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。     

CT and MR Image Fusion Scheme in Nonsubsampled Contourlet Transform Domain

Fusion of CT and MR images allows simultaneous visualization of details of bony anatomy provided by CT image and details of soft tissue anatomy provided by MR image. This helps the radiologist for the precise diagnosis of disease and for more effective interventional treatment procedures. This paper aims at designing an effective CT and MR image fusion method. In the proposed method, first source images are decomposed by using nonsubsampled contourlet transform (NSCT) which is a shift-invariant, multiresolution and multidirection image decomposition transform. Maximum entropy of square of the coefficients with in a local window is used for low-frequency sub-band coefficient selection. Maximum weighted sum-modified Laplacian is used for high-frequency sub-bands coefficient selection. Finally fused image is obtained through inverse NSCT. CT and MR images of different cases have been used to test the proposed method and results are compared with those of the other conventional image fusion methods. Both visual analysis and quantitative evaluation of experimental results shows the superiority of proposed method as compared to other methods.     

An Improved Medical Image Fusion Algorithm for Anatomical and Functional Medical Images

In recent years,many medical image fusion methods had been exploited to derive useful information from multimodality medical image data, but, not an appropriate fusion algorithm for anatomical and functional medical images. In this paper, the traditional method of wavelet fusion is improved and a new fusion algorithm of anatomical and functional medical images,in which high-frequency and low-frequency coefficients are studied respectively. When choosing high-frequency coefficients, the global gradient of each subimage is calculated to realize adaptive fusion,so that the fused image can reserve the functional information;while choosing the low coefficients is based on the analysis of the neighborbood region energy, so that the fused image can reserve the anatomical image＇ s edge and texture feature. Experimental results and the quality evaluation parameters show that the improved fusion algorithm can enhance the edge and texture feature and retain the function information and anatomical information effectively.     

人脑MRI和PET图像的融合方法

目的：研究MRI和PET医学图像融合的方法并且应用在人脑神经解剖中。方法：以Chamfer matching为基本配准方法和以模糊数学为理论基础的融合方法。结果：使得融合后图像有很强的抗配准偏差能力,并且能极大程度地保留原来解剖性信息图像和功能性图像的信息。能根据融合算子的不同组合,得到倾向于不同检查仪器结果的图像。结论：通过本文方法得出的融合后图像,能在人脑解剖结构上显示出该区域的功能状态,对于了解该结构的存在、变异、病变提供了很大的便利。对人脑神经解剖学研究和临床应用都有很大的理论和实践意义。     

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.     

基于双稀疏字典的医学图像融合算法及在脑血管疾病诊断中的应用

目的通过图像融合方法结合解剖和功能医学图像以提供更多有用的信息并辅助医生诊断。方法利用稀疏表示能很好地反映图像特征的优势。首先,选取医院脑梗死和脑出血的CT和MRI的临床图像,采用双稀疏字典算法得到稀疏字典,再通过结合空间域信息的最大选择法作为融合规则对其进行融合,并与基于主成分分析(principal component analysis,PCA)和离散小波变换(discrete wavelet transform,DWT)方法的图像融合结果在主观方面以及客观方面的QAB/F和Piella指标上进行比较。结果本文提出的方法所获得的融合图像主观评价优于另外两种方法。QAB/F和Piella的均值分别为0.9139和0.7213,客观评价指标也优于另外两种方法。结论基于双稀疏字典的图像融合算法得到的融合图像更清晰,对比度更高,并且特征保留效果更好,有助于医生的诊断。     

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.     

基于小波变换和一致性检验的多模态医学图像融合算法

目的选择已配准后的多聚焦医学图像以及MRI/CT灰度图像为实验素材,以探究不同的融合策略对图像融合效果的影响。方法在对多模态医学图像融合时,低频融合分别采取了加权平均、取极大值法、区域能量以及区域方差的对比实验。高频融合分别采取了区域能量、区域方差以及滤波后基于邻域窗口的一致性检验的对比实验。结果通过对融合图像主观(融合效果)与客观(灰度直方图、边缘提取、性能评价)对比分析,找到了多模态医学图像融合的最优融合策略。结论当低频选择局部区域方差融合,融合后的图像轮廓清晰、边缘较完整;而高频选择滤波后基于邻域窗口的一致性检验,融合后的图像更好地保留和加强了源图像的细节信息。     

基于自由变形法的多模态医学图像的配准与融合

本研究提出了一种自动识别颈部PET-CT图像特征点的算法，它应用自由变形（FFD）方法以CT图像的特征点为参考使PET图像产生变形，再结合最大互信息法对颈部PET与CT图像进行非刚体配准，最后用改进的小波图像融合法把两者进行融合得出视觉效果比较理想的融合图像。经实际计算得出的变形PET图像与对应CT图像的互信息量大于原始PET图像，并且最后用改进的小波图像融合法得出的融合图像的信息量比一般小波融合大，由此证明本研究所用方法是有效的。     

