ground truth for the quantitative validation, while structures on the planning CT were used both as the input to the registration method and the ground truth in validation. By registering the planning CT to the CBCT, a displacement map was generated. Segmented volumes in the CT images deformed using the displacement field were compared against the manual segmentations in the CBCT images to quantitatively measure the convergence of the shape and the volume. Other image features were also used to evaluate the overall performance of the registration. The algorithm was able to complete the segmentation and registration process within 1 min, and the superimposed clinical objects achieved a volumetric similarity measure of over 90% between the reference and the registered data. Validation results also showed that the proposed registration could accurately trace the deformation inside the target volume with average errors of less than 1 mm. The method had a solid performance in registering the simulated images with up to 20 Hounsfield unit white noise added. Also, the side by side comparison with the original demons algorithm demonstrated its improved registration performance over the local pixel-based registration approaches. Given the strength and efficiency of the algorithm, the proposed method has significant clinical potential to accelerate and to improve the CBCT delineation and targets tracking in online IGRT applications.

ORBIT: a multiresolution framework for deformable registration of brain tumor images.

A deformable registration method is proposed for registering a normal brain atlas with images of brain tumor patients. The registration is facilitated by first simulating the tumor mass effect in the normal atlas in order to create an atlas image that is as similar as possible to the patient's image. An optimization framework is used to optimize the location of tumor seed as well as other parameters of the tumor growth model, based on the pattern of deformation around the tumor region. In particular, the optimization is implemented in a multiresolution and hierarchical scheme, and it is accelerated by using a principal component analysis (PCA)-based model of tumor growth and mass effect, trained on a computationally more expensive biomechanical model. Validation on simulated and real images shows that the proposed registration framework, referred to as ORBIT (optimization of tumor parameters and registration of brain images with tumors), outperforms other available registration methods particularly for the regions close to the tumor, and it has the potential to assist in constructing statistical atlases from tumor-diseased brain images.

Improved accuracy of brain MRI/SPECT registration using a two-cluster SPECT normalization algorithm and a combinative similarity measure: application to the evaluation of Parkinson's disease

Single-photon emission computed tomography (SPECT) of dopamine transporters with technetium-99-labeled tropane derivative (99m)Tc-TRODAT-1 has recently been suggested to offer valuable information in assessing the functionality of dopaminergic systems. To facilitate the non-invasive examination of the dopamine concentration in vivo, registering magnetic resonance imaging (MRI) and SPECT image is important. This article proposes a new similarity measure for MRI/SPECT registration. The proposed similarity measure combines anatomic features that are characterized by specific binding of nuclear medicine and the distribution of image intensity that are characterized by the normalized mutual information (NMI). A preprocess, a novel two-cluster SPECT normalization algorithm, is also proposed. Compared with the conventional NMI-based registration algorithm, the proposed registration framework reduces the target of registration error from >7 mm to approximately 4 mm. The error of the specific-to-non-specific (99m)Tc-TRODAT-1 binding ratio (BR), a quantitative measure of TRODAT receptor binding, is also reduced from 0.45 to 0.08 in the healthy subjects and from 0.28 to 0.12 in Parkinson's disease patients. A suitable color map, such as "rainbow," for image display enables the two-cluster SPECT normalization algorithm to provide clinically meaningful visual contrast. In addition, registering MRI/SPECT based on the proposed similarity measure improves the accuracy compared with the conventional NMI-based algorithm.