乳腺肿瘤超声图像特征参数量化研究进展

乳腺肿瘤超声图像的特征量化分析对判别肿瘤的良、恶性具有重要价值。本文总结了良性和恶性乳腺肿瘤在超声图像上的特点，将乳腺良性肿瘤和恶性肿瘤鉴别特征在形状、边缘、边界、朝向、回声特点几个方面的量化方法和量化参数进行了较为全面的梳理，并对量化特征与肿瘤良、恶性之间的关系进行了分析。     

计算机辅助系统在诊断乳腺良恶性肿瘤中的应用

目的:探讨计算机辅助诊断系统在良恶性肿瘤检测与特征提取基础上的分类对于乳腺肿瘤的诊断价值。方法:回顾性分析乳腺超声检查发现肿瘤且经过病理学证实的617例患者影像资料,采用手工提取的方式得到乳腺超声图像的感兴趣区域及病灶轮廓,再利用方向梯度直方图（HOG）、局部二值模式（LBP）和灰度共生矩阵（GLCM）3个特征进行乳腺肿瘤的良恶性病变真假阳性检测;最后用受试者操作特征曲线（ROC）分别分析每个特征对于两类病变判别的诊断性能和应用所有特征集合的分类诊断性能。结果:多特征融合方法的各项诊断效能及ROC曲线下面积（AUC）值均优于单特征LBP、HOG、GLCM（P值均<0.05）。与人工诊断相比,多特征融合的敏感性无显著差异,但特异度显著升高达98.57%（Z值=2.25, P<0.05）,同时AUC值为0.985,显著优于人工诊断的0.910（Z值=1.99, P<0.05）。结论:计算机辅助系统乳腺超声肿瘤良恶性检测的算法是有效的,能够对乳腺癌鉴别诊断提供有益的参考。     

基于定量影像组学的乳腺肿瘤良恶性诊断

乳腺癌是女性致死率最高的恶性肿瘤之一。为提高诊断效率,提供给医生更加客观和准确的诊断结果。借助影像组学的方法,利用公开数据集BreaKHis中82例患者的乳腺肿瘤病理图像,提取乳腺肿瘤病理图像的灰度特征、Haralick纹理特征、局部二值模式(LBP)特征和Gabor特征共139维影像组学特征,并用主成分分析(PCA)对影像组学特征进行降维,然后利用随机森林(RF)、极限学习机(ELM)、支持向量机(SVM)、k最近邻(kNN)等4种不同的分类器构建乳腺肿瘤良恶性的诊断模型,并对上述不同的特征集进行评估。结果表明,基于支持向量机的影像组学特征的分类效果最好,准确率能达到88.2%,灵敏性达到86.62%,特异性达到89.82%。影像组学方法可为乳腺肿瘤良恶性预测提供一种新型的检测手段,使乳腺肿瘤良恶性临床诊断的准确率得到很大提升。     

Level Set Contouring for Breast Tumor in Sonography

The echogenicity, echotexture, shape, and contour of a lesion are revealed to be effective sonographic features for physicians to identify a tumor as either benign or malignant. Automatic contouring for breast tumors in sonography may assist physicians without relevant experience, in making correct diagnoses. This study develops an efficient method for automatically detecting contours of breast tumors in sonography. First, a sophisticated preprocessing filter reduces the noise, but preserves the shape and contrast of the breast tumor. An adaptive initial contouring method is then performed to obtain an approximate circular contour of the tumor. Finally, the deformation-based level set segmentation automatically extracts the precise contours of breast tumors from ultrasound (US) images. The proposed contouring method evaluates US images from 118 patients with breast tumors. The contouring results, obtained with computer simulation, reveal that the proposed method always identifies similar contours to those obtained with manual sketching. The proposed method provides robust and fast automatic contouring for breast US images. The potential role of this approach might save much of the time required to sketch a precise contour with very high stability.     

Advanced image fusion algorithms for Gamma Knife treatment planning. Evaluation and proposal for clinical use.

Image fusion is a process of combining information from multiple sensors. It is a useful tool implemented in the treatment planning programme of Gamma Knife Radiosurgery. In this paper we evaluate advanced image fusion algorithms for Matlab platform and head images. We develop nine level grayscale image fusion methods: average, principal component analysis (PCA), discrete wavelet transform (DWT) and Laplacian, filter - subtract - decimate (FSD), contrast, gradient, morphological pyramid and a shift invariant discrete wavelet transform (SIDWT) method in Matlab platform. We test these methods qualitatively and quantitatively. The quantitative criteria we use are the Root Mean Square Error (RMSE), the Mutual Information (MI), the Standard Deviation (STD), the Entropy (H), the Difference Entropy (DH) and the Cross Entropy (CEN). The qualitative are: natural appearance, brilliance contrast, presence of complementary features and enhancement of common features. Finally we make clinically useful suggestions.     

