Multimodality image registration by maximization of mutualinformation

A new approach to the problem of multimodality medical image registration is proposed, using a basic concept from information theory, mutual information (MI), or relative entropy, as a new matching criterion. The method presented in this paper applies MI to measure the statistical dependence or information redundancy between the image intensities of corresponding voxels in both images, which is assumed to be maximal if the images are geometrically aligned. Maximization of MI is a very general and powerful criterion, because no assumptions are made regarding the nature of this dependence and no limiting constraints are imposed on the image content of the modalities involved. The accuracy of the MI criterion is validated for rigid body registration of computed tomography (CT), magnetic resonance (MR), and photon emission tomography (PET) images by comparison with the stereotactic registration solution, while robustness is evaluated with respect to implementation issues, such as interpolation and optimization, and image content, including partial overlap and image degradation. Our results demonstrate that subvoxel accuracy with respect to the stereotactic reference solution can be achieved completely automatically and without any prior segmentation, feature extraction, or other preprocessing steps which makes this method very well suited for clinical applications     

稳健的图像匹配方法

景象匹配是计算机视觉研究的一个重要方向,如何在复杂的环境下提高匹配概率与定位精度是其亟待解决的难点之一。在分析畸变校正的量化噪声为高斯噪声的基础上,提出了基于特征和时空关联的积相关图像匹配算法。采用基于噪声抑制小波边缘检测方法,提取实时图和基准图的边缘特征;基于归一化积相关实现序列实时图(3帧)与基准图的匹配,再根据位置信息实现相关峰值的数据融合得到匹配点。此方法克服了因面积增大由几何失真导致的匹配概率下降的缺点,提高了匹配概率,具有较好的匹配稳健性。     

A computational vision approach to image registration

A computational vision approach is presented for the estimation of 2-D translation, rotation, and scale from two partially overlapping images. The approach results in a fast method that produces good results even when large rotation and translation have occurred between the two frames and the images are devoid of significant features. An illuminant direction estimation method is first used to obtain an initial estimation of camera rotation. A small number of feature points are then located, using a Gabor wavelet model for detecting local curvature discontinuities. An initial estimate of scale and translation is obtained by pairwise matching of the feature points detected from both frames. Finally, hierarchical feature matching is performed to obtain an accurate estimate of translation, rotation and scale. A method for error analysis of matching results is also presented. Experiments with synthetic and real images show that this algorithm yields accurate results when the scale of the images differ by up to 10%, the overlap between the two frames is as small as 23%, and the camera rotation between the two frames is significant. Experimental results and applications are presented.     

A contour-based approach to multisensor image registration

Image registration is concerned with the establishment of correspondence between images of the same scene. One challenging problem in this area is the registration of multispectral/multisensor images. In general, such images have different gray level characteristics, and simple techniques such as those based on area correlations cannot be applied directly. On the other hand, contours representing region boundaries are preserved in most cases. The authors present two contour-based methods which use region boundaries and other strong edges as matching primitives. The first contour matching algorithm is based on the chain-code correlation and other shape similarity criteria such as invariant moments. Closed contours and the salient segments along the open contours are matched separately. This method works well for image pairs in which the contour information is well preserved, such as the optical images from Landsat and Spot satellites. For the registration of the optical images with synthetic aperture radar (SAR) images, the authors propose an elastic contour matching scheme based on the active contour model. Using the contours from the optical image as the initial condition, accurate contour locations in the SAR image are obtained by applying the active contour model. Both contour matching methods are automatic and computationally quite efficient. Experimental results with various kinds of image data have verified the robustness of the algorithms, which have outperformed manual registration in terms of root mean square error at the control points.     

