超声乳腺肿瘤图像的边缘提取

目的探求乳腺肿瘤超声图像的边缘提取。方法广义梯度矢量流Snake模型已经成功地用于噪声相对比较小的CT、MRI等医学图像,然而乳腺肿瘤超声图像对比度低,斑点噪声大,很难将该模型直接应用于乳腺肿瘤超声图像。本文针对乳腺肿瘤超声图像的特点如图像对比度低,斑点噪声大,部分边缘缺失,肿瘤内部微细结构分布复杂(如血管,钙化灶等),特别恶性肿瘤还具有复杂形状等,采用相应的图像处理技术如非线性各向异性扩散滤除斑点噪声,形态学滤波器平滑图像,直方图均衡化提高图像的对比度,最后将该模型引入到乳腺肿瘤超声图像边缘提取。结果实验对158例乳腺肿瘤超声图像进行边缘提取,定量和定性分析均获得满意的结果。结论本文方法可以有效地用于超声乳腺肿瘤图像的边缘提取。     

基于阈值分割和Snake模型的弱边缘医学超声图像自动分割

医学超声图像分割是图像处理中的一项关键技术.文章以胆结石超声图像为例,介绍一种新的弱边缘超声图像自动分割算法.首先采用基于直方图凹度分析的闽值分割方法确定Snake模型的初始蛇,再基于Snake模型结合贪婪算法对图像进行目标分割.实验结果表明该算法对弱边缘现象较为严重的医学超声图像进行目标分割时,定位准确,分割效果良好,足一种全自动的超声医学图像分割方法.     

肝癌图像感兴趣目标的准确分割

背景:Snake模型为医学图像分割提供了一个全新的分割方式,可以克服传统图像分割方法在医学图像分割中的缺点.目的:针对肝癌CT图像特点,提出了一种改进的B样条曲线的Snake模型图像分割算法.方法:对腹部CT图像进行预处理,获得肝脏癌变部分的初始轮廓,再构造闭合B样条Snake模型,最后使用MMSE最小化外力变形模型以实现图像的准确分割.结果与结论:改进的B-Snake分割算法不仅减少了噪声的影响,而且使Snake曲线较好地收敛于目标轮廓边缘,对于肝癌CT图像该方法取得了感兴趣目标的良好分割效果.     

基于相位信息的乳腺超声图像水平集分割

目的基于相位信息改进距离正规化水平集演化(DRLSE)模型的速度收敛项,改善对乳腺肿瘤超声图像的分割效果。方法首先,利用Log-Gabor滤波器组对图像进行频域滤波,得到一组基于相位信息的特征图。其次,在相位一致性的基础上,求出乳腺超声图像经高斯噪声补偿后的最大方向能量相位PC(M),并采用细节保留各向异性扩散滤波(DPAD)模型对PC(M)降噪,减少斑点噪声的干扰。最后,选用Sigmoid函数,将滤波后的PC(M)作为其自变量,以替换DRLSE模型中的速度收敛项。结果采用改进后的模型对多幅临床乳腺肿瘤超声图像进行分割,分割结果显示基于相位信息的正规化水平集演化(PB-DRLSE)模型在相似性(SI)、真阳性(TP)和假阴性(FN)方面均优于原始DRLSE模型(P均<0.05)。结论本研究提出的分割方法较之原始模型对乳腺肿瘤超声图像的分割更为优越。     

基于超声图像边缘的乳腺肿瘤良恶性判别

目的：提取乳腺肿瘤超声图像的边缘,判别乳腺肿瘤的良恶性。方法：提出了一种改进的各向异性扩散滤波,即根据图像不同的梯度选择不同的扩散系数的扩散方程,滤除噪声的同时很好地保留了图像的边缘信息。然后在Level Set方法中提出一种新的变分公式,完全避免了重初始化步骤,且水平集函数的初始化灵活,采用手工勾画粗略边界的半自动分割流程,不仅提高了分割准确性,同时也进一步提高了分割效率。结果：采用综合灰度共生矩阵计算乳腺肿瘤的纹理特征和模糊C均值的方法进行良恶性判别,正确率为72.64%。结论：实验证明,本文算法能高效准确地提取出肿瘤边界,为肿瘤良恶性的判别提供可靠的依据。     

