灰阶超声和彩色多普勒超声诊断早期乳腺癌的价值

目的探讨超声声像图特征对早期乳腺癌诊断价值.方法84例女性患者(89个肿瘤)术前分别进行灰阶超声、彩色多普勒超声检查,观察肿块的形态、边缘、内部回声及钙化、肿块后回声以及肿块内血流信号情况.结果84例患者手术病理证实乳腺导管癌的7例,早期浸润癌的32例,良性肿瘤45例.灰阶超声、彩色超声多普勒对导管内癌及早期浸润性癌诊断的准确率分别为80.7%,79.3%和59.9%,65.9%.结论超声诊断早期乳腺癌目前主要依靠灰阶超声.     

高强度聚焦超声热疗中组织损伤的一种监测方法

用特定频率和功率的高强度聚焦超声（HIFU）照射离体猪肉组织,研究了焦点区域的B超图像变化与HIFU导致的组织损伤之间的关系,并研究了M超信号变化和温度的相关性。结果表明：逐渐增加HIFU照射次数,焦点区域组织变性,B超图像发生明显改变。靶区内灰度超过设定的阈值的区域面积增大,区域内灰度升高,两者均与照射次数成近似线性关系;模拟加热实验中M超信号也随温度升高而变化,其变化较B超更显著。与以往的方法相比,实验系统可以实时地检测到组织损伤的程度和范围,提供了一种新的可视化的HIFU治疗实时监测方法。     

基于水平集的组织热损伤区域自动检测

为超声引导的HIFU治疗系统设计一种自动检测凝固性坏死损伤区域的大小形状及位置的辅助诊断方法,本文提出一种基于水平集的HIFU损伤区域自动探测方法,利用超声剪影图像所含灰度变化信息,自动识别热损伤发生的位置,设置水平集函数的初始值,进而对热损伤区域的的边界进行检测.该算法分割出的组织损伤区域形状与大小均与组织剖面所见损伤区域相符,对连通或非连通区域均可进行很好的分割.     

E2 经阴道超声探测鉴别卵巢肿瘤

本文报告了179例妇科盆腔肿块的阴道超声诊断结果,与穿剌手术病理诊断相符的172例,符合率为96.0%。文中描述了阴道超声特点,并通过阴道超声与腹部超声的比较分析,认为阴道超声在鉴定妇科盆腔肿块性质、判断肿块来源以及对盆腔小肿瘤的早期诊断等方面具有明显优势,提出了阴道超声诊断妇科盆腔肿块应列为首选方法,讨论了阴道超声引导下穿剌的应用价值。     

超声显像诊断甲状腺肿块28例误诊分析

本文分析了我院经手术和病理证实的28例超声漏诊或误诊的甲状腺肿块,其中超声诊断与病理诊断不符者18例,超声未提示肿块病理性质者6例,超声漏诊甲状腺肿块者4例,计甲状腺癌19例,良性肿块9例。 作者分析了28例病例的声像图表现特点,并与手术后病理对照得出误诊或漏珍的原因: 1.超声能够发现甲状腺内直径0.5cm以上的肿块,直径1～2cm的肿块易受各种因素干扰而漏诊,尤其当肿块呈等回声时,常常是漏诊的主要原因。 2.部分甲状腺癌声像图上可有包膜或清晰的边界,特别是癌肿早期内部回声均匀,与甲状腺脉瘤相似而误诊。当癌肿出现坏死液化时,又易与腺…     

纹理分析在肝脏超声图像组织定征中的应用

现代超声医学影像通过研究超声传播中与生物组织相互作用后携带的图像纹理信息进行组织定征,为临床各学科疾病的检查、诊断和介入治疗提供了一条重要手段.本文在对目前文献进行分析和综合的基础上,首先阐述了图像纹理分析的常用方法,然后对纹理分析在肝脏超声图像中的应用进行了介绍,最后讨论了存在的问题及研究展望.     