Diagnosis of Solid Breast Tumors Using Vessel Analysis in Three-Dimensional Power Doppler Ultrasound Images

This study aims to evaluate whether the distribution of vessels inside and adjacent to tumor region at three-dimensional (3-D) power Doppler ultrasonography (US) can be used for the differentiation of benign and malignant breast tumors. 3-D power Doppler US images of 113 solid breast masses (60 benign and 53 malignant) were used in this study. Blood vessels within and adjacent to tumor were estimated individually in 3-D power Doppler US images for differential diagnosis. Six features including volume of vessels, vascularity index, volume of tumor, vascularity index in tumor, vascularity index in normal tissue, and vascularity index in surrounding region of tumor within 2 cm were evaluated. Neural network was then used to classify tumors by using these vascular features. The receiver operating characteristic (ROC) curve analysis and Student’s t test were used to estimate the performance. All the six proposed vascular features are statistically significant (p < 0.001) for classifying the breast tumors as benign or malignant. The A_Z (area under ROC curve) values for the classification result were 0.9138. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the diagnosis performance based on all six proposed features were 82.30 (93/113), 86.79 (46/53), 78.33 (47/60), 77.97 (46/59), and 87.04 % (47/54), respectively. The p value of A_Z values between the proposed method and conventional vascularity index method using z test was 0.04.     

基于边界特征的乳腺肿瘤超声图像识别

通过对乳腺肿瘤边界特征的分析，得到边界的特征量似圆度，面积比率，长宽比组成的特征矢量，最后用反向传播人工神经网络（BP）的算法对经病理证实的119幅乳腺良、恶性肿块超声图像进行分类识别。BP神经网络对良、恶性肿瘤正确识别率分别为89．7％、73．5N。量化后的乳腺超声图像肿瘤轮廓特征结合BP神经网络可以比较有效的用于肿瘤的良、恶性识别。     

A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation

This paper presents a method for breast cancer diagnosis in digital mammogram images. Multi-resolution representations, wavelet or curvelet, are used to transform the mammogram images into a long vector of coefficients. A matrix is constructed by putting wavelet or curvelet coefficients of each image in row vector, where the number of rows is the number of images, and the number of columns is the number of coefficients. A feature extraction method is developed based on the statistical t-test method. The method is ranking the features (columns) according to its capability to differentiate the classes. Then, a dynamic threshold is applied to optimize the number of features, which can achieve the maximum classification accuracy rate. The method depends on extracting the features that can maximize the ability to discriminate between different classes. Thus, the dimensionality of data features is reduced and the classification accuracy rate is improved. Support vector machine (SVM) is used to classify between the normal and abnormal tissues and to distinguish between benign and malignant tumors. The proposed method is validated using 5-fold cross validation. The obtained classification accuracy rates demonstrate that the proposed method could contribute to the successful detection of breast cancer.     

乳腺肿瘤超声图像中感兴趣区域的自动检测

由于斑点噪声、伪影以及病灶形状多变的影响,乳腺肿瘤超声图像中肿瘤区域的自动检测以及病灶的边缘提取比较困难,已有的方法主要是由医生先手工提取感兴趣区域(ROI)。本研究提出一种乳腺肿瘤超声图像中感兴趣区域自动检测的方法,选用超声图像的局部纹理、局部灰度共生矩阵以及位置信息作为特征,采用自组织映射神经网络进行分类,自动识别乳腺肿瘤区域。对包含168幅乳腺肿瘤超声图像的数据库进行识别的结果表明:该方法自动识别ROI的准确率达到86.9%,可辅助医生提取肿瘤的实际边缘以及进一步诊断。     

Characterization of breast tumors using machine learning based upon multiparametric magnetic resonance imaging features

