基于图像分割的Tamura纹理特征算法的研究与实现***☆

背景：ITK主要提供医学图像处理、分割与配准算法,但其缺少可视化的功能,缺乏灵活实用的用户界面,VTK提供了丰富的医学影像处理与分析工具,具有强大的图形处理和可视化功能。 目的：利用以前的确诊病例和医生的诊断经验以及患者的相关病史,对确诊的医学影像资源进行管理,归档,并检索,以减少人工干预,提高图像的查全率和查准率。 方法：以视觉感知机制为基础,在ITK平台上进行图像平滑去噪和分割的预处理过程,利用Tamura算法完成纹理特征提取,最后通过实验采集、计算数据,完成对比分析。 结果与结论：基于图像分割的Tamura纹理特征算法在基于图像纹理检索应用上便于相似性度量,进而可提高检索的准确率。     

基于掩膜优化的多模态医学图像刚性配准

目的:基于配准开源平台ITK和开源计算机显示视觉库OpenCV开发刚性配准程序,并集成到DeepPlan计划系统中,实现快速准确的多模态刚性配准。方法:基于形态学开运算初步去除图像中无需关注的细小区域和部分扫描床,使用最大类间方差法(Otsu)突出感兴趣的图像部位,Canny算子用于提取富含信息区域的边界信息。使用像素填充技术得到图像配准需要的掩膜,并采用OpenMP并行技术加速掩膜计算过程。最终在配准过程中将掩膜作用于参考图像或浮动图像。结果:测试了多组不同模态和部位的算例,实验结果表明基于掩膜优化的多模态医学图像刚性配准方法可以自动去除绝大部分背景图像和扫描床板,节约图像配准中一半以上时间,且图像配准质量并无下降;在1 min内可以完成两组100张左右的图像配准。且本方法以动态链接库的形式成功集成在治疗计划系统DeepPlan中。结论:在保证配准结果准确的基础上,基于掩膜优化的多模态医学图像刚性配准方法显著提高了图像配准速度,且算法稳定性能高,有很好的临床应用前景。     

基于VIP-Man图谱配准的腹部器官分割方法

提出了一种基于图谱配准的腹部器官分割方法.首先将一套预标记图谱向个体图像进行配准,建立二者之间器官的基本对应关系,同时完成对感兴趣器官的识别,其中配准包含全局配准和器官配准.然后,借助已配准的图谱,采用模糊连接方法对感兴趣器官进行分割.腹PCT和MR实验测试结果证明:这种方法实现了模糊连接分割方法中各项参数的自动指定,减轻了人工负担,提高了结果的可靠性.     

基于最大互信息的人脑多模图像快速配准算法

对脑图谱开发过程中来源于不同成像设备的多模图像进行配准。对预处理后的数码图像和MRI图像,首先提取图像的轮廓,采用基于轮廓的力矩主轴法计算初始平移量和旋转量,然后设定初始缩放系数,将此初始配准参数作为改进单纯形法的初始参数,以互信息作为相似性测度迭代搜索,使互信息最大,从而实现最佳配准。结果表明本算法不需要人为预调整待配准图像的分辨率,自动化程度高,配准速度快,精度较高,能够满足脑图谱开发过程中的多模图像配准要求。     

灰度与形状同步匹配的非刚性配准研究

基于灰度的非刚性配准算法一般假设参考图像和浮动图像对应结构之间的灰度保持一致,然而在基于图谱的图像配准应用中,这种假设往往不符合实际。本文在给出一种可以同时校正灰度和形状差异的弹性配准算法的同时,针对该算法不能校正局部微小形变的弱点,提出采用自由项变换的方法进行校正以提高配准精度。配准实验基于20个IBSR真实脑部MRI图像,结果表明配准后图像与参考图像间的互相关系数得到明显提高。实验证明,本文提出的方法不仅能够同时校正形状差异和灰度变化,而且具有较高的配准质量。     