阴道超声诊断妇科盆腔肿块的价值探讨(附179例分析)

本文报告了179例妇科盆腔肿块的阴道超声诊断结果,与穿剌手术病理诊断相符的172例,符合率为96.0%。文中描述了阴道超声特点,并通过阴道超声与腹部超声的比较分析,认为阴道超声在鉴定妇科盆腔肿块性质、判断肿块来源以及对盆腔小肿瘤的早期诊断等方面具有明显优势,提出了阴道超声诊断妇科盆腔肿块应列为首选方法,讨论了阴道超声引导下穿剌的应用价值。阴道超声诊断妇科盆腔肿块的价值探讨(附179例分析)@谢阳桂$南通医学院附属医院B超室 @燕山$上海第二医科大学九院B超科     

超声图像中目标的边界提取

由于对比度低和噪声强等特点,超声图像分割很难达到满意的效果,针对这一状况,将Gabor滤波器结合形态学操作应用到超声图像中目标的边界提取。首先对原始图像做预处理,去噪增强,然后再利用Gabor滤波进行目标区域特征提取,再经形态学腐蚀、膨胀等操作平滑图像,最后由sobel算子提取最终的边界图像。该法的关键之处在于Gabor滤波器尺度参数的选择,通过实验和分析得出了一组最佳尺度参数,取得了良好的分割效果,同时也验证了这一方法在超声图像分割中的实用性。     

基于超声图像小波分形维和熵监测生物组织凝固性坏死

高强度聚焦超声(HIFU)治疗肿瘤过程中,辨别组织是否发生凝固性坏死非常重要.本文从数字图像处理的角度出发,研究利用超声图像的小波分形维和熵监测生物组织变性的可行性.将高强度聚焦超声打击新鲜猪肉组织后获得的超声图像与打击前的超声图像做差值处理,截取焦域中心64×64像素的图像,然后提取其小波分形维和熵作为参量信息,比较不同参量对组织凝固性坏死的辨识效果.实验表明,提取小波分形维和熵特征并输入BP神经网络,相对于仅使用某种特征参数而言有更高的识别率,可为临床监测生物组织是否有凝固性坏死发生提供有力的依据.     

基于磁共振图像的多层介质声学特性分析

基于磁共振图像,提出了一种多层介质声学特性分析方法,并推算了超声经过分层结构的焦点定位。首先对蔗糖溶液的磁共振T1加权图像进行区域提取、阈值分割、腐蚀膨胀等边缘处理后,得到局部区域的灰度均值;通过磁共振图像上的灰度信息与对应蔗糖溶液的浓度、声速计算关系拟合函数;最后建立模拟生物组织的蔗糖溶液分层结构,运用关系函数推算超声经过分层结构的声透射及聚焦超声的焦点前移量。实验结果表明,该方法从蔗糖溶液磁共振图像中分析得到的声速、声透射系数及焦点前移量与真实值相近,最大差异为0.6239mm,验证了可通过磁共振获取生物组织声参数的可能性。     

Intuitionistic fuzzy approach for enhancement of low contrast mammogram images

Mammogram image enhancement is very much necessary in diagnosing breast cancer or tumor at an early stage. Nonuniform illumination and low contrast images are commonly encountered in mammogram images. Conventional enhancement algorithms produce either some artifacts or cannot highlight minute details present in the images, particularly when dealing with mammogram images. In this article, we propose a new mammogram image enhancement scheme using Atanassov's intuitionistic fuzzy set (IFS) theory. IFS considers two uncertainties—membership and nonmembership degree apart from membership degree as in fuzzy set theory. As mammogram images are low contrast images and many of the image definitions are vague/unclear, so IFS theory may be suitable for better image enhancement. Initially, the image is transformed to an intuitionistic fuzzy image using a novel intuitionistic fuzzy generator. Hesitation degree is computed and using the hesitation degree, two membership levels are computed to form an interval type 2 fuzzy set. These two membership functions are then combined using Zadeh's fuzzy t-conorm to form a new membership function. Threshold of interval type 2 fuzzy image is obtained using restricted equivalence function. Using the threshold, modified fuzzy hyperbolization is carried out. Real data experiments demonstrate that the proposed algorithm has better performance on contrast and visual quality of the images both quantitatively and qualitatively when compared with different existing methods.     

