改进的小波域医学图像序列的运动估计

医学图像序列压缩是远程医疗系统中的重要技术，而运动估计在视频序列压缩中起着关键作用。我们提出了一种改进的正方形-菱形搜索算法来实现医学图像序列的运动估计。这种改进的正方形-菱形算法减少了搜索点数。我们将其应用于小波域的医学图像序列的运动估计，并对数字减影血管造影图像序列（DSA）进行实验。结果表明，改进后的小波域正方形-菱形算法较其他算法精度高。     

基于医学图像建立预测模型的应用现况

基于医学图像建立的预测模型,可以在一定程度上帮助临床医生对一些复杂及早期难发现的疾病进行诊断,而日益受到重视.在医学图像分析中采用的预测模型,主要包括数据挖掘算法、回归预测方法和时间序列预测法等.本文重点介绍数据挖掘算法和其他模型的应用情况、模型间的对比及联合应用效果,总体上模型联合应用的效果较好.     

基于高维混沌序列的医学图像加密

目的:本文利用高维混沌序列具有伪随机性、确定性和对初始条件与系统参数的极端敏感性的特点,将其用于医学图像的加密.方法:首先初始化高维混沌系统,通过解离散系统的迭代方程得到混沌序列,然后分别将该序列和待加密图像转化为八位二进制序列表示,最后对其进行异或操作便可得到加密图像序列;解密时只需要将加密图像作为输入到原加密系统中即可.结果:实验结果表明该方法具有快速、准确的特点,特别适合于医学图像的加密.结论:混沌序列的产生仅须一个,不需任何存储,实现方便简单.本算法对目前一维混沌序列用于加密时密钥空间小易于被破解等缺点做了改进,具有形式简单,生成速度快,密钥空间大等优点,对灰度图像,彩色图像和压缩图像都适用.     

基于小波变换的医学图像编码方法

高分辨率的医学图像具有很大的信息量,影响了整个数字化的远程医疗系统的实时性,因此必须在保证不丢失关键诊断信息的前提下,对医学图像进行必要的压缩.本文提出了在给定小波基下,基于二维小波分解和重构的快速压缩方法.该方法使用了向量量化技术并采用LBG算法设计码本.实验结果证明,采用该方法可获得较高的压缩比和符合诊断要求的压缩图像.     

利用互信息量准则实现医学序列图像的广义配准

通过扫描仪输入计算机的医学序列图像由于平移和旋转而失去配准,本文利用互信息量准则来解决这一问题。它是从信息解释的角度,认为在配准的情况下同一序列相邻两幅图像之间的互信息量为最大。此准则的意义在于通过各图像之间的配准来获取帧间相关,从而为医学序列图像的压缩提供前提条件。实验证明利用互信息量准则解决医学序列图像配准问题具有令人满意的结果。     

医学图像融合技术的研究

利用图像融合技术,将不同模态的医学图像有机地结合在一起,可以充分利用各种医学图像的优点,为临床诊断和治疗提供帮助.本文主要介绍了医学图像融合技术的基本概念、发展情况、常用方法及面临的困难等,并对医学图像的研究前景作了预测.     

一种基于三维约束的医学图像序列分割新方法

基于三维图像具有三维平滑、连续变化等特性,提出一种新的医学图像序列分割方法.该方法在计算过程中,只需手动设置第一幅图中主动形变模型的关键点位置.在其他图像中,首先采用预测和视频运动估计中常用的块匹配法优化主动轮廓模型的初始化位置,然后采用偏三维约束和梯度矢量流(GVF),从初始化位置开始在图像中进一步迭代收敛得到每幅图像中的最终轮廓位置.在一般的二维平滑基础上.达到三维平滑、三维分割的作用.与光流法、一般预测法等方法的实验结果相比,本方法可以显著提高分割的准确性及速度.     

医学图像检索研究

介绍了基于内容的医学图像检索系统的意义、方法和关键技术,分析了国内外医学图像检索领域的应用现状,并在此基础上探讨了基于内容的图像检索技术在医学图像检索领域的应用前景和未来的发展方向.     