基于回归预测的肺4D-CT多相位配准

针对由于灰度不均和局部形变较大引起的肺4D-CT图像配准精度不足问题,提出基于回归的逐块预测初始形变的方法。新方法的核心思想是:配准一幅浮动图像至参考图像时,利用与浮动图像相对应的不同相位的图像信息进行形变场预测。首先,利用已有配准算法配准不同相位的图像至参考图像,得到各图像对应的形变场;再将图像和对应形变场分块作为训练集,利用多维支持向量回归机建立回归模型;将浮动图像分块输入回归模型中,预测出初始形变场,从而得到中间图像,并最终细化配准中间图像与参考图像。采用由德克萨斯安德森肿瘤中心DIR实验室采集并公开的数据集,评价所提出的算法。实验量化评价结果表明,与传统的Active Demons算法、Spectral Log-Demons算法相比,图像的均方误差平方和显著降低(Active Demons算法49.34±23.92,Spectral Log-Demons算法31.81±15.09,所提出算法18.97±5.75,P<0.05),相关系数显著提高(Active Demons算法0.952±0.022,Spectral Log-Demons算法0.967±0.015,所提出算法0.980±0.006,P<0.05)。同时,视觉评价结果显示,所提出算法能够获得更准确的配准图像。     

基于MRI和CT图像配准的颅内电极定位方法

目的应用多模医学图像配准,在颅内电极埋置术后对颅内电极进行精确定位。方法通过对颅内电极埋置前的头颅MRI图像和埋置后头颅CT图像进行配准,利用医学影像配准与分割工具包(ITK),将颅内电极位置准确地定位在MRI图像上,以建立电极位置与大脑解剖结构的联系。结果经过对10组断层图像进行配准定位,差值图像显示匹配程度较好,专家目测融合效果较为精确。在普通PC机上,以笔者所采用的数据为例,设定优化器初始步长为1,松弛因子为0.6,最小步长为0.000 2,最大迭代次数为100,整个电极定位的操作过程时间不超过1 min。结论多模医学图像配准对颅内电极定位较为准确,为医生提供了更加直观和完善的信息。     

结合脑图谱和水平集的MR图像分割的研究

本文利用脑图谱的先验知识并结合水平集等算法实现对脑MR图像的初步分割。主要步骤：（1）选取数字脑图谱，对图谱进行预处理；（2）实现图谱与脑MR图像的配准；（3）利用图谱提供的轮廓信息对水平集算法进行初始化，完成颅骨和脑脊液的提取以及脑白质和脑灰质的分割。实验结果表明，利用脑图谱提供的信息可有效解决水平集算法初始化问题，缩小求解空间，减少迭代次数，该方法具有较好的鲁棒性。     

基于灰度和形状的非刚性图像配准算法的研究

提出一种新的灰度和形状信息相结合的全自动同模态医学图像非刚性配准-分割算法,将欧氏距离表示的形状信息融入基于灰度的配准算法中,构造出新的代价函数.该算法在医学图像多目标分割的应用中,能够较好地完成灰度相近、边缘模糊、间距较小的不同结构的分割.对5组真实脑部MRI图像进行分割脑深层灰质结构的实验,结果表明,本算法优于基于灰度信息的图像配准算法.     

基于4D-CT最大呼吸气相位图像获取三维肺通气的信息

背景：传统的肺功能成像技术存在诸多不便,利用4D-CT中蕴含的通气信息进行功能图像的快速提取对肺部疾病的诊断和治疗有非常重要的意义。 目的：探讨基于三维变形图像配准算法从4D-CT最大吸气相位和最大呼气相位图像中获取肺通气的三维分布的可行性。 方法：利用电影模式采集自由呼吸状态下的胸部CT图像并利用已开发的4D-CT软件进行四维重建,得到吸气末和呼气末双相位CT图像,依次进行肺组织分割、利用基于体积的变形图像配准算法进行三维图像配准、量化分析三维空间象素的位移矢量,最后得到通气度量图即肺功能区的三维分布图。 结果与结论：利用三维变形图像配准算法,实现了从4D-CT最大吸气相位和最大呼气相位图像中获取在任意横断位、冠状位和矢状位的肺通气分布。     

MARS: a mouse atlas registration system based on a planar x-ray projector and an optical camera

