基于三次样条层间插值的多模态医学图像配准

我们从PET-CT多模态图像序列的特点出发,提出了一种全新的图像配准及融合方法,它采用三次样条插值法对PET-CT图像进行层间插值,然后再利用最大互信息法进行配准,最后应用改进的主成分分析(PCA)法融合PET-CT图像用以增强PET显像效果,从而得到满意的配准以及融合结果。用三次样条插值法进行层间插值并恢复层间缺失图像的信息,弥补了现有配准方法的不足,提高了配准精度,使融合后的图像更加接近实际的物理断层。该方法已经成功应用于三维适形放疗(3D-CRT)系统的开发中。     

医学图像融合配准技术

图像融合技术在现代医学中扮演着极其重要的角色,是现代医学图像技术研究的重点.图像融合技术中,图像的配准又是其中的重点、难点和热点.本文按照图像变换特性对图像配准进行了分类,对每个类别的不同配准方法(特征点的获取、图像配准的变换等)进行介绍.但是,图像配准是一个尚处在发展阶段的学科,实现配准的精确化、快速化、自动化仍需要进一步的努力.     

基于深度学习分割掩膜的胸片图像配准技术及其应用

医学图像配准技术对临床诊断治疗具有重要意义。相比传统的图像配准方法,目前基于深度学习的配准方法提高了配准的精度和速度。为了将深度学习图像配准技术应用于胸片的配准以及减影分析,本研究先采用深度学习掩膜对原始胸片进行预处理,然后以掩膜图像作为输入,以ResUNet网络作为配准框架来实现胸片图像配准,最后评估配准效果。结果显示深度学习掩膜结合深度学习图像配准方法训练出的模型在胸片配准上具有良好的图像配准精度。这种基于掩膜的深度学习配准模型可以较好地应用于胸片的减影分析。     

基于电磁定位的超声图像与CT图像的融合方法

在超声引导经皮介入治疗中,为集成多模态图像信息来弥补单一超声图像的不足,提出一种实时超声图像与CT图像的融合方法,使临床医生在实施介入治疗时得到患者病灶的多模态图像信息成为可能。首先,利用电磁定位系统,得到12个铅球球心的磁场坐标和CT图像坐标,利用两个点集的ICP配准算法,将磁场坐标系和CT图像坐标系进行配准;其次,利用电磁定位系统,将和超声探头固连在一起的电磁传感器自身坐标系与磁场坐标系进行配准;然后,利用超声探头的机械设计尺寸,将超声坐标系与电磁传感器自身坐标系进行配准;最后,通过多个坐标系的转换关系将超声坐标系配准到CT图像坐标系,最终将实时超声图像统一到CT图像中,并在软件中测量融合误差。在该方法下,实时超声图像与CT图像的融合误差为(0.71±0.03)mm,在软件中可以清晰地看到两种图像的实时融合效果。因此,该方法可以有效地将实时超声图像与CT图像进行融合,为介入治疗的精准性提供相应的技术支持。     

SPECT-CT同机图像融合的仪器质量控制方法探讨

目的探讨SPECT-CT同机图像融合硬件配准误差的质量评价方法。方法制作带外套点源、点线模型及用ECT模型,加注放射源后,在床有、无负重情况下,分别对模型进行SPECT-CT采集,然后进行SPECT-CT同机图像融合处理,分析两种图像融合偏差程度。结果SPECT与CT旋转中心无偏移。在床无负重情况时,点源及点线源与外套无X、Y轴偏移。在床有负重情况下,融合图像Y轴偏移最大值为8.0mm,X轴偏差无像素偏移。ECT模型可检测核医学"冷"区图像及整体图像融合情况,但不能进行定量测量偏移情况。结论单点源模型可用于日常简单检测SPECT-CT图像融合硬件配准情况;点线源模型可用于准确定量分析图像融合硬件配匹程度;ECT模型可用图像融合质量综合分析。     

基于海明窗滤波及粒子群优化搜索的医学图像配准

针对互信息在多模态医学图像配准中的局部极值问题,利用海明窗(Hamming窗)进行滤波预处理,并采用粒子群优化(Particle swarm optimization,PSO)方法搜索配准参数。结果表明,图像经过Hamming窗低通滤波后,局部极值大大减少,有利于利用互信息进行图像的配准。另外,PSO优化算法在大多数情况下都可以收敛到全局最优解。我们提出的方法可有效克服互信息的局部极值问题,并有效提高配准精度。     

