基于形态特征判别超声图像中乳腺肿瘤的良恶性

乳腺肿瘤超声图像的形态特征对判别肿瘤的良恶性具有重要的价值。为提高乳腺肿瘤超声诊断的准确率,提出一种基于其形态特征进行分类判别的计算机辅助诊断系统。该系统首先采用灰度阈值分割和动态规划相结合的方法提取超声图像中乳腺肿瘤的边缘,然后对所得边缘计算相应的三种形态参数,最后分别采用Fisher线性判据、误差反向传播神经网络和径向基函数神经网络对形态参数进行分类。该系统在157幅乳腺肿瘤(包括良性81例、恶性76例)超声图像上训练和测试,三种分类器均能取得较高的判别精度,其中误差反向传播神经网络和径向基函数神经网络的判别准确率、敏感性和特异性分别高达94.95%、95.74%和94.23%。结果表明,基于乳腺肿瘤超声图像的形态特征建立的神经网络系统对肿瘤的良恶性具有较好的判别能力。     

肝硬化的超声特征分析

利用肝脏硬度的无创估计系统，可以及时计肝脏的弹性状况，对了解和控制肝病进程有积极的意义，本文先在常用超声仪上获得肝脏的M型超声图像，接着从图像中分别提取肝脏包膜的运动包络和A型扫描信号相关系数随时间变化的曲线，然后从运动包络和相关曲线中提取出相应的特征参量，最后用Fisher判别法进行肝脏是否硬化的分类决策，结果表明：该方法可以为简单，有效地诊断肝硬化提供新的手段。     

一种超声乳腺图像中提取肿瘤边缘的方法

乳腺肿瘤边缘的提取是基于肿瘤超声图像特征进行良恶性诊断的基础.为此提出一种基于小波变换和动态规划从超声乳腺图像中提取肿瘤边缘的方法.先采用小波变换法提取乳腺肿瘤超声图像的初始边缘,再结合图像梯度的动态规划法对初始边缘进行修正,提取更为准确的乳腺肿瘤边缘.通过对临床采集的30例超声乳腺图像肿瘤边缘的提取和分析研究,表明该方法可以有效地用于超声乳腺图像肿瘤边缘的提取.     

改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域

为了解决超声图像斑点噪声、伪影、低图像对比度和图像亮度不均匀等问题,提出了一种改进的简化脉冲耦合神经网络(SPCNN)结合模糊互信息量的方法来自动检测乳腺肿瘤超声图像的感兴趣区域(ROI)。首先,对超声图像进行模糊增强预处理;然后,通过改进SPCNN对超声图像进行点火,以最大模糊互信息量作为最优判决准则,获得相应的分类结果;最后,对分类后的二值图像进行形态学等处理,从而得到乳腺超声图像的ROI。对包含118幅乳腺肿瘤超声图像的数据库进行处理,结果表明,该方法自动识别ROI准确率达到87.3%,处理每一幅图像的平均时间为4.68s。本算法能有效快速地检测乳腺肿瘤超声图像的ROI,有望用于基于超声图像的乳腺肿瘤CAD中。     

超光谱遥感图像特征分析

超光谱遥感图像是一种三维立体图像,可反映地物的空间信息和光谱信息,其数据量庞大.本文通过对实际多光谱遥感图像的测试,分析了空间相关性和谱间相关性;计算出自相关系数和互相关系数;并与普通图像进行比较,揭示了超光谱图像的特征,为超光谱图像处理和压缩编码奠定了理论基础.     

颈部淋巴结超声图像的计算机辅助分析

淋巴结的超声检查对疾病的诊断有重要意义,本文对颈部淋巴结超声图像的计算机辅助分析进行研究.首先根据颈部淋巴结的医学超声特性,对每一个淋巴结提取9个量化特征参数,然后基于K近邻法将其判为良性或恶性.采用留一法对62个病例进行测试,当k=5时,识别正确率为88.71%,灵敏度为83.87%,特异度为93.55%.本文为颈部淋巴结疾病的超声诊断提供一种客观、简捷的手段.     

