改进的粒子群算法多模态生物医学图像配准

多模态生物医学图像配准在医疗诊断、治疗方案的制定,以及身体机能的研究等方面起到越来越大的作用。如何将这些多模态信息融合在一起是目前研究的重点,目前,该融合主要基于图像强度信息的配准方法。该类方法通过最大化化图像间的相似度函数达到配准的目的,但配准过程中使用往往会出现参数变化非凸且不光滑的现象,因而,传统的局部最优方法通常不能得到较好的结果。粒子群算法是一种全局寻优算法,但传统的方法中受初始值的选取以及当前全局最优点的影响,易陷入局部最优。本文对其进行改进,使得即使在初始值离准确值较远时也能得到全局最优,并将该方法用于多模态医学图像配准中,得到了较好的结果。     

An approach to multimodal biomedical image registration utilizing particle swarm optimization

Biomedical image registration, or geometric alignment of two-dimensional and/or three-dimensional (3D) image data, is becoming increasingly important in diagnosis, treatment planning, functional studies, computer-guided therapies, and in biomedical research. Registration based on intensity values usually requires optimization of some similarity metric between the images. Local optimization techniques frequently fail because functions of these metrics with respect to transformation parameters are generally nonconvex and irregular and, therefore, global methods are often required. In this paper, a new evolutionary approach, particle swarm optimization, is adapted for single-slice 3D-to-3D biomedical image registration. A new hybrid particle swarm technique is proposed that incorporates initial user guidance. Multimodal registrations with initial orientations far from the ground truth were performed on three volumes from different modalities. Results of optimizing the normalized mutual information similarity metric were compared with various evolutionary strategies. The hybrid particle swarm technique produced more accurate registrations than the evolutionary strategies in many cases, with comparable convergence. These results demonstrate that particle swarm approaches, along with evolutionary techniques and local methods, are useful in image registration, and emphasize the need for hybrid approaches for difficult registration problems.     

显式重定向的扩散张量图像配准

扩散张量图像配准算法是近年图像配准研究的热点与难点之一.针对配准中容易出现的局部极值和张量重定向问题,以欧氏距离为相似性测度,将张量重定向显式融入目标函数,采用模拟退火算法与Powell算法法相结合的混合优化策略,对临床使用的扩散张量图像DTI(Diffusion Tensor Images)进行配准实验.实验结果表明,该算法稳定性良好,在对扩散张量图像进行配准时,能有效保持扩散张量主特征方向与纤维走向的一致性,同时成功解决了局部极值的困扰,是一种实用的扩散张量图像配准方法.     

基于互信息和随机优化的超光谱遥感图像配准

精确的谱间配准是从超光谱遥感图像中获取光谱信息的基本前提之一。而谱间配准的主要困难在于宽的成像光谱范围使波长间隔远的图像缺乏相似性, 超光谱图像本身海量的数据也限制了配准算法的复杂性。提出了一种结合互信息和随机优化技术的多分辨率配准方法。该方法采用互信息作为相似性测度, 能很好的适应超光谱图像光谱特征的变化; 二阶同步试探随机逼近(2SPSA )算法的应用, 解决了互信息的多变量优化问题; 通过一种具有平移和旋转不变性的小波分解实现算法的多分辨率形式, 能明显加快算法的收敛速度并保证搜索结果的全局最优性。实验结果表明该算法适用于配准波长范围很宽的超光谱图像, 并能达到子像素的配准精度。     

多元互信息在超光谱图像自动配准中的应用

文章提出了一种超光谱图像的高精度自动配准算法。该算法采用多元互信息作为相似性测度,能同时利用多个波段图像的可知信息,并能很好地克服图像光谱特征变化的影响;同时,随机优化算法二阶同步试探随机逼近算法(2SPSA)的应用解决了多元互信息的多参数优化问题;另外,算法的多分辨率实现形式,能明显加快搜索速度并增强优化算法的鲁棒性。实验结果表明该算法能有效地处理超光谱图像配准问题,并能达到亚像素的配准精度。     

