数字乳房X片图像的预处理算法研究

介绍了一种数字乳房X片图像的预处理算法。利用时域处理和形态学处理相结合的方法,对数字乳房X片图像进行预处理,去除无用背景像素点,有效减少后期增强、分割处理的数据量。     

基于模糊C均值和小波多分辨分析的数字乳房X射线片钙化点提取算法研究

目的为了使临床医生从数字乳房X片图像中得到更准确的钙化点信息,利用模糊C均值聚类算法（Fuzzy Cmeans,FCM）和小波多分辨分析算法,分两步提取出原图中的疑似钙化亮点。第一步是提取较亮区域;第二步是提取亮点簇。提取出亮点的图像可为医生进一步诊断提供依据。     

基于频谱图像灰度共生矩阵的无损测温方法

本文提出了一种基于哈达玛变换的频谱图像灰度共生矩阵(Hadamard-GLCM)的高强度聚焦超声治疗无损测温方法。利用高强度聚焦超声辐照新鲜离体猪肉组织,获取辐照前后的B超图像的减影图像,采用Hadamard变换对其进行处理,获取频谱图像,将频谱图像的灰度共生矩阵惯性矩作为反应温度变化的信息参数。实验表明:不仅单组数据的Hadamard-GLCM惯性矩(HGMI)和温度能很好的线性拟合,而且多组数据的Hadamard-GLCM惯性矩与温度也成近似的线性关系,而且斜率非常接近,拟合度更接近1,误差小,对温度的分辨能力高,容错能力强,与传统的测温方法相比有着明显的优势,能为HIFU治疗过程中的无损测温提供有效的实时依据。     

假彩色图象增强技术在X线诊断上的应用

X线摄影技术的应用和人的视觉特性在自然科学领域内,人们利用摄影技术将外界大量有价值的信息记录在底片上。由于黑白底片对亮度非常敏感,能将影象亮度的微小变化变为密度差异记录下来,所以黑白底片所记录的信息不仅容量大而且十分敏感。X线片上的影象亦是利用X线穿透人体组织时,由于各种组织的不同密度对X线的吸收差异,形成不同的X线强度,致使底片上形成灰度不同的黑白影象。虽然一张黑白 X线片上包含着极丰富的灰度级,有大量的重要信息,但是作为传感器的人眼,对不同的黑白灰度级的辨别能力却很差,只有15～20个密度等级,所以即使是有经验的专家,在通常情况下也不能检测或分辨出大量信息。但是人眼对彩色却有非常     

基于MATLAB的乳腺钼靶图像直方图增强方法的比较

目的比较不同直方图增强方法对改善乳腺铝靶图像质量的效果。方法基于MATLAB编程,分别采用直方图均衡化（HE）、直方图规定化（HS）和对比度受限自适应直方图均衡化（CLAHE）对乳腺钼靶图像进行增强处理;利用峰值信噪比（PSNR）客观评价图像的噪声水平。结果HE对图像对比度的增强效果一般,图像细节反而有所下降;HS可选择匹配直方图函数的类型,从而选择性增强所需灰度范围,但图像噪声水平在三种方法中最高;CLAHE能很好地增强图像各部分的对比度,且图像噪声水平最低。结论应用直方图增强方法处理乳腺钼靶图像,在图像噪声水平和灰度增强上,CLAHE明显优于HE和HS。     

天麻X射线衍射指纹图谱及数字化特征

本文研究了野生和人工栽培天麻和伪品羽裂蟹甲草的X射线衍射(XRD)指纹图谱及其数字化特征。利用Paeudo-Voigt函数模型进行全谱数字拟合分峰,对分峰后峰位和相对强度进行相似系数计算和分析。结果显示,XRD指纹图谱整体轮廓识别法能准确地鉴别真伪天麻;而经分峰处理后的数字特征信息可有效准确地鉴别野生和人工栽培天麻。相似系数计算结果表明不同样品存在着明显差异。数字分峰及图谱相似系数的原理和方法可应用于中药构效性研究和XRD指纹图谱数据库建立。     

小波变换及其在医学图像处理中的应用

医学图像的好坏直接影响着医生对病情的诊断和治疗,因此利用数字图像处理等技术对医学图像进行有效的处理,已成为医学图像处理研究和开发的一大热点。小波变换是对傅里叶变换的继承和发展,在医学影像领域有着广泛的应用前景。本文介绍了二维离散小渡变换的一般形式,在图像分解与重构的基础上．系统地阐述了利用小小组变换的时频域特性与多分辨分析对医学图像进行去噪、增强以及边缘提取等深层次的处理,有效的改善图像质量。     

一种图像分层表述的快速算法

提出一种新的灰度图像分层表述算法.该算法的核心是基于一系列具有高度规律性的灰度函数gn(x,y)来逼近不规则的原图像灰度函数f(x,y).本算法具有快速收敛性,是一个良好的逼近器.由于gn具有高度规律性,致使用较少的存储空间就可实现对它的存储.这一算法为生物图像的数据处理和重构提供一条新的途径.     

