Level Set Segmentation of Breast Masses in Contrast-Enhanced Dedicated Breast CT and Evaluation of Stopping Criteria

Dedicated breast CT (bCT) produces high-resolution 3D tomographic images of the breast, fully resolving fibroglandular tissue structures within the breast and allowing for breast lesion detection and assessment in 3D. In order to enable quantitative analysis, such as volumetrics, automated lesion segmentation on bCT is highly desirable. In addition, accurate output from CAD (computer-aided detection/diagnosis) methods depends on sufficient segmentation of lesions. Thus, in this study, we present a 3D lesion segmentation method for breast masses in contrast-enhanced bCT images. The segmentation algorithm follows a two-step approach. First, 3D radial-gradient index segmentation is used to obtain a crude initial contour, which is then refined by a 3D level set-based active contour algorithm. The data set included contrast-enhanced bCT images from 33 patients containing 38 masses (25 malignant, 13 benign). The mass centers served as input to the algorithm. In this study, three criteria for stopping the contour evolution were compared, based on (1) the change of region volume, (2) the average intensity in the segmented region increase at each iteration, and (3) the rate of change of the average intensity inside and outside the segmented region. Lesion segmentation was evaluated by computing the overlap ratio between computer segmentations and manually drawn lesion outlines. For each lesion, the overlap ratio was averaged across coronal, sagittal, and axial planes. The average overlap ratios for the three stopping criteria ranged from 0.66 to 0.68 (dice coefficient of 0.80 to 0.81), indicating that the proposed segmentation procedure is promising for use in quantitative dedicated bCT analyses.     

Segmentation of Bacteria Image Based on Level Set Method

In biology ferment engineering, accurate statistics of the quantity of bacteria is one of the most important subjects. In this paper, the quantity of bacteria which was observed traditionally manuauy can be detected automatically. Image acquisition and processing system is designed to accomplish image preprocessing, image segmentation and statistics of the quantity of bacteria. Segmentation of bacteria images is successfully realized by means of a region-based level set method and then the quantity of bacteria is computed precisely, which plays an important role in optimizing the growth conditions of bacteria.     

一种基于快速混合型K均值的水平集图像分割方法

目的:为提高水平集图像分割方法的速度。方法:本文介绍一种基于快速混合型K均值的水平集方法用于图像分割。首先介绍基于Mumford-Shah模型的水平集方法;然后介绍传统标准K均值方法与水平集方法的联系,分析其缺陷;最后提出了一种快速混合型K均值的方法,在保持传统水平集算法鲁棒性的前提下,较好地提高了计算的速度。结果:该方法与标准水平集方法相比,运算所花费时间相对减少。结论:该方法利用K均值算法的简易和高效率,达到提高水平集方法分割速度的目的,具有一定的实用价值。     

基于直方图拟合的MRI图像水平集分割

利用混合高斯模型对MRI图像直方图进行分析,将拟合获得的特征参数作为水平集曲线进化的约束条件,对医学图像进行分割。分割中采用的自适应Level Set方法,能够自适应地确定曲线进化方向（扩张或收缩）,而不必在分割之前指定其进化方向,减少了人工干预;同时也克服了传统测地活动轮廓线（GAC）方法对图像梯度信息的过分依赖,以及由于对图像进行大尺度高斯平滑处理造成边缘点移动、定位准确度下降的缺陷。分别对MRI仿真和真实图像进行了实验,MRI仿真实验的分割敏感性、专一性和总体性能指标分别达到了94.72%、97.52%和97.22%。分割结果的定量分析和定性分析表明算法的有效性以及较高的分割准确度。     

结合脑图谱和水平集的MR图像分割的研究

本文利用脑图谱的先验知识并结合水平集等算法实现对脑MR图像的初步分割。主要步骤：（1）选取数字脑图谱，对图谱进行预处理；（2）实现图谱与脑MR图像的配准；（3）利用图谱提供的轮廓信息对水平集算法进行初始化，完成颅骨和脑脊液的提取以及脑白质和脑灰质的分割。实验结果表明，利用脑图谱提供的信息可有效解决水平集算法初始化问题，缩小求解空间，减少迭代次数，该方法具有较好的鲁棒性。     

基于单水平集函数的细胞分割算法

目的：由于细胞图像十分复杂,传统的基于像素或者边界的图像分割方法难以精确的实现细胞分割。因此,需要设计一种可以实现细胞图像精确分割的方法。方法：结合大津分割算法和主动轮廓模型的优点,设计出一种基于单水平集函数的细胞分割算法,首先对细胞图像大津分割,其结果作为水平集函数的初始值,然后使用迭代法对水平集函数演化。采用MATLAB对显微镜下获取的细胞图像进行试验,将本文改进后的算法与常规的算法进行了对比。结果：与传统的水平集分割算法相比,本文方法对细胞图像分割结果更加准确,迭代次数减少一半左右,因此分割时间也减少了一半左右。结论：结合细胞图像的结构特点,利用大津分割结果作为主动轮廓模型的初始值,可有效解决主动轮廓模型因为初始值设置不当导致的分割缺陷问题,水平集函数能够跟踪拓扑结构变化,具有计算精度高、算法稳定、优化边界清晰光滑等优点,在本文中得到了充分的应用。因此本文所提出的算法能够高效地实现细胞图像的分割。     

