基于最大互信息和相关法的医学图象配准

本文提出了一种医学图象配准的方法,该方法分两步第一步采用搜索最大互信息的方法对图象做粗配准,使得参考图象与待配准图象大致一致;第二步采用快速相关法对图象做精细配准,从而获得医学图象的最优配准.由于此种算法具有良好的扩展性,所以既可用于多模医学图象的配准,也可用于单模医学图象的配准.     

三维医学图象可视化技术综述

概要地分析和评述了近年来三维医学图象可视化技术的发展,并主要从三维医学图象的分割标注、多模态医学图象的数据整合、体数据的绘制等3个角度对三维医学图象的可视化技术进行了分类综述,同时介绍了各种算法的原理和最新进展,由于医学图象可视化的目的是辅助医学了解生物内部组织的信息,因此除图象绘制技术外,组织及组织特性的精确自动分割标注技术,以及将不同图象模态提供的互补信息综合起来的匹配/融合技术外,都是医学图象可视化需要解决的重要问题,其中,多模态图象的可视化在三维医学图象可视化领域中最具有挑战性和发展前景。     

一种新的基于Legendre矩的fMRI图像配准方法

提出了一种脑功能磁共振图像配准的方法。Legendre正交矩可以用来作为图像配准的策略，它的快速计算至关重要，边界的拟合精度和速度对Legendre矩的计算影响很大。根据推导出的Legendre矩的边界特点，提出了采用四连通链码法和改进的矢量斜率法进行边界拟台，从而解决了Legendre矩快速计算的问题。采用遗传算法进行多参数配准策略优化，避免了局部极值的干扰。改进的Legendre矩配准方法是一种快速脑功能图像配准方法。     

基于自适应自由变形法和梯度下降法的胸部多模医学图像配准*

为了实现胸部多模态医学图像的自动配准,提出了一种基于层次B样条自适应自由变形法和梯度下降法的配准方法。首先采用GVF Snake与Canny算子实现边缘提取,并自动配对特征点;接着,采用矩主轴法对多模医学图像进行全局粗配准;最后,基于层次B样条自适应自由变形法对多模态医学图像进行自动细配准,并且采用梯度下降法以及最大信息熵准则加速求自由变形系数。实验证明该方法不仅效率高,而且配准效果好。     

胸部多模医学图像快速配准

为了实现胸部多模态医学图像的自动配准,提出了一种基于层次B样条自适应自由变形的快速配准方法。首先采用C-V水平集方法实现感兴趣区域的提取,并基于并行计算实现自动配对特征点;接着,采用矩主轴法对多模医学图像进行全局粗配准;最后,基于层次B样条自适应自由变形法对多模态医学图像进行自动细配准,并且采用梯度下降法以及最大信息熵准则加速求自由变形系数。实验证明该方法不仅效率高,而且配准效果好。     

基于多通道稀疏编码的非刚性多模态医学图像配准

针对稀疏编码相似性测度在非刚性医学图像配准中对灰度偏移场具有较好的鲁棒性,但只适用于单模态医学图像配准的问题,提出基于多通道稀疏编码的非刚性多模态医学图像配准方法。该方法将多模态配准问题视为一个多通道配准问题来解决,每个模态在一个单独的通道下运行;首先对待配准的两幅图像分别进行合成和正则化,然后划分通道和图像块,使用K奇异值分解（K-SVD）算法训练每个通道中的图像块得到分析字典和稀疏系数,并对每个通道进行加权求和,采用多层P样条自由变换模型来模拟非刚性几何形变,结合梯度下降法优化目标函数。实验结果表明,与局部互信息、多通道局部方差和残差复杂性（MCLVRC）、多通道稀疏诱导的相似性测度（MCSISM）、多通道Rank Induced相似性测度（MCRISM）多模态相似性测度相比,均方根误差分别下降了30.86%、22.24%、26.84%和16.49%。所提方法能够有效克服多模态医学图像配准中灰度偏移场对配准的影响,提高配准的精度和鲁棒性。     

基于联合直方图区域计数的时间序列图象自动配准方法

时间序列图象的配准是医学临床科研、诊断和治疗中图象应用的必要步骤。为了快速、准确、简便地进行医学序列图象配准，提出了一种新的用于时间序列图象自动配准的方法，该方法利用了图象的联合直方图，首先通过对图象做简单的阈值分割，将联合直方图划分为4个区域，然后根据不同的配准图象数据选择定义在不同区域上的计数值作为参数计算的准则函数。该方法设计简单、巧妙，以计数方法代替其他方法中大量的浮点运算。由于准则函数具有良好的光滑特性，且选择Powell算法做最优化搜索，因此保证了优化结果的准确性。和其他算法相经，该方法大大简化了准则函数的计算，从而显著提高了配准优化搜索的速度。根据实验结果及基于互信息量方法做的对比，证明本文提出的方法准确、简便、快速、有效。     