基于改进的Zernike矩的局部描述符与图割离散优化的非刚性多模态脑部图像配准

针对脑部图像中存在噪声和强度失真时，基于结构信息的方法不能同时准确提取图像强度信息和边缘、纹理特征，并且连续优化计算复杂度相对较高的问题，根据图像的结构信息，提出了基于改进Zernike距的局部描述符（IZMLD）和图割（GC）离散优化的非刚性多模态脑部图像配准方法。首先，将图像配准问题看成是马尔可夫随机场（MRF）的离散标签问题，并且构造能量函数，两个能量项分别由位移矢量场的像素相似性和平滑性组成。其次，采用变形矢量场的一阶导数作为平滑项，用来惩罚相邻像素间有较大变化的位移标签；用基于IZMLD计算的相似性测度作为数据项，用来表示像素相似性。然后，在局部邻域中用图像块的Zernike矩来分别计算参考图像和浮动图像的自相似性并构造有效的局部描述符，把描述符之间的绝对误差和（SAD）作为相似性测度。最后，将整个能量函数离散化，并且使用GC的扩展优化算法求最小值。实验结果表明，与基于结构表示的熵图像的误差平方和（ESSD）、模态独立邻域描述符（MIND）和随机二阶熵图像（SSOEI）的配准方法相比，所提算法目标配准误差的均值分别下降了18.78%、10.26%和8.89%，并且比连续优化算法缩短了约20 s的配准时间。所提算法实现了在图像存在噪声和强度失真时的高效精确配准。     

MetricFusion: Generalized metric swarm learning for similarity measure

Learning distance metrics for measuring the similarity between two data points in unsupervised and supervised pattern recognition has been widely studied in unconstrained face verification tasks. Motivated by the fact that enforcing single distance metric learning for verification via an empirical score threshold is not robust in uncontrolled experimental conditions, we therefore propose to obtain a metric swarm by learning local patches alike sub-metrics simultaneously that naturally formulates a generalized metric swarm learning (GMSL) model with a joint similarity score function solved by an efficient alternative optimization algorithm. Further, each sample pair is represented as a similarity vector via the well-learned metric swarm, such that the face verification task becomes a generalized SVM-alike classification problem. Therefore, the verification can be enforced in the represented metric swarm space that can well improve the robustness of verification under irregular data structure. Experiments are preliminarily conducted using several UCI benchmark datasets for solving general classification problem. Further, the face verification experiments on real-world LFW and PubFig datasets demonstrate that our proposed model outperforms several state-of-the-art metric learning methods.     

一种新的卫星多光谱图像自动配准算法

针对小卫星独立相机多光谱成像系统波段间配准的非线性误差问题,提出了一种多光谱图像波段间自动配准算法,该算法综合利用互信息、遗传算法和MQ几何校正模型进行多光谱图像的自动配准。在算法中,以互信息作为配准的相似性度量,获得了很高的配准精度;利用遗传算法的快速搜索特性,可以较快的完成搜索并获得整体的最优解;利用MQ几何模型可以精确的建立图像之间的几何关系。试验表明该算法对于多光谱图像波段间非线性几何关系,能够取得非常高的波段间自动配准精度,整体配准误差在一个像元以内。     

An improved quantum-behaved particle swarm optimization and its application to medical image registration

This paper investigates the quantum-behaved particle swarm optimization (QPSO) algorithm from the perspective of estimation of distribution algorithm (EDA) which reveals the reason of QPSO's superiority. A revised QPSO (RQPSO) technique with a novel iterative equation is also proposed. The modified technique is deduced from the distribution function of the sum of two random variables with exponential and normal distribution, respectively. We present a diversity-controlled RQPSO (DRQPSO) algorithm, which helps prevent the evolutionary algorithms’ tendency to be easily trapped into local optima as a result of rapid decline in diversity. Both the RQPSO and DRQPSO are tested on three benchmark functions, as well as in medical image registration for performance comparison with the particle swarm optimization and QPSO.     

使用特征点与灰度值的医学图像局部配准方法

针对医学图像配准中,存在某些图像间大部分区域没有差异或者存在差异但不被关心的情况,提出了一种局部图像配准方法。该方法使用局部可控的紧支撑径向基函数作为配准变换函数,通过在感兴趣区域设置特征点,将变换函数作用范围限制在图像中某一特定区域,保持其他区域不发生变形。利用图像间的互信息量作为测度函数,更加精确地求解变换函数。在优化策略的选择中,将图像配准看作为寻优过程,采用基于小生境的遗传算法优化变换函数参数,能够克服经典遗传算法早熟、搜索能力差等缺点。通过对已知变换函数的仿真图像与真实医学图像进行实验,结果表明该算法能够准确地找到较优的变换函数,并且将作用区域限制在较小范围内。该方法结合了基于特征点和基于像素配准方法的优点,有效的搜索策略保证了变换函数准确性,是一种可行的、鲁棒的局部医学图像配准方法。     