Comparison of Algorithms to Enhance Spicules of Spiculated Masses on Mammography

We have developed an algorithm for enhancement of spicules of spiculated masses, which uses the discrete radon transform. Previously, we employed a commonly used method to compute the discrete radon transform, which we refer to as the DRT. Recently, a new, more exact method to compute the discrete radon transform was developed by Averbuch et al, which is called the fast slant stack (FSS) method. Our hypothesis was that this new formulation would help to improve our enhancement algorithm. To test this idea, we conducted multiple two-alternative-forced-choice observer studies and found that most observers preferred the enhanced images generated with the FSS method.     

Impact of Breast Density on Computer-Aided Detection in Full-Field Digital Mammography

The goal of this study was to evaluate the performance of a computer-aided detection (CAD) system in full-field digital mammography (Senographe 2000D, General Electric, Buc, France) in finding out carcinomas depending on the parenchymal density. A total of 226 mediolateral oblique (MLO) and 186 craniocaudal (CC) mammographic views of histologically proven cancers were retrospectively evaluated with a digital CAD system (ImageChecker V2.3 R2 Technology, Los Altos, CA, USA). Malignant tumors were detected correctly by CAD in MLO view in 84.85% in breasts with parenchymal tissue density of the American College of Radiology (ACR) type 1, in 70.33% of the ACR type 2, in 68.12% of the ACR type 3, and in 69.70% of the ACR type 4. For the CC view, similar results were found according to the ACR types. Using the chi-square and McNemar tests, there was no statistical significance. However, a trend of better detection could be seen with decreasing ACR type. In conclusion, there seems to be a tendency for breast tissue density to affect the detection rate of breast cancer when using the CAD system.     

基于医学图像内容检索的计算机辅助乳腺X线影像诊断技术

乳腺癌是女性中高发的恶性肿瘤疾病.近年来,其发病率呈增高趋势.早期发现、早期诊断和早期治疗是降低乳腺癌患者死亡率的关键.计算机辅助诊断(CAD)技术能够有效提高早期诊断的准确性,而基于内容医学图像检索(CBMIR)技术的引入,为乳腺癌的诊断提供了有效的决策支持.文中就近年来基于医学图像内容检索的计算机辅助乳腺X线影像诊断关键技术进行了较为详尽的综述,包括微钙化和肿块检测、特征提取、相似性测度和相关反馈技术等,同时对该领域的发展趋势进行了展望.     

用改进的耦合水平集方法从MSCT中分割左心室

新型的多层螺旋CT(MSCT)能提供含有时间信息的四维CT成像数据,可用于动态心、肺功能的分析,但如何从中自动或半自动地精确分割出心脏和肺等器官是研究成功的关键。提出一种基于改进的耦合水平集自动分割方法(ICLS),从心脏MSCT数据集中精确提取左心室腔和心肌。根据层片间的结构连续性,自动定位并获取左心室腔的粗轮廓,作为水平集的初始化轮廓,同时,将腔粗轮廓和左心室先验知识融合到耦合水平集中,自动获取左心室内外膜的精确边缘。在8例256层MSCT三维心脏数据集上的实验表明I,CLS模型对血腔的分割结果和手工分割结果的平均相似度在95%以上,心肌的平均相似度在90%以上;分割结果的三维表面重建验证了ICLS方法提取出的左心室具有良好的各向同一性和完整性。     

An Interactive System for Computer-Aided Diagnosis of Breast Masses

Although mammography is the only clinically accepted imaging modality for screening the general population to detect breast cancer, interpreting mammograms is difficult with lower sensitivity and specificity. To provide radiologists “a visual aid” in interpreting mammograms, we developed and tested an interactive system for computer-aided detection and diagnosis (CAD) of mass-like cancers. Using this system, an observer can view CAD-cued mass regions depicted on one image and then query any suspicious regions (either cued or not cued by CAD). CAD scheme automatically segments the suspicious region or accepts manually defined region and computes a set of image features. Using content-based image retrieval (CBIR) algorithm, CAD searches for a set of reference images depicting “abnormalities” similar to the queried region. Based on image retrieval results and a decision algorithm, a classification score is assigned to the queried region. In this study, a reference database with 1,800 malignant mass regions and 1,800 benign and CAD-generated false-positive regions was used. A modified CBIR algorithm with a new function of stretching the attributes in the multi-dimensional space and decision scheme was optimized using a genetic algorithm. Using a leave-one-out testing method to classify suspicious mass regions, we compared the classification performance using two CBIR algorithms with either equally weighted or optimally stretched attributes. Using the modified CBIR algorithm, the area under receiver operating characteristic curve was significantly increased from 0.865 ± 0.006 to 0.897 ± 0.005 (p < 0.001). This study demonstrated the feasibility of developing an interactive CAD system with a large reference database and achieving improved performance.     