计算机辅助鉴别乳腺良、恶性肿块的临床价值

目的 提出一种基于灰度级二维直方图的计算机辅助分割算法,对乳腺高频超声图像中的肿块进行自动识别和分割处理,旨在提高乳腺良、恶性肿块的检出准确率.方法 采集100个乳腺肿块二维超声图像共466张(原片),应用计算机软件对原片进行分割处理,得到分割后图片.超声医师采用双盲法分别根据原片和分割后图片中的超声征象进行良、恶性判断,运用受试者工作曲线(ROC曲线)计算曲线下面积(A),比较前后两次诊断结果 ,分析图片处理前后诊断结果 的差异性.结果 处理后的图片中乳腺肿块的边缘、钙化等信息明显突出.超声医师对良、恶性肿块的确诊率明显提高.当特异性为74.31%时,诊断敏感性由基于原片的70.32%提高到图片分割后的90.52%.ROC曲线下面积由分割前的80.8%上升到90.5%,差异有统计学意义(P<0.01).结论 此分割算法能明显优化乳腺肿块的边缘信息,较好地突显肿块内微钙化,在一定程度上降低漏诊率和误诊率,提高乳腺良恶性肿块的确诊率.     

一种使用膨胀气球模型的Snakes多目标分割方法

目的为实现一种有效的基于Snakes的多目标医学图像分割算法。方法通过模拟气球在含多个物体的封闭空间内的膨胀,来实现Snake曲线的拓扑形变。算法使用一个燃烧区域滞后跟踪Snake曲线运动来给出其演化停止条件,然后忽略停止条件并继续演化Snake曲线,就能完成燃烧而得到一个连通区域。提取出已燃烧区域的轮廓可给出与各分割目标对应的子Snake。结果所提出的算法能够正确分割出医学图像中多目标对象的轮廓。结论此基于模型的分割算法原理明确且易于实现,具有较好的实用性。     

灰阶超声鉴别诊断良、恶性乳腺肿瘤

目的探讨灰阶超声鉴别良、恶性乳腺肿瘤的价值。方法利用改进的Level Set变分模型对126例乳腺肿瘤的超声图像进行分割,提取肿瘤边界,分别计算16个形态特征参数,结合特征参数间的相关性及部分特征参数性质确定特征向量组合,最后用模糊C-均值方法鉴别乳腺肿瘤的良、恶性。结果 126例中,恶性肿瘤50例,良性肿瘤76例。通过Level Set模型得到了较好的分割良、恶性的准确率达80.95%(102/126),其敏感度、特异度、阳性预测值和阴性预测值分别为80.00%(40/50)、81.58%(62/76)、74.07%(40/54)和86.11%(62/72)。结论良、恶性乳腺肿瘤在形态上有较大差异,灰阶超声可有效鉴别乳腺肿瘤的性质。     

超声图像中基于经验模态分解自动提取内-中膜厚度

目的为改善传统人工标记测量血管内-中膜厚度(IMT)的准确性和稳定性,提出基于图像分割技术的经验模态分解(EMD)改进算法。方法采用EMD改进算法去噪,根据血管壁的特点,在其中的极值点插值步骤使用非均匀的二维B样条函数,在水平和垂直方向上控制网格的密度不同,分别满足不同的分辨精度和平滑程度要求,改进了原始的二维EMD算法;然后通过K均值方法从图像中分离出血管腔、血管壁和其他组织,使用数学形态学算法逐步得到最终的内-中膜组织分割结果。结果改进EMD算法取得了较好的重建和滤波效果,有效克服了超声图像的强噪声和低分辨力对图像分割的限制,整个算法分割比较准确,算法复杂度相对较小。结论改进EMD算法是在超声图像中自动提取内-中膜的较有潜力的方法,能有效去除超声噪声,同时保留条纹结构的细节和边缘信息,有望于其他强噪声环境下提取条纹结构。     

基于MRI图像的羊水体积的测量

目的 探讨基于MRI图像,通过算法计算测量羊水量的可行性。方法 利用MatLab图像处理技术,对胎儿磁共振图像进行分割,提取目标区域并计算目标区域的面积,乘以层厚得出一层的体积,再将每层体积相加计算得到羊水总体积。结果 通过该算法最终计算得出羊水的体积为495.10 ml。定性分析显示,图像羊水分割边缘与原图目标区域的边缘拟合较好。定量分析显示,手动金标准分割的体积为458.20 ml,本研究算法与手动分割结果的误差率为8.06%。脂肪抑制序列图像分割效果定性评价亦显示羊水分割边缘与原图目标区域的边缘拟合较好;定量分析显示,金标准手动计算得到的羊水量为557.34 ml,本研究算法计算得到的羊水量为604.50 ml,与手动分割的误差率为8.46%。结论 采用本研究算法测量羊水量切实可行。     