Image registration by compression

Image registration consists in finding the transformation that brings one image into the best possible spatial correspondence with another image. In this paper, we present a new framework for image registration based on compression. The basic idea underlying our approach is the conjecture that two images are correctly registered when we can maximally compress one image given the information in the other. The contribution of this paper is twofold. First, we show that image registration can be formulated as a compression problem. Second, we demonstrate the good performance of the similarity metric, introduced by Li et al., in image registration. Two different approaches for the computation of this similarity metric are described: the Kolmogorov version, computed using standard real-world compressors, and the Shannon version, calculated from an estimation of the entropy rate of the images.     

改进混合策略的多分辨率3D医学图像配准

基于混合策略的多分辨率算法是当前3D医学图像刚体配准中普遍采用的方法,不过其仅仅是优化算法的混合。通过研究不同分辨率对一阶互信息（常称为互信息）和二阶互信息配准的影响,在二级多分辨率策略的配准中,各级采用相对更适合的相似性测度,提出了混合优化算法和混合测度的改进算法。实验表明,改进算法在配准精度上达到了亚体素级,且明显优于基于单一测度的算法,在配准速度上远远快于基于二阶互信息单一测度的算法,略慢于基于一阶互信息单一测度的算法。     

An improved biogeography based optimization approach for segmentation of human head CT-scan images employing fuzzy entropy

The present paper proposes the development of a three-level thresholding based image segmentation technique for real images obtained from CT scanning of a human head. The proposed method utilizes maximization of fuzzy entropy to determine the optimal thresholds. The optimization problem is solved by employing a very recently proposed population-based optimization technique, called biogeography based optimization (BBO) technique. In this work we have proposed some improvements over the basic BBO technique to implement nonlinear variation of immigration rate and emigration rate with number of species in a habitat. The proposed improved BBO based algorithm and the basic BBO algorithm are implemented for segmentation of fifteen real CT image slices. The results show that the proposed improved BBO variants could perform better than the basic BBO technique as well as genetic algorithm (GA) and particle swarm optimization (PSO) based segmentation of the same images using the principle of maximization of fuzzy entropy.     

A hybrid watermarking technique applied to digital images

In this paper, a hybrid watermarking technique applied to digital images is proposed. A watermarking technique is to insert copyright information into digital images that the ownerships can be declared. A fundamental problem for embedding watermarks is that the ways of pursuing transparency and robustness are always trade-off. To solve this problem, a hybrid watermarking technique is proposed to improve the similarity of extracted watermarks. In the proposed technique, the parameters of perceptual lossless ratio (PLR) for two complementary watermark modulations are first derived. Furthermore, a hybrid algorithm based on genetic algorithm (GA) and particle swarm optimization (PSO) is simultaneously performed to find the optimal values of PLR instead of heuristics. From simulation results, it shows the superiority of the proposed hybrid watermarking technique for digital images.     

Medium-low resolution multisource remote sensing image registration based on SIFT and robust regional mutual information

Owing to significant geometric distortions and illumination differences, high precision and robust matching of multisource remote sensing images is a difficult task. To solve this, mutual information (MI)-based methods have been a preferred choice, as MI represents a measure of statistical dependence between the two images. However, MI only considers original grey information and neglects spatial information in the calculation of the probability distribution. In this paper, a novel similarity metric based on rotationally invariant regional mutual information (RIRMI) is proposed. The RIRMI metric is constructed by combining MI with a regional information based on the statistical relationship between rotationally invariant centre-symmetric local binary patterns of the images. The similarity metric based on RIRMI considers not only the spatial information, but the effect of the local grey variations and rotation changes on computing probability density function as well. The proposed method is tested on various simulated remote sensing images (5–30 m GSD) and real remote sensing images (2–30 m GSD) which are taken at different sensors, spectral bands, and times. Results verify that RIRMI is more robust and accurate than the common MI-based registration method.     