Characterizing the Clustered Microcalcifications on Mammograms to Predict the Pathological Classification and Grading: A Mathematical Modeling Approach

In this study, we explore a mathematical model to characterize the clustered microcalcifications on mammograms for predicting the pathological classification and grading. Our database consists of both retrospective cases (78 cases) and prospective cases (31 cases) with pathologically diagnosed clusters of microcalcifications on mammograms. The microcalcifications were divided into four grades: grade 0, benign breast disease including mastopathies (n = 12) and fibroadenomas (n = 20); grade 1, well-differentiated infiltrating ductal carcinoma (n = 12); grade 2, moderately differentiated infiltrating ductal carcinoma (n = 38); grade 3, poorly differentiated infiltrating ductal carcinoma (n = 27). A feature parameter, defined as the pattern form factor of microcalcification cluster θ by us, combines five computer-extracted image parameters of microcalcification clusters of those mammograms. In every case, only one imaging was selected for modeling analysis. A total of 109 imagings were adopted in current study. We find the existence of a positive relationship between the feature parameter θ and pathological grading G of microcalcifications in retrospective cases, which was expressed as G =  6.438 + 1.186 ×  Ln <θ>. The model above has been verified further by the prospective study with a comparative evaluation accuracy of approximately 77.42%. The binary predication simply for both benignancy and malignancy was also included using same but reshuffled data, and the receiver operating characteristic (ROC) analysis was performed with ROC value 0.74351∼0.79891. As one candidate for feature parameter in computer-aided diagnosis, the pattern form factor θ of clustered microcalcifications may be useful to predict the pathological grading and classification of microcalcification clusters on mammography in breast cancer.     

Detection of Breast Cancer with a Computer-Aided Detection Applied to Full-Field Digital Mammography

A study was conducted to evaluate the sensitivity of computer-aided detection (CAD) with full-field digital mammography in detection of breast cancer, based on mammographic appearance and histopathology. Retrospectively, CAD sensitivity was assessed in total group of 152 cases for subgroups based on breast density, mammographic presentation, lesion size, and results of histopathological examination. The overall sensitivity of CAD was 91 % (139 of 152 cases). CAD detected 100 % (47/47) of cancers manifested as microcalcifications; 98 % (62/63) of those manifested as non-calcified masses; 100 % (15/15) of those manifested as mixed masses and microcalcifications; 75 % (12/16) of those manifested as architectural distortions, and 69 % (18/26) of those manifested as focal asymmetry. CAD sensitivity was 83 % (10/12) for cancers measuring 1–10 mm, 92 % (37/40) for those measuring 11–20 mm, and 92 % (92/100) for those measuring >20 mm. There was no significant difference in CAD detection efficiency between cancers in dense breasts (88 %; 69/78) and those in non-dense breasts (95 %; 70/74). CAD showed a high sensitivity of 91 % (139/152) for the mammographic appearance of cancer and 100 % sensitivity for identifying cancers manifested as microcalcifications. Sensitivity was not influenced by breast density or lesion size. CAD should be effective for helping radiologists detect breast cancer at an earlier stage.     

塔式多相水平集三维医学图像多目标分割算法

由于Chan-Vese（GV）模型采用的是单一水平集，所以只能通过水平集的符号表示目标和背景两个区域。当三维医学图像的目标区域含有复杂的子目标时，C-V模型将无法表示。为了解决GV模型在表示三维子目标上的局限，首先将二维GV模型拓展为三维模型；其次，依据同时明度对比提出了背景填充技术，理论上保证了轮廓曲面仅收敛于目标内部；再次，将该技术与三维C-V模型相结合提出了塔式多相水平集算法；最后，实验结果表明，本算法能够实现三维医学图像多目标分割（n-1次收敛可以实现”目标分割），并且能够检测由弱边缘构成的子目标。     

医学图像分割中的主动轮廓模型研究现状

主动轮廓模型具有强大的先验知识引入能力,非常适合解决复杂医学图像分割问题。本文介绍了两种主动轮廓模型的基本原理及其相互关系,详细综述了模型的几个重要改进措施,包括曲线的表示方式、基于梯度的ACM、基于区域的ACM,以及结合先验形状的ACM,并讨论了医学图像分割中的主要应用实例,最后展望了模型今后的研究方向。     