SPECT-CT同机图像融合的仪器质量控制方法探讨

目的 探讨SPECT-CT同机图像融合硬件配准误差的质量评价方法.方法 制作带外套点源、点线模型及用ECT模型,加注放射源后,在床有、无负重情况下,分别对模型进行SPECT-CT采集,然后进行SPECT-CT同机图像融合处理,分析两种图像融合偏差程度.结果 SPECT与CT旋转中心无偏移.在床无负重情况时,点源及点线源与外套无X、Y轴偏移.在床有负重情况下,融合图像Y轴偏移最大值为8.0 mm,X轴偏差无像素偏移.ECT模型可检测核医学"冷"区图像及整体图像融合情况,但不能进行定量测量偏移情况.结论 单点源模型可用于日常简单检测SPECT-CT图像融合硬件配准情况;点线源模型可用于准确定量分析图像融合硬件配匹程度;ECT模型可用图像融合质量综合分析.     

锥形束CT与螺旋CT图像配准算法及其在放疗中的应用

目的：随着肿瘤放射治疗的发展,提高肿瘤放射治疗的精确度成为了重要的发展趋势。通过硬件与软件的共同发展,实现在线纠正治疗误差在医学图像帮助下完成放疗是现今临床研究的热点。图像引导放射治疗就是在这样理念的基础上发展出来的新型放疗模式。本文研究的目的就是阐述在现今临床普遍采用的锥形束CT与螺旋CT的图像配准在肿瘤放射治疗中的实际应用与重要性。通过研究总结出一套系统化的肿瘤放射治疗图像配准理论,发现最新研究热点、阐述最新研究不足,为今后进一步的发展图像引导放射治疗打下基础。方法：本文通过阐述基本医学图像配准理论,结合具体图像配准算法,应用于图像引导放射治疗,总结出一套系统化用于锥形束CT与螺旋CT图像配准的模式,从而获得更加快速准确的配准结果,改善图像引导放射治疗的效率。本文查阅了近几年计算机软件图像处理的大量文献,同时结合查阅大量图像引导放射治疗的文献,总结前人经验结合理论实践,综合阐述了一套应用于图像引导放射治疗的图像配准系统。结果：锥形束CT与螺旋CT的图像配准,在临床应用上多使用刚性图像配准,其有速度快便于计算的优势。但涉及到患者整体体位配准情况下,弹性图像配准在配准准确度上具有明显优势,需结合临床实际需求以及计算机运算能力的发展想结合选择合适的配准算法。结论：随着肿瘤放射治疗中图像引导技术的应用,螺旋CT定位图像与锥形束CT治疗图像的配准是图像引导放射治疗的关键技术,如何准确而且快速的获取配准结果成了精确放射治疗关注的焦点。螺旋CT定位图像与锥形束CT治疗图像的精确配准是精确放射治疗的前提,并在提高肿瘤剂量的同时,最大限度的保护正常组织,从而提高肿瘤放射治疗的疗效。本文主要综述了应用于精确放射治     

基于最大互信息的人脑MR-PET图像配准方法

利用最大互信息法进行多模医学图像配准近来成为医学图像处理领域的热点。MR和PET图像配准对研究神经组织的结构关系和引导神经外科手术有着重要的指导意义。本文描述了一种基于互信息的人脑MR－PET图像配准方法。我们将这种方法应用于图像的几何对准并给出了初步的评估结果。由于不需要对不同成像模式下的图像灰度间的关系作任何假设,最大互信息法是一种稳健性强,可广泛应用于基于体素的多模图像的配准方法。     

基于傅里叶梅林变换的图像配准方法

目的:提出一种新的配准框架用于图像引导放射治疗系统中的2D/3D图像配准,有效降低传统方法迭代搜索时间,同时保证放射治疗要求的配准精度。方法:利用傅里叶梅林变换方法对正侧位kV图像与对应方位参考CT图像生成的数字重建放射影像（DRR）进行粗配准,根据傅里叶梅林变换计算得到的二维平移向量以及放射治疗系统的机械几何参数反推出参考CT图像的三维空间位置偏差,更新正侧位的DRR图像,最后通过正侧位kV图像与DRR图像的相似度进行精配准达到临床需求。结果:采用临床金标准数据验证方法的配准性能,实验结果表明,配准误差为0.576 5 mm,平均运行时间为3.34 s。结论:该方法鲁棒性强,对图像的噪声不敏感,人工干预少,可满足临床应用的需求。     

Regional improvement of signal-to-noise and contrast-to-noise ratios in dual-screen CR chest imaging--a phantom study.