This paper introduces a mouse atlas registration system (MARS), composed of a stationary top-view x-ray projector and a side-view optical camera, coupled to a mouse atlas registration algorithm. This system uses the x-ray and optical images to guide a fully automatic co-registration of a mouse atlas with each subject, in order to provide anatomical reference for small animal molecular imaging systems such as positron emission tomography (PET). To facilitate the registration, a statistical atlas that accounts for inter-subject anatomical variations was constructed based on 83 organ-labeled mouse micro-computed tomography (CT) images. The statistical shape model and conditional Gaussian model techniques were used to register the atlas with the x-ray image and optical photo. The accuracy of the atlas registration was evaluated by comparing the registered atlas with the organ-labeled micro-CT images of the test subjects. The results showed excellent registration accuracy of the whole-body region, and good accuracy for the brain, liver, heart, lungs and kidneys. In its implementation, the MARS was integrated with a preclinical PET scanner to deliver combined PET/MARS imaging, and to facilitate atlas-assisted analysis of the preclinical PET images.     

Matching of digitised brain atlas to magnetic resonance images

A method has been developed to match a standard digitised brain atlas onto MR images for identification of cerebral structures in anatomical images. This method uses, first, a three-dimensional crude registration based on the proportional system of Talairach. Then, a two-dimensional refined registration is performed using a deformation function based on a set of homologous landmarks on both images (MR and atlas). Displacements vectors are computed between each corresponding landmark. These vectors are interpolated by thin-plate splines, generating an unwarping function defined on the whole image. This function can then be applied on any structure of the atlas. An evaluation of the matching procedure has been performed. First, the influence of the choice of the landmarks has been evaluated for the fine registration method. The latter has been then compared to the crude registration method considered as a classical reference method. These results show the advantages of the fine registration approach.     

Automatic nonrigid registration of whole body CT mice images

Three-dimensional intra- and intersubject registration of image volumes is important for tasks that include quantification of temporal/longitudinal changes, atlas-based segmentation, computing population averages, or voxel and tensor-based morphometry. While a number of methods have been proposed to address this problem, few have focused on the problem of registering whole body image volumes acquired either from humans or small animals. These image volumes typically contain a large number of articulated structures, which makes registration more difficult than the registration of head images, to which the majority of registration algorithms have been applied. This article presents a new method for the automatic registration of whole body computed tomography (CT) volumes, which consists of two main steps. Skeletons are first brought into approximate correspondence with a robust point-based method. Transformations so obtained are refined with an intensity-based nonrigid registration algorithm that includes spatial adaptation of the transformation's stiffness. The approach has been applied to whole body CT images of mice, to CT images of the human upper torso, and to human head and neck CT images. To validate the authors method on soft tissue structures, which are difficult to see in CT images, the authors use coregistered magnetic resonance images. They demonstrate that the approach they propose can successfully register image volumes even when these volumes are very different in size and shape or if they have been acquired with the subjects in different positions.     

Automatic segmentation of the prostate in 3D MR images by atlas matching using localized mutual information

An automatic method for delineating the prostate (including the seminal vesicles) in three-dimensional magnetic resonance scans is presented. The method is based on nonrigid registration of a set of prelabeled atlas images. Each atlas image is nonrigidly registered with the target patient image. Subsequently, the deformed atlas label images are fused to yield a single segmentation of the patient image. The proposed method is evaluated on 50 clinical scans, which were manually segmented by three experts. The Dice similarity coefficient (DSC) is used to quantify the overlap between the automatic and manual segmentations. We investigate the impact of several factors on the performance of the segmentation method. For the registration, two similarity measures are compared: Mutual information and a localized version of mutual information. The latter turns out to be superior (median DeltaDSC approximately equal 0.02, p < 0.01 with a paired two-sided Wilcoxon test) and comes at no added computational cost, thanks to the use of a novel stochastic optimization scheme. For the atlas fusion step we consider a majority voting rule and the "simultaneous truth and performance level estimation" algorithm, both with and without a preceding atlas selection stage. The differences between the various fusion methods appear to be small and mostly not statistically significant (p > 0.05). To assess the influence of the atlas composition, two atlas sets are compared. The first set consists of 38 scans of healthy volunteers. The second set is constructed by a leave-one-out approach using the 50 clinical scans that are used for evaluation. The second atlas set gives substantially better performance (DeltaDSC=0.04, p < 0.01), stressing the importance of a careful atlas definition. With the best settings, a median DSC of around 0.85 is achieved, which is close to the median interobserver DSC of 0.87. The segmentation quality is especially good at the prostate-rectum interface, where the segmentation error remains below 1 mm in 50% of the cases and below 1.5 mm in 75% of the cases.     