基于3D医学图像的血管三维分割

血管三维分割在血管疾病(如狭窄或畸形)诊断、手术规划和手术引导等许多实际应用中发挥重要作用。但三维分割的实时性仍是一个难题。本研究提出一种基于水平集的快速三维血管分割方法,该方法用内、外邻域曲面来描述被分割目标的边界,并定义水平集函数为简单的整数符号距离函数。通过扫描内外邻域曲面上的点,使之在速度场的作用下向目标边界移动。该方法的不同之处在于利用简单的模型极大地减小了计算量,分割速度快,大容量的MS-CTA[2563体素]图像可在20s内处理完毕。同时,展示了一些三维血管的分割实例。特别需要指出的是,对于人体的大血管,可在不经血管造影的情况下,直接从CT等三维图像中分割出来。     

基于RoughSet的特征集融合PET/CT肺部肿瘤CAD模型

针对肺部肿瘤PET/CT感兴趣区域(ROI)在高维特征表示下存在着特征相关和维数灾难问题,提出了一种基于粗糙集特征集融合的PET/CT肺部肿瘤CAD模型。首先提取肺部肿瘤ROI的8维形状特征、7维灰度特征、3维Tamura纹理特征、56维GLCM特征和24维频域特征,得到98维特征矢量;然后基于遗传算法的知识约简方法和基于属性重要度的启发式算法对提取的特征集合分别进行特征级融合得到特征子集G1、G2、G3,A1、A2、A3,降低特征矢量的维数;再次利用网格寻优算法优化核函数的SVM作为分类器分别进行融合前和融合后的分类识别比较,基于遗传算法的特征集融合和基于属性重要度的特征集融合的分类识别比较2组实验;最后以2 000幅肺部肿瘤的PET/CT图像为原始数据,采用基于粗糙集特征集融合的肺部肿瘤PET/CT计算机辅助诊断模型对肺部肿瘤进行辅助诊断。实验结果表明,经过粗糙集特征集融合的肺部肿瘤诊断识别方法能有效提高肺部肿瘤的诊断正确率,一定程度上降低了特征之间的相关性。     

Determining the View of Chest Radiographs

Automatic identification of frontal (posteroanterior/anteroposterior) vs. lateral chest radiographs is an important preprocessing step in computer-assisted diagnosis, content-based image retrieval, as well as picture archiving and communication systems. Here, a new approach is presented. After the radiographs are reduced substantially in size, several distance measures are applied for nearest-neighbor classification. Leaving-one-out experiments were performed based on 1,867 radiographs from clinical routine. For comparison to existing approaches, subsets of 430 and 5 training images are also considered. The overall best correctness of 99.7% is obtained for feature images of 32 × 32 pixels, the tangent distance, and a 5-nearest-neighbor classification scheme. Applying the normalized cross correlation function, correctness yields still 99.6% and 99.3% for feature images of 32 × 32 and 8 × 8 pixel, respectively. Remaining errors are caused by image altering pathologies, metal artifacts, or other interferences with routine conditions. The proposed algorithm outperforms existing but sophisticated approaches and is easily implemented at the same time.     

血清CA15-3和超声、CT、MRI检查对乳腺癌诊断价值的比较

目的：探讨了三种非创伤性影像检查方法,超声（US）、X线计算机断层摄影技术（CT）和磁共振成像（MRI）及血清CA15-3水平在乳腺癌诊断中的敏感性和准确性,以提高对乳腺癌早期诊断的方法。方法：回顾分析,比较38例乳腺癌患者的US、CT和MRI及CA15-3的优缺点。结果：乳腺癌的确诊率US为76.3%,CT为84.2%,MRI为93.8%,CA15-3为68.4%。US对乳腺癌的早期检出率较高,但确诊率较低。CT和MRI对乳腺癌的确诊率较高,血清CA15-3的确诊率较低。结论：US、CT、MRI和血清CA15-3各有其优点,合理的综合应用可提高对乳腺癌的早期诊断。     

智能肝肿瘤CT图像分割

提出了一种智能肝肿瘤CT图像分割的新方法.该方法将医学专家的高层知识融合到图像分割算法中,使算法具有智能性,能够更加准确、快速地实现分割.根据医学图像分割不同阶段的特点以及不同算法的适用性,结合了多尺度分水岭变换与模糊聚类方法,从总体上达到最佳效果.将图像空间信息引入传统的基于灰度的模糊C均值聚类算法中,对传统的模糊C均值聚类算法的目标函数进行修正,推导出修正后算法的迭代公式,并证明了迭代的收敛性.对实际CT肝肿瘤图像的分割实验结果验证了所提方法的有效性.