乳腺肿瘤常规超声联合超声造影影像组学特征与乳腺癌分子分型相关性的研究进展

影像组学（radiomics）是一种从医学影像中高通量地提取影像特征来深入挖掘内部数据信息的技术方法,通过肿瘤分割、特征提取与模型建立来辅助临床对肿瘤的诊断与治疗。在精准医疗时代,乳腺癌（breast cancer,BC）的个体化早期诊治尤为重要。常规超声是诊断乳腺肿瘤的重要影像学方法,超声造影（contrast enhanced ultrasound,CEUS）可以实时显示乳腺肿瘤微血管灌注的形态学及功能学变化,在此基础上产生的超声及超声造影影像组学在乳腺肿瘤良恶性诊断及判断乳腺癌分子分型中具有潜在临床应用价值。本文就乳腺肿瘤常规超声联合超声造影影像组学特征与乳腺癌分子分型相关性方面进行综述。     

3-D breast ultrasound segmentation using active contour model

In this study, we made use of the discrete active contour model to overcome the natural properties of ultrasound (US) images, speckle, noise and tissue-related textures, to segment the breast tumors precisely. Determination of the real tumor boundary with the snake-deformation process requires an initial contour estimate. However, the manual way to sketch an initial contour is very time-consuming. Thus, we propose an automatic initial contour-finding method that not only maintains the tumor shape, but also is close to the tumor boundary and inside the tumor. During the deformation process, to prevent the snake trapping into the false position caused by tissue-related texture or speckle, we added the edge information as an image feature to define the external force. In addition, because the 3-D volume of a tumor is essentially constructed by a sequence of 2-D images, our method for finding boundaries of a tumor can be extended to 3-D cases. By precisely counting the volume of the 3-D images, we can get the volume of tumor. Finally, we will show that the proposed techniques have rather good performance and lead to a satisfactory result in comparison with the estimated volume and physician's estimate.     

Calcification segmentation based on a different scales superpixels saliency detection algorithm

Accurate detection of breast tumor calcifications is of great significance in assisting doctors’ diagnosis to improve the accuracy of breast cancer early detection. In this article, a different scale of superpixels saliency detection algorithm is used to segment calcifications in breast tumor ultrasound images based on a simple linear iterative cluster. First, a multi-scale saliency segmentation algorithm was used to divide the tumor region of different sizes and weak calcification (Wca) was extracted according to uneven gray distribution and texture contrast between regions. Second, based on single-scale superpixel segmentation of the original image, the strong calcification extraction map was calculated by measuring gray value difference and calcification gray distance features. Finally, the final calcification extraction map was obtained by combining the strong and weak calcification extraction maps. The detection algorithm proposed in this article could effectively detect calcifications in breast ultrasound images.     

Detection of microcalcifications using nonlinear beamforming techniques

Objective: Abundant research demonstrates that early detection of cancer leads to improved patient prognoses. By detecting cancer earlier, when tumors are in their primary stages, treatment can be applied before metastases have occurred. The presence of microcalcifications (MCs) is indicative of malignancy in the breast, i.e., 30-50% of all nonpalpable breast cancers detected using mammograms are based on identifying the presence of MCs. Therefore, improving the ability to detect MCs with modern imaging technology remains an important goal. Specifically, improving the sensitivity of ultrasound imaging techniques to detect MCs in the breast will provide an important role for the early detection and diagnosis of breast cancer. Methods: In this work, a novel nonlinear beamforming technology for ultrasonic arrays is investigated for its ability to detect MCs. The beamforming technique, called null subtraction imaging (NSI), utilizes nulls in the beam pattern to create images using ultrasound. NSI provides improved lateral resolution, a reduction in side lobes, and an accentuation of bright singular targets. Therefore, it was hypothesized that the use of NSI would result in identification of more MCs in rat tumors having a speckle background. To test this hypothesis, rats with tumors were injected with Hydroxyapatite (HA) particles to mimic MCs. Ultrasound was used to scan the rat tumors and images were constructed using conventional delay and sum and using NSI beamforming. Three readers with experience in diagnostic ultrasound imaging examined the 1,344 images and scored the presence or absence of MCs. Discussion: In all, 336 different tumor image slices were recorded and each reconstructed using NSI or conventional delay and sum with Hann apodization. In every image where one or MCs were detected in the Hann reconstructions, MCs were detected in the NSI images. In nine rat tumor images, one or more MCs were detected in the NSI images but not in the Hann images. Conclusions: Statistically, the results did support the hypothesis that NSI would increase the number of MCs detected in the rat tumors.     