Ultrasound holographic B-scan imaging

An ultrasound holographic B-scan (UHB) imaging apparatus comprising a minicomputer system, a data acquisition unit, and a special 64-element UHB transducer has been developed. Simulation studies and real experiments with a tissue-equivalent phantom show that lateral and longitudinal resolution (-6 dB) of about 1 mm was achieved in the entire image. Furthermore, results from clinical evaluation, including diagnostic and neurosurgical imaging, suggest that the UHB imaging method is operational and has some special advantages in patient diagnosis. Theoretically, the addition of phase information to the ultrasound images can result in enhanced tissue characterization, which is extremely important in tumor diagnosis and treatment.     

A Modular Software System to Assist Interpretation of Medical Images—Application to Vascular Ultrasound Images

Improvements in medical imaging technology have greatly contributed to early disease detection and diagnosis. However, the accuracy of an examination depends on both the quality of the images and the ability of the physician to interpret those images. Use of output from computerized analysis of an image may facilitate the diagnostic tasks and, potentially improve the overall interpretation of images and the subsequent patient care. In this paper, Analysis, a modular software system designed to assist interpretation of medical images, is described in detail. Analysis allows texture and motion estimation of selected regions of interest (ROIs). Texture features can be estimated using first-order statistics, second-order statistics, Laws' texture energy, neighborhood gray-tone difference matrix, gray level difference statistics, and the fractal dimension. Motion can be estimated from temporal image sequences using block matching or optical flow. Image preprocessing, manual and automatic definition of ROIs, and dimensionality reduction and clustering using fuzzy c-means, are also possible within Analysis. An important feature of Analysis is the possibility for online telecollaboration between health care professionals under a secure framework. To demonstrate the applicability and usefulness of the system in clinical practice, Analysis was applied to B-mode ultrasound images of the carotid artery. Diagnostic tasks included automatic segmentation of the arterial wall in transverse sections, selection of wall and plaque ROIs in longitudinal sections, estimation of texture features in different image areas, motion analysis of tissue ROIs, and clustering of the extracted features. It is concluded that Analysis can provide a useful platform for computerized analysis of medical images and support of diagnosis     

基于人眼视觉特性的邻域自适应模糊增强算法

针对灰度适中时人眼分辨力较强的视觉特性,利用Prewitt算子求得梯度图像,并在隶属函数的定义中引入像素的邻域均值分量,对梯度图像进行模糊域的自适应增强。实验证明该算法克服了传统模糊增强算法会对噪声点进行增强的缺点,在增强图像细节的同时有效地抑制了图像的噪声。     

A novel prognosis and segmentation of necrosis (dead cells) in contrast enhanced T1-weighted glioblastoma tumor with automatic contextual clustering

In recent years, mortality rate with high-grade tumor has been increased significantly especially with glioblastoma (GBM) brain tumor while compared to other malignant brain tumor. Here, the amount of dead cells accommodated with the tumor tissue in GBM brain tumor play a vital task and necessitate an earlier diagnosis of malignancy with the GBM tumor. It inspires to implement new automatic diagnosis system which detects the dead cells and tumor tissue with the GBM brain tumor, such that the survival rate of the diseased can easily be prognosis by the Radiologist and Neurosurgeon. The main objective of this article is to detect the amount of dead cells with respect to tumor tissue associated with the GBM brain tumor which desires the impact factor of the brain tumor. In this framework, initially, the new contrast enhancement modality is incorporated to enhance the gray information over the dead cells and the tumor tissue with the T1-weighted MRI GBM brain tumor. In this enhancement, the edges of the tumor cells and its dead cells are magnified efficiently. As the noises and outliers with MR image is unpredictable and it experiences the variable amount of noises over the local window, the contextual information over each pixel of the image is adaptively modified with respect to the amount of noise over local window using adaptive contextual clustering. The performance evaluation of the framework is investigated which exhibits the overwhelming result compared to conventional detection techniques.     