超声诊断科中的计算机应用

计算机发展的日新月异,其功能强、运算快、精度高、存取和查询方便,现已成为本科不可缺少的一个重要工具。我们利用图像处理软件将原灰阶图伪彩色化,检查近方例病人取得良好的效果;同时能将图像重排、加字等编辑和对某一区域作直方图计算;将图像存储、再现和传输,决不会降低图像质量。利用FOXBASE+等软件进行病人资料的管理、数据统计和文件处理。作者提出了超声的三维成像和图像处理网络的会诊中心,如能实现将是超声诊断上一台阶。     

基于B超图像评价HIFU治疗剂量对组织损伤程度的影响

基于B超图像分析HIFU治疗中辐照剂量、组织凝固性坏死区域和图像参数之间的关系。通过对高强度聚焦超声辐照新鲜离体组织前后获得的B超图像做数字减影处理,计算图像灰度平均值,同时切片观察并记录生物组织的凝固性坏死区域大小,在此基础上得到大批量数据的统计特性。结果表明：辐照剂量、组织凝固性坏死区域与B超图像灰度平均值在一定范围内成正相关性;当凝固性坏死区域增大到一定程度时,B超图像灰度平均值不再增大,而是呈无规律分布。B超图像灰度可反映组织损伤程度,为实时监控HIFU治疗效果提供依据。     

应用计算机图像技术识别间日疟原虫的初步研究

目的应用数字图像技术识别间日疟原虫。方法基于图像预处理、图像分割、特征提取、判决分类等步骤,分别对间日疟原虫薄血膜的裂殖体图像进行处理,观察其识别效率和准确度。结果边缘检测和图像灰度值检测两种方法均能够识别间日疟原虫裂殖体,而二者的联合方法可以得到较好的识别效果。结论初步探索采用边缘和图像灰度联合检测的方法能够识别间日疟原虫薄血膜的裂殖体。     

In situ monitoring of cell concentration in a photobioreactor using image analysis: comparison of uniform light distribution model and artificial neural networks

Light intensity is a very important factor that determines the growth of photosynthetic cells. In this study, the light distribution in a photobioreactor was analyzed by processing the images captured with a digital camera. The contour images obtained by filtering the original images clearly showed the effects of the cell concentration and external light intensity on the light distribution. Image-processing techniques were then applied to predict the cell density in the photobioreactor. To correlate the cell concentration with the light intensity in the photobioreactor, the captured images were processed using two different approaches. The first method involved the use of an average gray value after deriving a simplified model equation that could be related to the cell density. The second method involved the use of local points instead of a representative value. In this case, an artificial neural network model was adopted to infer the cell density from the information of the local points. By using these two methods, it was possible to relate the image data to the cell concentration. Finally, we compared these two methods with regard to their accuracy, easiness, and effectiveness.     

Visualization of gluten and starch distributions in dough by fluorescence fingerprint imaging

A novel method combining imaging techniques and fluorescence fingerprint (FF) data measurement was developed to visualize the distributions of gluten and starch in dough without any preprocessing. Fluorescence images of thin sections of gluten, starch, and dough were acquired under 63 different combinations of excitation and emission wavelengths, resulting in a set of data consisting of the FF data for each pixel. Cosine similarity values between the FF of each pixel in the dough and those of gluten and starch were calculated. Each pixel was colored according to the cosine similarity value to obtain a pseudo-color image showing the distributions of gluten and starch. The dough sample was then fluorescently stained for gluten and starch. The stained image showed patterns similar to the pseudo-color FF image, validating the effectiveness of the FF imaging method. The method proved to be a powerful visualization tool, applicable in fields other than food technology.     

Visualization of Gluten and Starch Distributions in Dough by Fluorescence Fingerprint Imaging

A novel method combining imaging techniques and fluorescence fingerprint (FF) data measurement was developed to visualize the distributions of gluten and starch in dough without any preprocessing. Fluorescence images of thin sections of gluten, starch, and dough were acquired under 63 different combinations of excitation and emission wavelengths, resulting in a set of data consisting of the FF data for each pixel. Cosine similarity values between the FF of each pixel in the dough and those of gluten and starch were calculated. Each pixel was colored according to the cosine similarity value to obtain a pseudo-color image showing the distributions of gluten and starch. The dough sample was then fluorescently stained for gluten and starch. The stained image showed patterns similar to the pseudo-color FF image, validating the effectiveness of the FF imaging method. The method proved to be a powerful visualization tool, applicable in fields other than food technology.     

A Method for the Evaluation of Image Quality According to the Recognition Effectiveness of Objects in the Optical Remote Sensing Image Using Machine Learning Algorithm

Objective and effective image quality assessment (IQA) is directly related to the application of optical remote sensing images (ORSI). In this study, a new IQA method of standardizing the target object recognition rate (ORR) is presented to reflect quality. First, several quality degradation treatments with high-resolution ORSIs are implemented to model the ORSIs obtained in different imaging conditions; then, a machine learning algorithm is adopted for recognition experiments on a chosen target object to obtain ORRs; finally, a comparison with commonly used IQA indicators was performed to reveal their applicability and limitations. The results showed that the ORR of the original ORSI was calculated to be up to 81.95%, whereas the ORR ratios of the quality-degraded images to the original images were 65.52%, 64.58%, 71.21%, and 73.11%. The results show that these data can more accurately reflect the advantages and disadvantages of different images in object identification and information extraction when compared with conventional digital image assessment indexes. By recognizing the difference in image quality from the application effect perspective, using a machine learning algorithm to extract regional gray scale features of typical objects in the image for analysis, and quantitatively assessing quality of ORSI according to the difference, this method provides a new approach for objective ORSI assessment.     