Standard atlas space for C57BL/6J neonatal mouse brain

A standard atlas space with stereotaxic co-ordinates for the postnatal day 0 (P0) C57BL/6J mouse brain was constructed from the average of eight individual co-registered MR image volumes. Accuracy of registration and morphometric variations in structures between subjects were analyzed statistically. We also applied this atlas coordinate system to data acquired using different imaging protocols as well as to a high-resolution histological atlas obtained from separate animals. Mapping accuracy in the atlas space was examined to determine the applicability of this atlas framework. The results show that the atlas space defined here provides a stable framework for image registration for P0 normal mouse brains. With an appropriate feature-based co-registration strategy, the probability atlas can also provide an accurate anatomical map for images acquired using invasive imaging methods. The atlas templates and the probability map of the anatomical labels are available at .     

基于互信息的多分辨率三维脑图像配准方法

在3D多模医学图像的配准方法中，最大互信息法精度高，鲁棒性强，使用范围广，本文将归一化互信息作为相似性测度，采用不同的采样范围和采样子集，使用Powell多参数优化法和Brent一维搜索算法对3DCT，MR和PET脑图像进行了刚体配准，为了加快配准速度，使用了多分辨的金字塔方法，对PET图像采用基于坐标的阈值选取方法对图像进行分割预算法，消除了大部分放射状背景伪影，美国万德贝尔大学对结果进行的评估证明配准精度可达亚体元级。     

Adaptation of a 3D prostate cancer atlas for transrectal ultrasound guided target-specific biopsy

Due to lack of imaging modalities to identify prostate cancer in vivo, current TRUS guided prostate biopsies are taken randomly. Consequently, many important cancers are missed during initial biopsies. The purpose of this study was to determine the potential clinical utility of a high-speed registration algorithm for a 3D prostate cancer atlas. This 3D prostate cancer atlas provides voxel-level likelihood of cancer and optimized biopsy locations on a template space (Zhan et al 2007). The atlas was constructed from 158 expert annotated, 3D reconstructed radical prostatectomy specimens outlined for cancers (Shen et al 2004). For successful clinical implementation, the prostate atlas needs to be registered to each patient's TRUS image with high registration accuracy in a time-efficient manner. This is implemented in a two-step procedure, the segmentation of the prostate gland from a patient's TRUS image followed by the registration of the prostate atlas. We have developed a fast registration algorithm suitable for clinical applications of this prostate cancer atlas. The registration algorithm was implemented on a graphical processing unit (GPU) to meet the critical processing speed requirements for atlas guided biopsy. A color overlay of the atlas superposed on the TRUS image was presented to help pick statistically likely regions known to harbor cancer. We validated our fast registration algorithm using computer simulations of two optimized 7- and 12-core biopsy protocols to maximize the overall detection rate. Using a GPU, patient's TRUS image segmentation and atlas registration took less than 12 s. The prostate cancer atlas guided 7- and 12-core biopsy protocols had cancer detection rates of 84.81% and 89.87% respectively when validated on the same set of data. Whereas the sextant biopsy approach without the utility of 3D cancer atlas detected only 70.5% of the cancers using the same histology data. We estimate 10-20% increase in prostate cancer detection rates when TRUS guided biopsies are assisted by the 3D prostate cancer atlas compared to the current standard of care. The fast registration algorithm we have developed can easily be adapted for clinical applications for the improved diagnosis of prostate cancer.