基于乳腺超声动态连续影像的深度学习模型建立与初步应用

目的 探讨基于乳腺超声动态连续影像的深度学习模型建立方法并对其效能进行初步验证。方法 对506例女性进行乳腺超声扫查,存储实时动态图像,导入深睿影像智能分析平台,采用基于深度学习的端到端的肿块检出网络对原始动态序列图像进行分析提取,训练建立最优化深度学习模型,并对模型的效能进行测试验证,数据采用Python3.6软件进行统计分析。结果 单帧乳腺超声影像的肿块检出敏感率（0.1、0.2、0.5/scan）为76.6%、84.2%、86.0%,序列乳腺超声影像的肿块检出敏感率（0.1、0.2、0.5/scan）为77.3%、91.8%、95.3%;0.1/scan,单帧乳腺超声影像的肿块检出与序列乳腺超声影像的肿块检出无统计学意义（P >0.05）,0.2/scan,单帧乳腺超声影像的肿块检出与序列乳腺超声影像的肿块检出有统计学意义（P <0.05）,0.5/scan, 单帧乳腺超声影像的肿块检出与序列乳腺超声影像的肿块检出有统计学意义（P <0.05）。结论 基于乳腺超声动态连续影像的深度学习模型能提高乳腺超声影像的肿块检出率。     

Watershed segmentation for breast tumor in 2-D sonography

Automatic contouring for breast tumors using medical ultrasound (US) imaging may assist physicians without relevant experience, in making correct diagnoses. This study integrates the advantages of neural network (NN) classification and morphological watershed segmentation to extract precise contours of breast tumors from US images. Textural analysis is employed to yield inputs to the NN to classify ultrasonic images. Autocovariance coefficients specify texture features to classify breasts imaged by US using a self-organizing map (SOM). After the texture features in sonography have been classified, an adaptive preprocessing procedure is selected by SOM output. Finally, watershed transformation automatically determines the contours of the tumor. In this study, the proposed method was trained and tested using images from 60 patients. The results of computer simulations reveal that the proposed method always identified similar contours and regions-of-interest (ROIs) to those obtained by manual contouring (by an experienced physician) of the breast tumor in ultrasonic images. As US imaging becomes more widespread, a functional automatic contouring method is essential and its clinical application is becoming urgent. Such a method provides robust and fast automatic contouring of US images. This study is not to emphasize that the automatic contouring technique is superior to the one undertaken manually. Both automatic and manual contours did not, after all, necessarily result in the same factual pathologic border. In computer-aided diagnosis (CAD) applications, automatic segmentation can save much of the time required to sketch a precise contour, with very high stability.     

DFY-Ⅱ型超声图像定量分析仪对乳腺良恶性肿瘤的鉴别诊断

目的 研究DFY-Ⅱ型超声图像定量分析仪对乳腺良恶性肿瘤的量化诊断方法。方法 采集手术确诊的良恶性乳腺肿瘤各20例的原始超声图像,使用DFY-II型超声图像定量分析仪提取两组图像的纹理特征和灰度特征参数,对比分析两组问各参数的差异。结果 良恶性乳腺肿瘤患者超声图像的熵、平均灰度、平均声强、扭曲度、边缘不规则度及纵横比参数比较,差异有统计学意义（P〈0．05）。结论 DFY-Ⅱ型超声图像定量分析仪可量化乳腺肿瘤的超声图像特征,熵、平均灰度、平均声强、扭曲度、边缘不规则度及纵横比对乳腺良恶性肿块的超声诊断量化有一定参考价值。     

Quantitative evaluation of diagnostic information around the contours in ultrasound images

Purpose To develop a new contour extraction method for identifying abnormal tissue. Methods We combined two techniques: logarithmic K distribution of a scattering model (method 1) and regional discrimination using the characteristics of local ultrasound images (method 2) into an integrated method (method 3) that provides accurate contours, which are essential for quantitizing border information. Results The diagnostic tissue information around the border of an image can be characterized by its shape and texture statistics. The degrees of circularity and irregularity and the depth–width ratio were calculated for the extracted contours of breast tumors. In addition, gradients, separability, and variance between the two regions along the contour and the area and variance of the internal echoes, were calculated as indices of diagnostic criteria of breast tumors. The quantitized indices were able to discriminate among cysts, fibroadenomas, and cancer. Conclusion In many ultrasound images of breast tumors, the combined techniques, the variance ratio of the logarithmic K distribution to the logarithmic Rayleigh distribution and the multilevel technique with local image information can effectively extract abnormal tissue contours.     

基于改进SUSAN算法的医学图像边缘检测

背景:医学图像的边缘检测是医学图像处理中的一项重要的技术,也是医学图像进一步处理的基础。目的:运用改进的SUSAN算法对医学图像进行边缘检测,取得更丰富的医学图像边缘信息,以便于医学图像的进一步处理。方法:运用Sobel算子对SUSAN算法进行了改进,采用C++语言编程,并在VC++6.0开发平台上实现了改进算法。结果与结论:实验结果表明,该算法能实现阈值的自适应选取,对医学图像中的低对比度的图像边缘有较好的检测效果。