基于Mimics软件虚拟人膝关节三维图像融合实验

背景：国内外已有学者利用不同的方法对人体膝关节进行三维建模,根据各自研究侧重点不同,在方法和最终效果上各有不同。 目的：根据不同模态中膝关节影像的特点,将膝关节建模结果进行配准、融合,为进一步生物力学研究提供一种方便的方法。 方法：采用Mimics V 10.0软件根据膝关节在CT和MR断层图像的特点,选择不同分割算法进行膝关节解剖组织分割,并对不同的分割图像进行三维重建。 结果与结论：基于逆向工程原理,利用虚拟人膝关节连续CT断面图像分别重建出膝关节的骨性结构如股骨、胫骨、腓骨、髌骨;并利用膝关节的连续MRI断面图像重建出半月板、髌韧带、内侧副韧带、前交叉韧带、后交叉韧带等结构,并成功对上述结构进行融合,融合后的三维膝关节模型可以任意角度或单独观察,并可以进行体视学测量。说明通过不同模态图像融合的方法可以建立膝关节的三维模型,为计算机辅助膝关节损伤康复研究奠定基础。     

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。     

Medical Image Fusion Based on Sparse Representation with KSVD

Medical image fusion is a process by which two different models of images are combined into a single image, in order to provide doctors with accurate diagnoses, and take right action. This paper proposes an image fusion method based on sparse representation with KSVD. Firstly, all source images are combined into a joint-matrix, which can be represented with sparse coefficients using an overcompletedictionary trained by KSVD algorithm. Secondly, the coefficients which are considered as image features are combined with the choose-max fusion rule. Finally, the fused image is reconstructed from the concatenated coefficients and the overcomplete dictionary. Compared with three state-of-the-art algorithms, the proposed method has better fusion performance.     

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。     

Fusions of anthrax toxin lethal factor with shiga toxin and diphtheria toxin enzymatic domains are toxic to mammalian cells.

To investigate the ability of anthrax toxin lethal factor (LF) to translocate foreign proteins into the cytosol of eukaryotic cells and to characterize the structural requirements of this process, fusion proteins containing a portion of LF and the catalytic domains of either diphtheria toxin or Shiga toxin were constructed. Previous work showed that residues 1 to 254 of anthrax toxin lethal factor (LF1-254) are sufficient for binding to the protective antigen component of the toxin and that portions of Pseudomonas exotoxin A fused to LF1-254 are efficiently translocated to the cytosol of eukaryotic cells (N. Arora and S. H. Leppla, J. Biol. Chem. 268:3334-3341, 1993). In this study, it was found that fusion proteins containing the ADP-ribosylation domain of diphtheria toxin fused at either the amino end or the carboxyl end of LF1-254 are highly toxic to Chinese hamster ovary (CHO) cells, indicating that translocation does not strictly require that the amino terminus of LF be free. A fusion protein containing the ribosome-inactivating A1 subunit of Shiga toxin fused to the carboxyl terminus of LF1-254 was also highly toxic for CHO cells. All fusion proteins were toxic only when administered with the anthrax toxin protective antigen component. The data show that the combination of protective antigen and LF fusion proteins can efficiently import polypeptides from diverse bacterial sources to the cytosol of eukaryotic cells and that LF fusion proteins may have the passenger polypeptides fused at either the amino terminus or the carboxyl terminus of LF1-254. These LF fusion proteins could potentially be used as components of a therapeutic agent when the destruction of certain types of cells is desired (e.g., in treating cancer).     

Geometrical accuracy and fusion of multimodal vascular images: a phantom study

The aim of this work was to compare the geometrical accuracy of x-ray angiography, magnetic resonance imaging (MRI), x-ray computed tomography (XCT), and ultrasound imaging (B-mode and IVUS, or intravascular ultrasound) for measuring the lumen diameters of blood vessels. An image fusion method was also developed to improve these measurements. The images were acquired from a phantom that mimic vessels of known diameters. After acquisition, the multimodal images were coregistered by manual alignment of fiducial markers, and then by maximization of mutual information. The fusion method was performed by means of a fuzzy logic modeling approach followed by a combination process based on a possibilistic theory. The results showed (i) the better geometrical accuracy of XCT and IVUS compared to the other modalities, and (ii) the better accuracy and smaller variability of fused images compared to single modalities, with respect to most diameters investigated. For XCT, the error varied from 0.4% to 5.4%, depending on the vessel diameter that ranged from 0.93 to 6.24 mm. For IVUS, the error ranged from -0.3% to 1.7% but the smallest vessel (0.93 mm) could not be investigated because of the probe size. Compared to others fusion schemes, the XCT-MRI fused images provided the best results for both accuracy (from -1.6% to 0.2% for the three largest vessels) and robustness (mean relative error of 1.9%). To conclude, this work underlined both the usefulness of the multimodality vascular phantom as a validation tool and the utility of image fusion in the vascular context.     