残差密集相对平均CGAN的脑部图像配准

目的 针对图像合成配准算法中鲁棒性差及合成图像特征信息不足导致配准精度不高的问题,提出了基于残差密集相对平均条件生成对抗网络（residual dense-relativistic average conditional generative adversarial network,RD-RaCGAN）的多模态脑部图像配准方法。方法 相对平均生成对抗网络中的相对平均鉴别器能够增强模型稳定性,条件生成对抗网络加入条件变量能提高生成数据质量,结合两种网络特点,利用残差密集块充分提取深层网络特征的能力,构建RD-RaCGAN合成模型。然后,待配准的参考CT（computed tomography）和浮动MR（magnetic resonance）图像通过已训练好的RD-RaCGAN合成模型双向合成对应的参考MR和浮动CT图像。采用区域自适应配准算法,从参考CT和浮动CT图像中选取骨骼信息的关键点,从浮动MR和参考MR图像中选取软组织信息的关键点,通过提取的关键点指导形变场的估计。从浮动CT图像到参考CT图像估计一个形变场。类似地,从浮动MR图像到参考MR图像估计一个形变场。另外,采用分层对称的思想进一步优化两个形变场,当两个形变场之间的差异达到最小时,将两个形变场融合得到最终的形变场,并将形变场作用于浮动图像完成配准。结果 实验结果表明,与其他6种图像合成方法相比,本文模型合成的目标图像在视觉效果和客观评价指标上均优于其他方法。对比Powell优化的MI（mutual information）法、ANTs-SyN（advanced normalization toolbox-symmetric normalization）、D.Demons（diffeomorphic demons）、Cue-Aware Net（cue-aware deep regression network）和I-SI（intensity and spatial information）的图像配准方法,归一化互信息分别提高了43.71%、12.87%、10.59%、0.47%、5.59%,均方根误差均值分别下降了39.80%、38.67%、15.68%、4.38%、2.61%。结论 本文提出的多模态脑部图像配准方法具有很强的鲁棒性,能够稳定、准确地完成图像配准任务。     

基于分窗口相关的遥感图象配准方法

多源遥感数据的融合和综合应用必须实行严格的配准,若将通过选取控制点的传统方法,用于成象特性差异较大的图象间配准就存在较大的误差,为解决该问题,研究发展了一种基于分窗口相关的图象配准方法,即采用移动窗灰度相关的方法对图象上的每一点进行搜索,来寻找最大相关位置,以达到精确配准的目的。通过将该方法应用于不同时相的TM图象、SAR图象、不同成象方式和不同分辨率的AVIRIS图象和航片间配准的实验表明,该方法能够有效地实现复杂图象间的精确配准,配准误差已达到子象素级水平。     

基于最大互信息的多模医学图象配准

介绍了一种基于最大互信息原理的图象配准技术,并就实施最大互信息配准法的一些重要技术问题进行了研究,其中包括不增加新数据点的格点采样子集、不产生分数灰度值的ＰＶ插值技术和出界点策略等。该方法在搜索策略上采用了无需计算梯度的Ｐｏｗｅｌｌ算法。由于计算互信息的关键技术与有效的搜索策略的结合,使得该方法能快速、准确地实现多模医学图象的配准。用该方法对７个病人的４１套ＣＴ－ＭＲ和３５套ＭＲ－ＰＥＴ３Ｄ全脑数     

基于小波统计特性的CT/MR医学影像优化融合方法

多模医学影像融合技术服务于临床诊断具有十分重要的意义。计算机断层摄像CT(ComputerTomography)仅能清晰显示人体骨骼组织,而磁共振成像MR(MagneticResonance)具有软组织对比分辨率高的特点。论文提出了一种基于小波统计特性的CT、MR医学颅脑部影像优化融合方法,采用信息熵和边缘保持度两项指标作为优化融合依据,获得的融合影像有效地综合CT与MR影像信息,可同时清晰地显示脑部骨组织和软组织信息。     

DiCyc: GAN-based deformation invariant cross-domain information fusion for medical image synthesis

Cycle-consistent generative adversarial network (CycleGAN) has been widely used for cross-domain medical image synthesis tasks particularly due to its ability to deal with unpaired data. However, most CycleGAN-based synthesis methods cannot achieve good alignment between the synthesized images and data from the source domain, even with additional image alignment losses. This is because the CycleGAN generator network can encode the relative deformations and noises associated to different domains. This can be detrimental for the downstream applications that rely on the synthesized images, such as generating pseudo-CT for PET-MR attenuation correction. In this paper, we present a deformation invariant cycle-consistency model that can filter out these domain-specific deformation. The deformation is globally parameterized by thin-plate-spline (TPS), and locally learned by modified deformable convolutional layers. Robustness to domain-specific deformations has been evaluated through experiments on multi-sequence brain MR data and multi-modality abdominal CT and MR data. Experiment results demonstrated that our method can achieve better alignment between the source and target data while maintaining superior image quality of signal compared to several state-of-the-art CycleGAN-based methods.     