灰度级别对基于互信息医学图像配准方法的影响

医学图像配准在医学图像处理领域中已经被广泛使用。基于互信息配准的方法具有自动化程度高、配准精度高等优点。基于互信息的配准方法实质上是一种进行灰度统计和计算的方法 ,因此同一图像采用不同的灰度表示必然会影响配准结果。在分析灰度级别的压缩对于图像质量的影响和基于互信息配准方法的影响的基础上 ,进行了一系列的多模态医学图像配准试验 ,从配准精度和计算时间两个方面比较了不同的灰度级别对图像配准的影响。在详细分析和比较不同级别图像配准结果的基础上 ,给出了基于互信息配准时所采用的合理灰度级别的建议。     

一种新颖的序列图像自动配准方法

序列图像的配准是医学临床与科研实践中扮演着非常重要的角色.为了快速、准确地进行医学序列图像配准,本文提出了一种利用图像联合直方图进行序列图像自动配准的新方法.首先对图像阈值分割,将其联合直方图划分为4个区域,然后根据不同的配准图像数据,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.和其他算法相比,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,及与基于互信息量方法的对比,证明该方法准确、简便、快速、有效.     

基于图像特征的CT-MR图像配准

本文采用了基于图像特征的相关性算法对3－D CT－MR图像进行配准。首先使用基于局部坐标系的二阶导数算子对CT和MR图像进行处理,获取由图像的“脊”或“谷”,组成的特征图像然,然后在进行刚体变换条件下对特征图像进行相关计算,使其相关系数达到最大,从而获取配准后的图像。该方法不需在成像过程中人为增加标记物,后续处理中不需人为干预,是一种自动的图像配准方法,最后本文给出了这一方法用于实际数据的结果。     

Spatiotemporal anisotropic diffusion filtering to improve signal-to-noise ratios and object restoration in fluorescence microscopic image sequences

We present an approach for significantly improving the quantitative analysis of motion in noisy fluorescence microscopic image sequences. The new partial differential equation based method is a general extension of a 2-D nonlinear anisotropic diffusion filtering scheme to a specially adapted 3-D nonlinear anisotropic diffusion filtering scheme, with two spatial image dimensions and the time t in the image sequence as the third dimension. Motion in image sequences is considered as oriented, line-like structures in the spatiotemporal x,y,t domain, which are determined by the structure tensor method. Image enhancement is achieved by a structure adopted smoothing kernel in three dimensions, thereby using the full 3-D information inherent in spatiotemporal image sequences. As an example for low signal-to-noise ratio (SNR) microscopic image sequences we have applied this method to noisy in vitro motility assay data, where fluorescently labeled actin filaments move over a surface of immobilized myosin. With the 3-D anisotropic diffusion filtering the SNR is significantly improved (by a factor of 3.8) and closed object structures are reliably restored, which were originally degraded by noise. Generally, this approach is very valuable for all applications where motion has to be measured quantitatively in low light level fluorescence microscopic image sequences of cellular, subcellular, and molecular processes.     

Automatic chart reader--an example of computer systems for patients' data interpretation

A new approach to the processing of circular medical charts based on "odd symmetry digital subtraction" is presented. The technique allows automatic digitisation of these charts using an image processing system based on a flat bed scanner. This approach is simple, fast, and reliable; and provides a system in which the digitised image is processed by a microcomputer to extract and quantify the plotted information. The main features and the potential applications of this approach in medical and nonmedical fields are discussed.     

Image reconstruction through turbid media under a transmission-mode microscope

In this paper, image enhancement and reconstruction through a turbid medium by utilizing polarization gating and mathematical image reconstruction methods in a microscopic imaging system are investigated. A Monte Carlo simulation model based on Mie theory and the concept of the effective point spread function (EPSF) is adopted to study image formation under a transmission-mode microscope. The results show that polarization gating methods, and particularly the differential polarization gating method, can be efficient in suppressing highly scattered light, which leads to a significant enhancement of image quality. An image reconstruction method based on the concept of the EPSF is demonstrated to be efficient in further improving image quality.     