Food��s visually perceived fat content affects discrimination speed in an orthogonal spatial task

Choosing what to eat is a complex activity for humans. Determining a food's pleasantness requires us to combine information about what is available at a given time with knowledge of the food's palatability, texture, fat content, and other nutritional information. It has been suggested that humans may have an implicit knowledge of a food's fat content based on its appearance; Toepel et al. (Neuroimage 44:967-974, 2009) reported visual-evoked potential modulations after participants viewed images of high-energy, high-fat food (HF), as compared to viewing low-fat food (LF). In the present study, we investigated whether there are any immediate behavioural consequences of these modulations for human performance. HF, LF, or non-food (NF) images were used to exogenously direct participants' attention to either the left or the right. Next, participants made speeded elevation discrimination responses (up vs. down) to visual targets presented either above or below the midline (and at one of three stimulus onset asynchronies: 150, 300, or 450?ms). Participants responded significantly more rapidly following the presentation of a HF image than following the presentation of either LF or NF images, despite the fact that the identity of the images was entirely task-irrelevant. Similar results were found when comparing response speeds following images of high-carbohydrate (HC) food items to low-carbohydrate (LC) food items. These results support the view that people rapidly process (i.e. within a few hundred milliseconds) the fat/carbohydrate/energy value or, perhaps more generally, the pleasantness of food. Potentially as a result of HF/HC food items being more pleasant and thus having a higher incentive value, it seems as though seeing these foods results in a response readiness, or an overall alerting effect, in the human brain.     

Artefacts of PET/CT images

Positron emission tomography (PET) is a non-invasive imaging modality, which is clinically widely used both for diagnosis and accessing therapy response in oncology, cardiology and neurology.Fusing PET and CT images in a single dataset would be useful for physicians who could read the functional and the anatomical aspects of a disease in a single shot.The use of fusion software has been replaced in the last few years by integrated PET/CT systems, which combine a PET and a CT scanner in the same gantry. CT images have the double function to correct PET images for attenuation and can fuse with PET for a better visualization and localization of lesions. The use of CT for attenuation correction yields several advantages in terms of accuracy and patient comfort, but can also introduce several artefacts on PET-corrected images.PET/CT image artefacts are due primarily to metallic implants, respiratory motion, use of contrast media and image truncation. This paper reviews different types artefacts and their correction methods.PET/CT improves image quality and image accuracy. However, to avoid possible pitfalls the simultaneous display of both Computed Tomography Attenuation Corrected (CTAC) and non corrected PET images, side by side with CT images is strongly recommended.     

PET image reconstruction with anatomical edge guided level set prior

Acquiring both anatomical and functional images during one scan, PET/CT systems improve the ability to detect and localize abnormal uptakes. In addition, CT images provide anatomical boundary information that can be used to regularize positron emission tomography (PET) images. Here we propose a new approach to maximum a posteriori reconstruction of PET images with a level set prior guided by anatomical edges. The image prior models both the smoothness of PET images and the similarity between functional boundaries in PET and anatomical boundaries in CT. Level set functions (LSFs) are used to represent smooth and closed functional boundaries. The proposed method does not assume an exact match between PET and CT boundaries. Instead, it encourages similarity between the two boundaries, while allowing different region definition in PET images to accommodate possible signal and position mismatch between functional and anatomical images. While the functional boundaries are guaranteed to be closed by the LSFs, the proposed method does not require closed anatomical boundaries and can utilize incomplete edges obtained from an automatic edge detection algorithm. We conducted computer simulations to evaluate the performance of the proposed method. Two digital phantoms were constructed based on the Digimouse data and a human CT image, respectively. Anatomical edges were extracted automatically from the CT images. Tumors were simulated in the PET phantoms with different mismatched anatomical boundaries. Compared with existing methods, the new method achieved better bias-variance performance. The proposed method was also applied to real mouse data and achieved higher contrast than other methods.     

基于深度学习的多模态医学图像融合方法研究进展

医学图像融合方法可以将有用的信息整合到一张图上，提高单张图像的信息量。对多模态医学图像进行融合时，如何对图像进行有效的变换，提取到不同图像中独有的特征，并施以适当的融合规则是医学图像融合领域研究的重点。近年随着深度学习的快速发展，深度学习被广泛应用于医学图像领域，代替传统方法中的一些人工操作，并在图像表示、图像特征提取以及融合规则的选择方面显示出独特优势。本文针对基于深度学习的医学图像融合进展予以探讨，介绍了卷积神经网络、卷积稀疏表示、深度自编码和深度信念网络这些常用于医学图像融合的框架，对一些应用于融合过程不同步骤的深度学习方法进行分析和总结，最后，分析了当前基于深度学习的融合方法的不足并展望了未来的研究方向。     

图像融合技术在Computed Radiography影像中的应用研究

将图像融合技术应用于CR(ComputedRadiography)技术中 ,有效改善影像的信噪比 (signal-to -noiseratio)。运用双IP(ImagePlate)技术采集人体体模影像后 ,在变换域进行图像配准。建立融合图像的数学模型 ,基于此模型对配准完成的源图像实施不同权重的加权计算得到融合图像。结果　融合图像信噪比源图像可提高 30 %左右。结论　将图像融合技术应用于CR技术可有效改善影像质量 ,有助于提高诊断的准确性。