The improvement of signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in dual-screen computed radiography (CR) has been investigated for various regions in images of an anthropomorphic chest phantom. With the dual-screen CR technique, two image plates are placed in a cassette and exposed together during imaging. The exposed plates are separately scanned to form a front image and a back image, which are then registered and superimposed to form a composite image with improved SNRs and CNRs. The improvement can be optimized by applying specifically selected weighting factors during superimposition. In this study, dual-screen CR images of an anthropomorphic chest phantom were acquired and formed with four different combinations of standard resolution (ST) and high-resolution (HR) screens: ST-ST, ST-HR, HR-ST, and HR-HR. SNRs and their improvements were measured and compared over twelve representative regions-of-interest (ROIs) in these images. A 19.1%-45.7% increase of the SNR was observed, depending on the ROI and screen combination used. The optimal weighting factors were found to vary by only 4.5%-12.4%. Largest improvement was found in the lung field for all screen combinations. Improvement of CNRs was investigated over two ROIs in the lung field using the rib bones as the contrast objects and a 29.2%-43.9% improvement of the CNR was observed. Among the four screen combinations, ST-ST resulted in the most SNR and CNR improvement, followed in order by HR-ST, HR-HR, and ST-HR. The HR-ST combination yielded the lowest spatial variation of the optimal weighting factors with improved SNRs and CNRs close to those of the ST-ST combination.     

MRI-PET image fusion based on NSCT transform using local energy and local variance fusion rules

Image fusion means to integrate information from one image to another image. Medical images according to the nature of the images are divided into structural (such as CT and MRI) and functional (such as SPECT, PET). This article fused MRI and PET images and the purpose is adding structural information from MRI to functional information of PET images. The images decomposed with Nonsubsampled Contourlet Transform and then two images were fused with applying fusion rules. The coefficients of the low frequency band are combined by a maximal energy rule and coefficients of the high frequency bands are combined by a maximal variance rule. Finally, visual and quantitative criteria were used to evaluate the fusion result. In visual evaluation the opinion of two radiologists was used and in quantitative evaluation the proposed fusion method was compared with six existing methods and used criteria were entropy, mutual information, discrepancy and overall performance.     

Comparison of clinical and physical measures of image quality in chest and pelvis computed radiography at different tube voltages

The aim of this work was to study the dependence of image quality in digital chest and pelvis radiography on tube voltage, and to explore correlations between clinical and physical measures of image quality. The effect on image quality of tube voltage in these two examinations was assessed using two methods. The first method relies on radiologists' observations of images of an anthropomorphic phantom, and the second method was based on computer modeling of the imaging system using an anthropomorphic voxel phantom. The tube voltage was varied within a broad range (50-150 kV), including those values typically used with screen-film radiography. The tube charge was altered so that the same effective dose was achieved for each projection. Two x-ray units were employed using a computed radiography (CR) image detector with standard tube filtration and antiscatter device. Clinical image quality was assessed by a group of radiologists using a visual grading analysis (VGA) technique based on the revised CEC image criteria. Physical image quality was derived from a Monte Carlo computer model in terms of the signal-to-noise ratio, SNR, of anatomical structures corresponding to the image criteria. Both the VGAS (visual grading analysis score) and SNR decrease with increasing tube voltage in both chest PA and pelvis AP examinations, indicating superior performance if lower tube voltages are employed. Hence, a positive correlation between clinical and physical measures of image quality was found. The pros and cons of using lower tube voltages with CR digital radiography than typically used in analog screen-film radiography are discussed, as well as the relevance of using VGAS and quantum-noise SNR as measures of image quality in pelvis and chest radiography.     