Interpolation artifacts in multimodality image registration based on maximization of mutual information

Mutual information (MI) is an increasingly popular match metric for multimodality image registration. However, its value is affected by interpolation, which may limit registration accuracy. The purpose of this study was to characterize the artifacts from eight interpolators and to investigate efficient strategies to overcome these artifacts. The interpolators were: 1) nearest neighbor; 2) linear; 3) cubic Catmull-Rom; 4) Hamming-windowed sinc; 5) partial volume; 6) NN with jittered sampling (JIT); 7) NN with histogram blurring (BLUR); and 8) NN with JIT and BLUR. The impact of interpolation on MI was evaluated in two dimensions over different translational and rotational misregistration. Interpolation caused spurious fluctuations in MI whenever the voxel grids had coinciding periodicities and were nearly aligned. The artifacts did not lessen by using intensity interpolators with wider support (e.g., cubic Catmull-Rom, Hamming-windowed sinc). PV could lead to either arch artifacts or inverted-arch artifacts, depending on the relative voxel sizes. Several strategies reduced artifacts and improved registration robustness: JIT, BLUR, avoiding an extreme number of intensity bins, and resampling the images in a rotated orientation with different relative voxel sizes (e.g., pi/3). These findings also apply to related methods, including normalized MI, joint entropy, and Hill's third moment.     

Likelihood maximization for list-mode emission tomographic imagereconstruction

The maximum a posteriori (MAP) Bayesian iterative algorithm using priors that are gamma distributed, due to Lange, Bahn and Little, is extended to include parameter choices that fall outside the gamma distribution model. Special cases of the resulting iterative method include the expectation maximization maximum likelihood (EMML) method based on the Poisson model in emission tomography, as well as algorithms obtained by Parra and Barrett and by Huesman et al. that converge to maximum likelihood and maximum conditional likelihood estimates of radionuclide intensities for list-mode emission tomography. The approach taken here is optimization-theoretic and does not rely on the usual expectation maximization (EM) formalism. Block-iterative variants of the algorithms are presented. A self-contained, elementary proof of convergence of the algorithm is included.     

改进BRISK特征的快速图像配准算法

为了实现超分辨率图像重建中高精度快速图像配准,提出一种改进BRISK特征的快速图像配准算法。原有BRISK算法在特征提取和匹配过程中,忽视了角点分布信息,其匹配策略单一,导致误匹配率高。针对该问题,首先利用BRISK算法构建连续尺度空间,在此基础上对图像进行分块,然后利用图像区域显著性自适应选择角点检测阈值,获得均匀分布的角点,最后利用快速最近邻FLANN算法结合RANSAC的方法进行二值特征快速匹配。实验结果表明:改进的BRISK算法相比原算法在保持速度的基础上达到亚像素级配准精度,并具有优越的场景适应性能。     

Fingerprint registration by maximization of mutual information.

Fingerprint registration is a critical step in fingerprint matching. Although a variety of registration alignment algorithms have been proposed, accurate fingerprint registration remains an unresolved problem. We propose a new algorithm for fingerprint registration using orientation field. This algorithm finds the correct alignment by maximization of mutual information between features extracted from orientation fields of template and input fingerprint images. Orientation field, representing the flow of ridges, is a relatively stable global feature of fingerprint images. This method uses the statistics and distribution of global feature of fingerprint images so that it is robust to image quality and local changes in images. The primary characteristic of this method is that it uses this stable global feature to align fingerprints, and that its behavior may resemble the way humans compare fingerprints. Experimental results show that the occurrence of misalignment is dramatically reduced and that registration accuracy is greatly improved at the same time, leading to enhanced matching performance.     

Consistent image registration

This paper presents a new method for image registration based on jointly estimating the forward and reverse transformations between two images while constraining these transforms to be inverses of one another. This approach produces a consistent set of transformations that have less pairwise registration error, i.e., better correspondence, than traditional methods that estimate the forward and reverse transformations independently. The transformations are estimated iteratively and are restricted to preserve topology by constraining them to obey the laws of continuum mechanics. The transformations are parameterized by a Fourier series to diagonalize the covariance structure imposed by the continuum mechanics constraints and to provide a computationally efficient numerical implementation. Results using a linear elastic material constraint are presented using both magnetic resonance and X-ray computed tomography image data. The results show that the joint estimation of a consistent set of forward and reverse transformations constrained by linear-elasticity give better registration results than using either constraint alone or none at all.     