超声信号的特征提取与选择在缺陷分类识别中的应用

超声缺陷回波信号的特征提取与选择是超声波检测的基础和关键。结合待检测超声信号的特点,在时域、频域上研究了超声缺陷信号的特征提取,提出SBS和SFS结合的特征选择方法。在满足识别准确率的同时,有效地降低了分类器输入向量的维数,提高了运算效率。     

基于血管内超声图像自动识别易损斑块

为克服手工判别动脉粥样硬化易损斑块耗时耗力、主观性强、重复性差等缺点,研究了基于血管内超声自动识别易损斑块的方法。首先将Contourlet变换与Snake模型相结合进行斑块的图像分割,提取内腔轮廓与外弹力膜。接着实现经典形态特征的计算机自动提取,并提取纹理、弹性两类新特征以量化斑块属性,其中纹理特征包括一阶统计量和灰度共生矩阵特征,弹性特征的提取则基于非刚性图像配准。最后设计Fisher线性判别、支撑向量机、广义相关学习矢量量化3种分类器进行分类判决。对124例斑块(36例易损,88例非易损)的实验结果表明:20个形态特征、24个纹理特征和6个弹性特征在两类斑块间存在显著性差异(P<0.05);采用三类特征由支撑向量机进行分类时效果最好,在测试集上敏感性、特异性、准确率和约登指数分别达到91.7%、97.7%、96.7%和89.4%,表明利用血管内超声图像中斑块的三类特征能自动、准确地识别易损斑块。     

基于迁移学习与特征融合的眼底图像分类

针对大量眼底图片难以收集和标注、有经验的眼科医生地区分配不均匀等,导致眼底疾病患者检查准确度低、花费时间较长等问题,本文基于迁移学习提出一种图像分类方法:首先修改EfficientNet-B0和EfficientNet-B7模型并进行参数微调,将微调后的模型作为特征提取器用于提取眼底图像的特征,再对提取的特征进行特征融...     

原发性输卵管癌的超声图像特征及误诊分析

目的:观察原发性输卵管癌(PFTC)的超声图像特征,分析误诊原因,总结临床诊断思路。方法 :于我院接受外科手术,经术后病理组织学检查明确PFTC诊断的患者53例,调取患者术前超声检查资料,对超声分型表现及诊断结果进行分析,并归纳PFTC超声误诊率及误诊原因。结果:53例PFTC患者中,超声分型Ⅰ型8例,Ⅱ型3例,Ⅲ型17例,Ⅳ型18例,Ⅴ型7例。超声分型Ⅰ型、Ⅱ型者术前超声准确诊断率均为100.00%;Ⅲ型诊断准确率82.35%,3例患者误诊为浆膜下肌瘤;Ⅳ型患者转移率为100.00%,均误诊为卵巢来源恶性肿瘤,误诊率100%;Ⅴ型术前超声均漏诊。结论:腊肠状囊性肿块是PFTC的典型征象,对于不典型图像根据输卵管病变位置、大小、内部回声及周围脏器解剖关系及病史综合判断,有望降低误诊率、漏诊率。     

基于相位和GGVF的水平集乳腺超声图像分割

提出一种基于相位和广义梯度矢量流(generalized gradient vector flow,GGVF)的水平集分割方法,并用于乳腺超声图像的肿瘤分割。首先,在频域空间,用Cauchy核替代Log-Gabor作为正交滤波器对图像进行滤波,提取来自于单演信号的多尺度图像特征,引入相位一致的思想将多尺度特征结合起来进行边界检测;然后,在此基础上,利用相位一致梯度图定义了一个基于相位的速度停止项函数,同时改进了GGVF;最后,将得到的速度停止项和梯度矢量流融入到水平集演化方程中来控制曲线的演化,获得乳腺肿瘤的边界。实验结果表明,使用该分割方法可获得比现有方法更好的乳腺肿瘤分割结果。     