车辆号牌识别中车辆速度的估计

光照不足导致了运动物体图像出现运动模糊。为提高图像质量,对多种算法方案进行了分 析,提出了一种稳健实用计算量少的新方法。在车辆号牌识别的实际例子里利用图像中运动物体的特征点估算出运动物体的运动速度从而对图像进行修正处理,成功地得到满意的图像。     

应用统计信号处理和模糊数学的图像融合算法

针对多传感器图像在像素级上的融合问题,将模糊数学理论引入到图像融合模型。该模型假定理想的融合后的图像包含场景所有的信息;将它乘上一个模糊因子,再加上随机噪声,可用来描述某一个成像传感器中获得的场景图像;不同的传感器对应不同的模糊因子和噪声。在此基础上,提出了建立在非多尺度分解框架下的图像融合算法。它以各传感器获取的图像作为输入条件,应用统计信号处理中的EM算法,求出针对不同传感器的噪声参数和模糊因子,通过迭代估计出融合的图像。实验结果显示,该算法获得的融合图像的互信息和联合熵分别达到3．5079和24．732,均优于加权平均融合法、小波融合算法和Laplacian融合算法的融合质量。     

浅析肝脏疾病B超诊断的临床价值

B型超声诊断仪是目前在临床中应用最广的一种超声图象诊断装置。由于它能对脏器进行实时动态观察,因而十分直观。它既可作静态检查,如对各器官和组织的观察和分析,又可作动态检查,如对心脏、胎儿的观察和分析。本文主要对借助B超在肝脏疾病诊断中的方法与临床价值进行探讨。     

Detection of tissue harmonic motion induced by ultrasonic radiation force using pulse-echo ultrasound and Kalman filter

A method using pulse echo ultrasound and the Kalman filter is developed for detecting submicron harmonic motion induced by ultrasonic radiation force. The method estimates the amplitude and phase of the motion at desired locations within a tissue region with high sensitivity. The harmonic motion generated by the ultrasound radiation force is expressed as extremely small oscillatory Doppler frequency shifts in the fast time (A-line) of ultrasound echoes, which are difficult to estimate. In slow time (repetitive ultrasound echoes) of the echoes, the motion also is presented as oscillatory phase shifts, from which the amplitude and phase of the harmonic motion can be estimated with the least mean squared error by Kalman filter. This technique can be used to estimate the traveling speed of a harmonic shear wave by tracking its phase changes during propagation. The shear wave propagation speed can be used to solve for the elasticity and viscosity of tissue as reported in our earlier study. Validation and in vitro experiments indicate that the method provides excellent estimations for very small (submicron) harmonic vibrations and has potential for noninvasive and quantitative stiffness measurements of tissues such as artery.     

Cell-type based semantic segmentation of histopathological images using deep convolutional neural networks

Histopathological whole-slide image (WSI) analysis is still one of the most important ways to identify regions of cancer risk. For cancer in which early diagnosis is vital, pathologists are at the center of the decision-making process. Thanks to the widespread use of digital pathology and the development of artificial intelligence methods, automatic histopathological image analysis methods help pathologists in their decision-making process. In this process, rather than producing labels for whole-slide image patches, semantic segmentation is very useful, which facilitates the pathologists’ interpretation. In this study, automatic semantic segmentation based on cell type is proposed for the first time in the literature using novel deep convolutional networks structure (DCNN). We presents semantic information on four classes, including white areas in the whole-slide image, tissue without cells, tissue with normal cells and tissue with cancerous cells. This visual information presented to the pathologist is an easy-to-understand picture of the status of the cells and their implications for the spread of cancerous cells. A new DCNN architecture is created, inspired by the residual network and deconvolution network architecture. Our network is trained end-to-end manner with histopathological image patches for cell structures to be more discriminative. The proposed method not only produces more successful results than other state-of-art semantic segmentation algorithms with 9.2% training error and 88.89% F-score for test, but also has the most important advantage in that it has the ability to generate automatic information about the cancer and also provides information that pathologists can quickly interpret.