基于多AGENT技术的CT图像检索

针对众多CT图像,利用多Agent技术,提出了一种新的图像检索方法。首先对原始图像库进行特征提取并分类,建立与类别相关的图像特征库,然后根据特征和权重按相似度匹配原则进行图像检索。检索过程由多Agent协同控制,反馈Agent依据待检索图像数据和用户反馈信息,对检索过程中的特征权重重置并更改图像库。实验结果表明该方法具有较好的检索效能。     

基于互信息医学刚性图像配准方法的研究

目的:基于互信息的配准方法是医学图像配准领域的重要方法,具有鲁棒性,精度高等优点。本文探究医学刚性图像配准的有效算法和关键技术。方法:基于互信息配准方法,利用Powell多参数算法和改进的PV插值算法,得到两幅图像之间的最大互信息和最佳配准参数。结果:二维磨牙CT图像配准实验表明,配准速度快,精度提高,验证了插值方法的有效性。结论:方法和算法可提高配准速度,能有效抑制互信息目标函数的局部极值。     

Application of X-ray grating interferometry for the imaging of joint structures

Conventional X-ray absorption contrast imaging does not depict soft tissues, such as cartilage, in sufficient detail. For visualization of the soft tissues, X-ray phase-contrast imaging is more sensitive than absorption-contrast imaging. The basic concept of the X-ray phase-contrast imaging used in this study is similar to that of differential interference contrast (Nomarski) microscopy. We applied Talbot–Lau X-ray interferometry to visualize the joint structures in the right hand and knee of a donated cadaver. This imaging system simultaneously produced three different types of images: an absorption image, a differential phase image, and a visibility image. The interface between the articular cartilage of the metacarpo-phalangeal joint and fluid or the bony cortex was clearly demonstrated on the differential phase image, whereas this interface was unclear on the absorption image. Within the knee joint, the surface of the articular cartilage was demonstrated both on the differential phase and visibility images; the medial collateral ligament and medial meniscus were also visualized successfully. These results are clinically significant for the diagnosis and therapeutic estimation of rheumatoid arthritis and related joint diseases. This feasibility study on the clinical application of this imaging tool was a collaborative effort of researchers in the fields of physics, radiology, and gross anatomy.     

Automatic segmentation of medical images using image registration: diagnostic and simulation applications

Automatic identification of the boundaries of significant structure (segmentation) within a medical image is an are of ongoing research. Various approaches have been proposed but only two methods have achieved widespread use: manual delineation of boundaries and segmentation using intensity values. In this paper we describe an approach based on image registration. A reference image is prepared and segmented, by hand or otherwise. A patient image is registered to the reference image and the mapping then applied to ther reference segmentation to map it back to the patient image. In general a high-resolution nonlinear mapping is required to achieve accurate segmentation. This paper describes an algorithm that can efficiently generate such mappings, and outlines the uses of this tool in two relevant applications. An important feature of the approach described in this paper is that the algorithm is independent of the segmentation problem being addresses. All knowledge about the problem at hand is contained in files of reference data. A secondary benefit is that the continuous three-dimensional mapping generated is well suited to the generation of patient-specific numerical models (e.g. finite element meshes) from the library models. Smoothness constraints in the morphing algorithm tend to maintain the geometric quality of the reference mesh.     

基于叠加DRR库的胸主动脉腔内修复术中CT血管造影与X线图像配准

目的胸主动脉腔内修复术(thoracic endovascular aortic repair,TEVAR)已经广泛应用于胸主动脉病变的治疗,成为传统主动脉开胸手术的可靠替代方案。然而,医生在术中看不到血管形态和位置,覆膜支架容易封堵主动脉重要分支而引发严重并发症。为了帮助医生导航支架,提出并实现了一种TEVAR术前CT血管造影(computed tomographic angiography,CTA)与术中X线图像的配准算法。方法首先,对影响CTA投影形状的参数高密度采样,利用采样获得的系列投影形变,分别对CTA全图和分割的CTA骨架进行数字影像重建(digitally reconstructed radiograph,DRR),将两者叠加起来,生成叠加DRR库;然后,以爬山优化,在叠加DRR库中寻找与X线图像归一化互信息最大的DRR图像,推算出投影形变,最终实现CTA与X线图像的配准。结果采用叠加DRR库的方法,配准了1例患者的术前CTA图像与一帧术中X线图像。与归一化互相关方法以及无骨架叠加的普通DRR库方法相比较,本方法获得了更为精确的配准结果。结论基于叠加DRR库的方法能有效配准术前CTA与术中X线图像。