基于稀疏表示和脉冲耦合神经网络的医学影像融合算法

为满足医学图像辅助诊断的需要,提出一种基于稀疏表示和脉冲耦合神经网络（PCNN）的CT和MR影像融合算法。首先,原始图像通过滑动窗方法构成联合矩阵,通过K-SVD算法得到该联合矩阵的冗余字典,采用正交匹配追踪算法得到该联合矩阵的稀疏系数;然后,根据稀疏系数的特点,采用脉冲耦合神经网络来融合稀疏系数;最后,由融合后的稀疏系数和冗余字典得到融合矩阵,反变换得到融合图像。实验图像为10组配准的脑部CT和MR图像,采用5种性能指标来评价融合图像的质量,同2种流行的医学影像融合算法进行比较,结果显示算法除Q^AB/F指数外,其他4项指标均为最优,Piella指数、Q^AB/F指数和BSSIM指数的均值分别为0.760 4、0.877 1和0.537 3,融合图像的纹理和边缘清晰,对比度高。主观和客观分析显示,算法的融合性能比较优越。     

Feature-Motivated Simplified Adaptive PCNN-Based Medical Image Fusion Algorithm in NSST Domain

Multimodality medical image fusion plays a vital role in diagnosis, treatment planning, and follow-up studies of various diseases. It provides a composite image containing critical information of source images required for better localization and definition of different organs and lesions. In the state-of-the-art image fusion methods based on nonsubsampled shearlet transform (NSST) and pulse-coupled neural network (PCNN), authors have used normalized coefficient value to motivate the PCNN-processing both low-frequency (LF) and high-frequency (HF) sub-bands. This makes the fused image blurred and decreases its contrast. The main objective of this work is to design an image fusion method that gives the fused image with better contrast, more detail information, and suitable for clinical use. We propose a novel image fusion method utilizing feature-motivated adaptive PCNN in NSST domain for fusion of anatomical images. The basic PCNN model is simplified, and adaptive-linking strength is used. Different features are used to motivate the PCNN-processing LF and HF sub-bands. The proposed method is extended for fusion of functional image with an anatomical image in improved nonlinear intensity hue and saturation (INIHS) color model. Extensive fusion experiments have been performed on CT-MRI and SPECT-MRI datasets. Visual and quantitative analysis of experimental results proved that the proposed method provides satisfactory fusion outcome compared to other image fusion methods.     

图像融合技术及其在癫痫患者中的应用

癫痫灶的准确定位是决定癫痫外科疗效的关键步骤。利用多模态医学图像融合技术将MR与PET的影像融合能明显地提高癫痫病灶定位诊断的准确率，为癫痫外科手术治疗和立体定向放射外科治疗提供更准确的信息。将融合技术应用到临床数据，对20例癫痫疾病患者的影像数据作了融合研究，并由临床专家作了验证。     

基于在线字典学习的医学图像特征提取与融合

提出一种基于在线字典学习(ODL)的医学图像特征提取与融合的新算法。首先,采用大小为8像素×8像素的滑动窗处理源图像,得到联合矩阵;通过ODL算法得到该联合矩阵的冗余字典,并利用最小角回归算法(LARS)计算该联合矩阵的稀疏编码;将稀疏编码列向量的1范数作为稀疏编码的活动级测量准则,然后根据活动级最大准则融合稀疏编码;最后根据融合后的稀疏编码和冗余字典重构融合图像。实验图像为20位患者的已配准脑部CT和MR图像,采用5种性能指标评价融合图像的质量,同两种流行的融合算法比较。结果显示,所提出算法的各项客观指标均值最优,Piella指数、QAB/F指数、MIAB/F指数、BSSIM指数和空间频率的均值分别为0.800 4、0.552 4、3.630 2、0.726 9和31.941 3,融合图像对比度、清晰度高,病灶的边缘清晰,运行速度较快,可以辅助医生诊断和临床治疗。     

Research and Realization of Medical Image Fusion Based on Three-Dimensional Reconstruction

A new medical image fusion technique is presented. The method is based on three-dimensional reconstruction. After reconstruction, the three-dimensional volume data is normalized by three-dimensional coordinate conversion in the same way and intercepted through setting up cutting plane including anatomical structure,as a result two images in entire registration on space and geometry are obtained and the images are fused at last. Compared with traditional two-dimensional fusion technique,three-dimensional fusion technique can not only resolve the different problems existed in the two kinds of images,but also avoid the registration error of the two kinds of images when they have different scan and imaging parameter. The research proves this fusion technique is more exact and has no registration, so it is more adapt to arbitrary medical image fusion with different equipments.