3D multimodality medical image registration using morphological tools

Multimodal medical images are often of too different a nature to be registered on the basis of the image grey values only. It is the purpose of this paper to construct operators that extract similar structures from these images that will enable rigid registration by simple grey value based methods, such as maximization of cross-correlation. These operators can be constructed using only basic morphological tools such as erosion and dilation. Simple versions of these operators are easily implemented on any computer system. We will show that accurate registration of images of various modalities (MR, CT, SPECT and PET) can be obtained using this approach.     

Multimodal image registration system for image-guided orthopaedic surgery

We present a novel multimodality image registration system for spinal surgery. The system comprises a surface-based algorithm that performs computed tomography/magnetic resonance (CT/MR) rigid registration and MR image segmentation in an iterative manner. The segmentation/registration process progressively refines the result of MR image segmentation and CT/MR registration. For MR image segmentation, we propose a method based on the double-front level set that avoids boundary leakages, prevents interference from other objects in the image, and reduces computational time by constraining the search space. In order to reduce the registration error from the misclassification of the soft tissue surrounding the bone in MR images, we propose a weighted surface-based CT/MR registration scheme. The resultant weighted surface is registered to the segmented surface of the CT image. Contours are generated from the reconstructed CT surfaces for subsequent MR image segmentation. This process iterates till convergence. The registration method achieves accuracy comparable to conventional techniques while being significantly faster. Experimental results demonstrate the advantages of the proposed approach and its application to different anatomies.     

Convolutional neural network-based multimodal image fusion via similarity learning in the shearlet domain

Neural Computing and Applications - Recently, deep learning has been shown effectiveness in multimodal image fusion. In this paper, we propose a fusion method for CT and MR medical images based on...     

Medical image registration based on self-adapting pulse-coupled neural networks and mutual information

Medical image registration plays a dominant role in medical image analysis and clinical research. In this paper, we present a new coarse-to-fine method based on pulse-coupled neural networks (PCNNs) and mutual information (MI). In the coarse-registration process, we use the PCNN-clusters’ invariant characteristics of translation, rotation and distortion to get the coarse parameters. And the parameters of the PCNN model are optimized by ant colony optimization algorithm. In the fine-registration process, the coarse parameters provide a near-optimal initial solution. Based on this, the fine-tuning process is implemented by mutual information using the particle swarm optimization algorithm to search the optimal parameters. For the purpose of proving the proposed method can deal with medical image registration automatically, the experiments are carried out on MR and CT images. The comparative experiments on MI-based and SIFT-based methods for medical image registration show that the proposed method achieves higher performance in accuracy.     

三维医学图像配准在图像引导放疗中的应用

为了确定病人的摆位误差,实现精确放疗,提出一种改进的Demons弹性配准算法。采用FDK算法对锥形束CT(CBCT)图像进行三维重建,利用可视化工具包 (VTK)体绘制法可视化重建结果;在分割与配准工具包 (ITK)基础上实现Demons算法,并基于对称梯度的思想,将参考图像和浮动图像的梯度场信息加入到Demons算法中,给出新的Demons形变力公式。分别使用单模态和多模态医学图像进行配准实验,结果显示改进的Demons算法与原始Demons算法相比,配准速度更快、精度更高。基于对称梯度的Demons算法更适用于图像引导放射治疗中CBCT重建图像与CT计划图像间的配准。     

Image registration by local histogram matching

We previously presented an image registration method, referred to hierarchical attribute matching mechanism for elastic registration (HAMMER), which demonstrated relatively high accuracy in inter-subject registration of MR brain images. However, the HAMMER algorithm requires the pre-segmentation of brain tissues, since the attribute vectors used to hierarchically match the corresponding pairs of points are defined from the segmented image. In many applications, the segmentation of tissues might be difficult, unreliable or even impossible to complete, which potentially limits the use of the HAMMER algorithm in more generalized applications. To overcome this limitation, we have used local spatial intensity histograms to design a new type of attribute vector for each point in an intensity image. The histogram-based attribute vector is rotationally invariant, and importantly it also captures spatial information by integrating a number of local intensity histograms from multi-resolution images of original intensity image. The new attribute vectors are able to determine the corresponding points across individual images. Therefore, by hierarchically matching new attribute vectors, the proposed method can perform as successfully as the previous HAMMER algorithm did in registering MR brain images, while providing more generalized applications in registering images of various organs. Experimental results show good performance of the proposed method in registering MR brain images, DTI brain images, CT pelvis images, and MR mouse images.