Multimodal genetic algorithms-based algorithm for automatic point correspondence

In this paper, the problem of automatic determination of point correspondence between two images is formulated as a multimodal function optimization and the usefulness of genetic algorithms (GAs) as a multimodal optimizer is explored. Initially, a number of variations of GAs, capable of simultaneously discovering multiple extremes of an objective function are evaluated on a mathematical benchmark objective function with multiple unequal maxima. The variation of the GAs that performs best on the benchmark function, in terms of the number of maxima discovered, is selected for the determination of automatic point correspondence between two images. The selected variation of the GAs involves an iterative procedure for the formation of a genetic population of individuals (or chromosomes). Each individual encodes the position of a point of interest on one of the available images as well as parameters of a local transformation that generates the position of the corresponding point on the other image. The proposed algorithm aims to discover individuals that corresponds to local maxima of an objective function that measures the similarity between patches of the two images. When the GAs-based multimodal optimization algorithm terminates, pairs of corresponding points between the two images are obtained that can be used for the generation of a dense deformation field by means of the thin plate splines model.The proposed algorithm is applied to 2D medical images (dental and retinal images) under known transformations (similarity and elastic transformation) and is also assessed on medical images with unknown transformations (computer tomography transverse slices). The proposed algorithm is compared against the iterative closest point (ICP) algorithm, and a well-known non-rigid registration algorithm, based on free-form deformations (FFD) using various quantitative criteria. The obtained results indicate that in case of known similarity transformations, the proposed multimodal GAs-based algorithm and the ICP algorithm present equivalent performance, whereas the FFD algorithm is clearly outperformed. In the case of known sinousoidal deformations, the proposed multimodal GAs-based and the FFD algorithm achieve equivalent performance and clearly outperform the ICP algorithm. Finally, in the case of unknown elastic deformations, the proposed GAs-based algorithm appears to perform marginally better than the FFD algorithm, whereas it clearly outperforms the ICP algorithm.     

Information Theoretic Deformable Registration Using Local Image Information

We present a deformable registration algorithm for multi-modality images based on information theoretic similarity measures at the scale of individual image voxels. We derive analytical expressions for the mutual information, the joint entropy, and the sum of marginal entropies of two images over a small neighborhood in terms of image gradients. Using these expressions, we formulate image registration algorithms maximizing local similarity over the whole image domain in an energy minimization framework. This strategy produces highly elastic image alignment as the registration is driven by voxel similarities between the images, the algorithms are easily implementable using the closed-form expressions for the derivative of the optimization function with respect to the deformation, and avoid estimation of joint and marginal probability densities governing the image intensities essential to conventional information theoretic image registration methods. This work has been supported in part by NIH grants R01-NS42645 and R01-AG14971.     

改进的鸡群优化算法及其在DTI-FA图像配准中的应用

鸡群优化算法(Chicken Swarm Optimization,CSO)是一个全新的群智能优化算法,简单且具有良好的扩展性。针对鸡群优化算法中因为母鸡的寻优能力差而使算法容易陷入局部极值的问题,提出了一种结合混沌思想的改进鸡群优化算法(Chaotic Improved Chicken Swarm Optimization Algorithm,CICSO)。该算法结合混沌思想的遍历性初始化鸡群位置,将母鸡的位置更新公式改为仅向全局适应度值最好的公鸡学习,并引入学习系数来避免陷入局部最优。最后将改进的鸡群优化算法(CICSO)应用于DTI-FA图像配准。仿真实验结果表明,在解决高维问题时,改进的鸡群优化算法避免了陷入局部极值,提高了收敛精度,在DTI-FA图像配准中提高了图像的配准精确度。     

一种基于混合优化算法的医学图像配准方法

为了实现脑部多模医学图像配准,提出了一种基于混合优化算法的配准方法。该算法采用遗传算法中的杂交思想改进了混沌粒子群算法,并用最大互信息测度对脑部MRI及CT图像进行配准。该改进算法可有效地避免优化算子陷入局部极值,而且算法收敛快。实验结果证明了提出的基于遗传思想的改进混沌粒子群优化算法对多模医学图像配准具有有效性。     

结合形态学梯度互信息和多分辨率寻优的图像配准新方法

对互信息配准法进行算法改进. 在互信息基础上结合形态学梯度作为新的图像配准测度, 不仅考虑所有体素信息, 而且有效结合像素在空间位置的相互关系. 将粒子群优化 (Particle swarm optimization, PSO) 算法这种全局寻优算法和 Powell 这一局部寻优算法相结合, 前者的配准结果为后者的算法优化提供了非常有效的初始点, 优化时间大为减少. 借鉴小波变换中多分辨率的思想, 在低分辨率图像中粗略配准后, 上升到高分辨率图像上进一步细化配准结果, 增加算法鲁棒性. 实验结果证明, 本文算法效果良好, 寻优过程在数分钟内完成, 能够满足诊断和科研的实时性要求.