To the ways of the most reasonable implementation of digital radiography into the practical public health of the Russian Federation

The main idea of the authors' paper is to propose the most reasonable way of actively introducing the digital principle into the traditional roentgenological section of radiation diagnosis. For this, a luminophore digital radiography system has been chosen. The authors of the paper give a full-scale assessment and appropriate recommendations for its use. The paper essentially discusses the entire complex of matters that permit assessment whether its sound use is possible in regional and municipal health care systems. This is both a section devoted to a dose load, by making a comparative assessment of luminophore radiography and "the green system" and a study of different clinical diseases (456 cases). In their study, the authors have applied an original principle in the formation of an image obtained and some other approaches in order to make a comprehensive assessment of this method. In the authors' opinion, luminophore radiography has a variety of advantages. Firstly, this technique can be simultaneously applied to several nondigital apparatuses, including those available in the ward and it shows a rather diagnostic effectiveness and economic profitability, yields a qualitative image of varying density tissues upon single exposure, and has some other capacities of the CR system as a digital technique. All this things considered, the authors consider that luminophore radiography may be one of the main ways of introducing a digital technique into the conventional roentgenological section of radiation diagnosis at the level of regional and municipal heath care systems.     

Fully automated measurements by light microscopy of tissue sections using a cellular array computer

Software was developed for the acquisition, segmentation and analysis of microscopic OD-images on a VICOM digital image processor, extended with a VISIOMORPH morphoprocessor board. The delineation algorithms for peroxisomes, lysosomes, and nuclei in liver, kidney, and adrenal gland sections start by thresholding the difference between the original image and a low pass filtered version. The resulting binary mask is then processed by morphological operations in order to produce an object overlay. The efficiency of the programs is evaluated by comparing delineated objects at different OD-levels, created by varying the stain or by multiplying the original pixel values with constant factors. Manual delineation on some images is also used as a reference. More complex algorithms are used for the delineation of muscle fibres in ATP-ase-stained sections and immunocytochemically labelled cells in monolayer preparations. Muscle images from parallel sections with different stainings are matched with a coordinate transform, enabling the transfer of the object mask from a single delineated image to the unprocessed images and thus obtain all necessary information for fibre classification. After segmentation, the OD-images and their object overlays are fed into a data extraction program, measuring for each delineated object user-selected features. Data are sent to a VAX for statistical interpretation.     

The CR digital radiography system in traditional X-ray studies (according to the materials of the Moscow Regional Clinical Research Institute)

The basic idea of the author's paper is to attempt to estimate and prove whether it is advisable to use the CR digital radiography system in a multidisciplinary therapeutic institution mainly at the municipal level. The pre-requisites for this were the results of diagnostic studies of different diseases of organs and systems. Emphasis is laid on the specific features of use of this digital system; namely, it can convert several analogue X-ray apparatuses to digital ones and it is more profitable than indirect image numeralization apparatuses and produces lower radiation loads. This all makes the use of these digital systems tempting in traditional X-ray study. A comparatively large material (4237 cases) was used to show the efficiency of the CR digital radiography system in the diagnosis of ENT diseases, osteology, interventional radiology, gastroenterology, pediatrics and to demonstrate a modernized approach to having a solid copy of a digital image, the possibilities of postprocessing that may enhance the validity of existing X-ray symptoms. This all allows the author to recommend that the CR digital radiography systems be used in traditional X-ray study for the diagnosis of various diseases occurring in a multidisciplinary health care facility mainly at municipal and regional levels.     

Quantitation of cell area on glass and fibronectin-coated surfaces by digital image analysis.

By using digital image processing and analysis, two procedures were developed to rapidly measure the projected area of a field of adherent 3T3 fibroblasts without staining of cell borders. The cell area of newly attached and rounded cells with well-resolved borders was obtained by a gray value thresholding procedure. For cells that had undergone an appreciable degree of spreading, cell boundaries were less distinct and a nonlinear spatial Sobel filter was used, followed by thresholding. For both procedures, linear relations were observed between cell areas obtained from image analysis and cell areas obtained by tracing. The areas of a population of traced cells were not statistically different from the area distribution obtained by using the standard curves for the processed images. Uncertainty in the estimated mean area depended only upon the number of cells examined. Approximate numbers of cells required to obtain estimates of the mean are calculated. As an application of these procedures, cell areas were measured for 3T3 cells attached to glass and fibronectin-coated surfaces and were found to be significantly larger for cells spreading on fibronectin-coated glass than on glass alone. Increased cell area during spreading on fibronectin-coated surfaces was proportional to increased cell adhesivity after exposure to a shear stress of 58 dyn/cm2.