Speckle reduction in breast cancer ultrasound images by using homogeneity modified bayes shrink

Ultrasound imaging suffers from severe artifacts caused by speckle noise. The paper introduces an algorithm for speckle noise reduction in breast cancer ultrasound images. Based on wavelet analysis and filtering, we employed a combination of homogeneity filtering and modified bayes shrink methods to remove noise while keeping the sharpness of important features. First, we replace pixel intensity by the mean of homogenous neighborhood and then, the threshold value of modified bayes shrink is employed to distinguish homogenous regions from regions with speckle noise obtained from homogeneity filtering. The proposed algorithm is called Homogeneity Modified Bayes Shrink (HMBS). A comparative study with other despeckling methods, using quantitative indices, showed the superiority of the proposed method over those methods.     

Efficient texture analysis of binary images

A new method of determining some characteristics of binary images is proposed based on a special linear filtering. This technique enables estimation of the area fraction, the specific line length and the specific integral of curvature. Furthermore, the specific length of the total projection is obtained, which gives detailed information about the texture of the image. The influence of lateral and directional resolution depending on the size of the applied filter mask is discussed in detail. The technique includes a method of increasing directional resolution for texture analysis while keeping lateral resolution as high as possible.     

Linear filtering of 2-D wavelet coefficients for denoising ultrasound medical images

The paper presents a novel denoising method for ultrasound medical images, whose quality is degraded by the peculiar phenomenon of speckle noise. The method is constructed step-by-step on the basis of recent research on the topic, and consists in Gaussian filtering of proper wavelet coefficients of the image, corresponding to vertical and diagonal details. A comparison with other filtering techniques for ultrasound imaging, i.e. Wiener and median filter, is presented. The obtained results, combined with those reported in independent research, demonstrate that the proposed denoising scheme has very good performance and is very promising for actual medical application.     

On the analysis of spatial binary images

This paper deals with the analysis of spatial images taken from microscopically heterogeneous but macroscopically homogeneous microstructures. A new method is presented, which is strictly based on integral-geometric formulae such as Crofton's intersection formulae and Hadwiger's recursive definition of the Euler number. By means of this approach the quermassdensities can be expressed as the inner products of two vectors where the first vector carries the 'integrated local knowledge' about the microstructure and the second vector depends on the lateral resolution of the image as well as the quadrature rules used in the discretization of the integral-geometric formulae. As an example of application we consider the analysis of spatial microtomographic images obtained from natural sandstones.     

Quantitative photogrammetric analysis and qualitative stereoscopic analysis of SEM images

This paper is concerned with methods for obtaining three-dimensional (3D) information from scanning electron microscope (SEM) images. It may come as a surprise that this topic merits separate discussion, because, it is generally accepted that every SEM image of a rough surface using the secondary electron emission mode gives apparent 3D information. This is true to some extent, since SEM images are comparable with photographs of rough surfaces illuminated with light coming from one direction, but our main concern here will be with 3D visualization from stereoscopic pairs of images. However, there are other ways in which 3D information may be obtained, even in the SEM, and these are considered first. The remainder of the paper is largely concerned with the use of stereoscopic parallaxes, whether or not they are visualized as such. Commonly used methods for viewing stereo-pairs are described, followed by simple methods for measuring stereoscopic parallaxes. Formulae for reducing linear measurements in the two photographs to real height differences are given.     

单向阀密封结构特性分析

介绍了单向阀的结构特性和装配方法,这种结构已于2005年7月获得专利（专利号：ZL200420037783.2）.     

NASH锥体型水环式真空泵的性能特点分析

NASH锥体型设计水环式真空泵设计思路独特，具有抽气量大，运行可靠，节能，寿命长等诸多优点，通过锥体型水环式真空泵与普通平面型水环式真空泵的分析比较，详细论述了NASH锥体型水环式真空泵的性能特点。