A Markov random field approach for topology-preserving registration: application to object-based tomographic image interpolation

This paper proposes a topology-preserving multiresolution elastic registration method based on a discrete Markov random field of deformations and a block-matching procedure. The method is applied to the object-based interpolation of tomographic slices. For that purpose, the fidelity of a given deformation to the data is established by a block-matching strategy based on intensity- and gradient-related features, the smoothness of the transformation is favored by an appropriate prior on the field, and the deformation is guaranteed to maintain the topology by imposing some hard constraints on the local configurations of the field. The resulting deformation is defined as the maximum a posteriori configuration. Additionally, the relative influence of the fidelity and smoothness terms is weighted by the unsupervised estimation of the field parameters. In order to obtain an unbiased interpolation result, the registration is performed both in the forward and backward directions, and the resulting transformations are combined by using the local information content of the deformation. The method is applied to magnetic resonance and computed tomography acquisitions of the brain and the torso. Quantitative comparisons offer an overall improvement in performance with respect to related works in the literature. Additionally, the application of the interpolation method to cardiac magnetic resonance images has shown that the removal of any of the main components of the algorithm results in a decrease in performance which has proven to be statistically significant.     

A maximum likelihood approach for image registration using control point and intensity

Registration of multidate or multisensor images is an essential process in many image processing applications including remote sensing, medical image analysis, and computer vision. Control point (CP) and intensity are the two basic features used separately for image registration in the literature. In this paper, an exact maximum likelihood (EML) registration method, which combines both CP and intensity, is proposed for image alignment. The EML registration method maximizes the likelihood function based CP and intensity to estimate the registration parameters, including affine transformation and CP coordinates. The explicit formulas of the Cramer-Rao bound (CRB) are also derived for the proposed EML and conventional image registration algorithms. The performances of these image registration techniques are evaluated with the CRBs.     

A new image registration method robust to noise

Image registration is a fundamental task in many image processing applications. In this paper, we estimate the translation, rotation, and scaling parameters between a reference image and a distorted image in order to register them. We use the ratio of means to estimate the scaling factor, the Radon transform to estimate the rotation angle, and the fast Fourier transform to estimate global spatial shifts. Experimental results show that our proposed method can estimate the transformation parameters very accurately. Furthermore, our method performs very well in noisy environments.     

A block alternating likelihood maximization approach to multiuser detection

In this paper, we address the maximum-likelihood (ML) multiuser detection problem for asynchronous code-division multiple access (CDMA) systems with multiple receiver antennas in frequency-selective fading environments. Multiuser ML detection (MLD) in this case provides attractive symbol error performance, but it requires the solution of a large-scale combinatorial optimization problem. To deal with the computational complexity of this problem, we propose an efficient approximation method based on a block alternating likelihood maximization (BALM) principle. The idea behind BALM is to decompose the large-scale MLD problem into smaller subproblems. Assuming binary or quaternary phase shift keying (BPSK or QPSK) (which are often employed in CDMA), the combinatorial subproblems are then accurately and efficiently approximated by the semidefinite relaxation (SDR) algorithm-an algorithm that has been recently shown to lead to quasi-ML performance in synchronous CDMA scenarios. Simulation results indicate that this BALM detector provides close-to-optimal bit error rate (BER) performance. The BALM principle is quite flexible, and we demonstrate this flexibility by extending BALM to multicarrier (MC) multiuser systems. By exploiting the special signal correlation structure of MC systems, we develop a variation of BALM in which dynamic programming (DP) is used to solve the subproblems. It is shown using simulations that the BER performance of this DP-based BALM detector is as promising as that of the SDR-based BALM detector.     

Accurate image registration for MAP image super-resolution

The accuracy of image registration plays a dominant role in image super-resolution methods and in the related literature, landmark-based registration methods have gained increasing acceptance in this framework. In this work, we take advantage of a maximum a posteriori (MAP) scheme for image super-resolution in conjunction with the maximization of mutual information to improve image registration for super-resolution imaging. Local as well as global motion in the low-resolution images is considered. The overall scheme consists of two steps. At first, the low-resolution images are registered by establishing correspondences between image features. The second step is to fine-tune the registration parameters along with the high-resolution image estimation, using the maximization of mutual information criterion. Quantitative and qualitative results are reported indicating the effectiveness of the proposed scheme, which is evaluated with different image features and MAP image super-resolution computation methods.     

图像配准技术研究进展

图像配准是解决图像融合、图像镶嵌和变化检测等问题的必要前提,其应用遍及军事、遥感、医学和计算机视觉等多个领域.简要回顾了图像配准技术的发展史和研究现状,重点阐述了当前的技术热点和应用趋势,最后展望了进一步的研究方向.     

Hybrid retinal image registration.

This work studies retinal image registration in the context of the National Institutes of Health (NIH) Early Treatment Diabetic Retinopathy Study (ETDRS) standard. The ETDRS imaging protocol specifies seven fields of each retina and presents three major challenges for the image registration task. First, small overlaps between adjacent fields lead to inadequate landmark points for feature-based methods. Second, the non-uniform contrast/intensity distributions due to imperfect data acquisition will deteriorate the performance of area-based techniques. Third, high-resolution images contain large homogeneous nonvascular/texureless regions that weaken the capabilities of both feature-based and area-based techniques. In this work, we propose a hybrid retinal image registration approach for ETDRS images that effectively combines both area-based and feature-based methods. Four major steps are involved. First, the vascular tree is extracted by using an efficient local entropy-based thresholding technique. Next, zeroth-order translation is estimated by maximizing mutual information based on the binary image pair (area-based). Then image quality assessment regarding the ETDRS field definition is performed based on the translation model. If the image pair is accepted, higher-order transformations will be involved. Specifically, we use two types of features, landmark points and sampling points, for affine/quadratic model estimation. Three empirical conditions are derived experimentally to control the algorithm progress, so that we can achieve the lowest registration error and the highest success rate. Simulation results on 504 pairs of ETDRS images show the effectiveness and robustness of the proposed algorithm.     

Image registration by maximization of combined mutual information and gradient information

Mutual information has developed into an accurate measure for rigid and affine monomodality and multimodality image registration. The robustness of the measure is questionable, however. A possible reason for this is the absence of spatial information in the measure. The present paper proposes to include spatial information by combining mutual information with a term based on the image gradient of the images to be registered. The gradient term not only seeks to align locations of high gradient magnitude, but also aims for a similar orientation of the gradients at these locations. Results of combining both standard mutual information as well as a normalized measure are presented for rigid registration of three-dimensional clinical images [magnetic resonance (MR), computed tomography (CT), and positron emission tomography (PET)]. The results indicate that the combined measures yield a better registration function does mutual information or normalized mutual information per se. The registration functions are less sensitive to low sampling resolution, do not contain incorrect global maxima that are sometimes found in the mutual information function, and interpolation-induced local minima can be reduced. These characteristics yield the promise of more robust registration measures. The accuracy of the combined measures is similar to that of mutual information-based methods.     

Fast parametric elastic image registration

We present an algorithm for fast elastic multidimensional intensity-based image registration with a parametric model of the deformation. It is fully automatic in its default mode of operation. In the case of hard real-world problems, it is capable of accepting expert hints in the form of soft landmark constraints. Much fewer landmarks are needed and the results are far superior compared to pure landmark registration. Particular attention has been paid to the factors influencing the speed of this algorithm. The B-spline deformation model is shown to be computationally more efficient than other alternatives. The algorithm has been successfully used for several two-dimensional (2-D) and three-dimensional (3-D) registration tasks in the medical domain, involving MRI, SPECT, CT, and ultrasound image modalities. We also present experiments in a controlled environment, permitting an exact evaluation of the registration accuracy. Test deformations are generated automatically using a random hierarchical fractional wavelet-based generator.     

Performance bounds on image registration

Registration is a fundamental step in image processing systems where there is a need to match two or more images. Applications include motion detection, target recognition, video processing, and medical imaging. Although a vast number of publications have appeared on image registration, performance analysis is usually performed visually, and little attention has been given to statistical performance bounds. Such bounds can be useful in evaluating image registration techniques, determining parameter regions where accurate registration is possible, and choosing features to be used for the registration. In this paper, Crame/spl acute/r-Rao bounds on a wide variety of geometric deformation models, including translation, rotation, shearing, rigid, more general affine and nonlinear transformations, are derived. For some of the cases, closed-form expressions are given for the maximum-likelihood (ML) estimates, as well as their variances, as space permits. The bounds are also extended to unknown original objects. Numerical examples illustrating the analytical performance bounds are presented.