Magnetic resonance imaging (MRI) is playing an important role in the classification of breast tumors. MRI can be used to obtain multiparametric (mp) information, such as structural, hemodynamic, and physiological information. Quantitative analysis of mp-MRI data has shown potential in improving the accuracy of breast tumor classification. In general, a large set of quantitative and texture features can be generated depending upon the type of methodology used. A suitable combination of selected quantitative and texture features can further improve the accuracy of tumor classification. Machine learning (ML) classifiers based upon features derived from MRI data have shown potential in tumor classification. There is a need for further research studies on selecting an appropriate combination of features and evaluating the performance of different ML classifiers for accurate classification of breast tumors. The objective of the current study was to develop and optimize an ML framework based upon mp-MRI features for the characterization of breast tumors (malignant vs. benign and low- vs. high-grade). This study included the breast mp-MRI data of 60 female patients with histopathology results. A total of 128 features were extracted from the mp-MRI tumor data followed by features selection. Five ML classifiers were evaluated for tumor classification using 10-fold crossvalidation with 10 repetitions. The support vector machine (SVM) classifier based on optimum features selected using a wrapper method with an adaptive boosting (AdaBoost) technique provided the highest sensitivity (0.96 ± 0.03), specificity (0.92 ± 0.09), and accuracy (94% ± 2.91%) in the classification of malignant versus benign tumors. This method also provided the highest sensitivity (0.94 ± 0.07), specificity (0.80 ± 0.05), and accuracy (90% ± 5.48%) in the classification of low- versus high-grade tumors. These findings suggest that the SVM classifier outperformed other ML methods in the binary classification of breast tumors.     

Acinic cell carcinoma of the breast: an immunohistochemical and ultrastructural study

The clinicopathological features of six cases of breast carcinomas showing features of acinic cell differentiation, which are similar to those seen in homologous tumors of salivary glands, are presented. The patients, all women, were 35–80 years of age. One case recurred after 4 years, and in two cases axillary lymph-node metastases were found at the time of surgery. Histologically the tumors showed a microglandular pattern merging with solid areas. Cytologically, immunohistochemically, and ultrastructurally the tumors were very similar to cases of acinic cell carcinoma of the parotid gland.The differential diagnostic criteria with microglandular adenosis and carcinomas showing granular cytoplasm are discussed. It seems that acinic cell carcinomas of the breast have to be added to the long list of tumors that affect the salivary glands and can also arise in the breast. Received: 19 November 1999 / Accepted: 7 February 2000     

Breast Ultrasound Image Classification Based on Multiple-Instance Learning

Breast ultrasound (BUS) image segmentation is a very difficult task due to poor image quality and speckle noise. In this paper, local features extracted from roughly segmented regions of interest (ROIs) are used to describe breast tumors. The roughly segmented ROI is viewed as a bag. And subregions of the ROI are considered as the instances of the bag. Multiple-instance learning (MIL) method is more suitable for classifying breast tumors using BUS images. However, due to the complexity of BUS images, traditional MIL method is not applicable. In this paper, a novel MIL method is proposed for solving such task. First, a self-organizing map is used to map the instance space to the concept space. Then, we use the distribution of the instances of each bag in the concept space to construct the bag feature vector. Finally, a support vector machine is employed for classifying the tumors. The experimental results show that the proposed method can achieve better performance: the accuracy is 0.9107 and the area under receiver operator characteristic curve is 0.96 (p < 0.005).     

Estrogen receptor-negative breast carcinomas: a review of morphology and immunophenotypical analysis.

Estrogen receptor (ER)-negative breast cancers are a group of tumors with poor prognosis and fewer cancer prevention and treatment strategies compared to ER-positive tumors. The aim of this study was to assess the morphological characteristics and immunohistochemical profile of ER-negative tumors and thus to understand the biological behavior and unique nature. In total, 291 consecutive ER-negative cases available from our primary breast cancer series were examined. Hematoxylin- and eosin-stained sections of all the cases were studied for several morphological parameters and their immunophenotype profile. These findings were correlated with patient and tumor characteristics and survival data. ER-negative tumors constituted 30% of the primary operable breast cancer series. The majority of tumors were grade 3 (94%) and the commonest histological types were ductal/no specific type (85%), and atypical medullary carcinoma (8%). High-grade comedo-type necrosis, lymphoid stroma, central necrosis/fibrosis and pushing margins were the most common morphological features. The presence of a pushing margin showed a significant relation to androgen receptor negativity, absence of epidermal growth factor receptor expression and negative lymph nodes. Lymphoid stroma and comedo-necrosis correlated with higher tumor grade. ER-negative breast cancers are a distinct group of tumors with several common morphological features. Grade 3 histology, pushing margin, lymphoid stroma, comedo-type necrosis and central fibrosis/necrosis are the dominant morphological findings. The presence of a pushing margin appears to have a significant correlation with negative lymph node status. ER-negative tumors show a higher expression of p53, CerbB2 and epidermal growth factor receptor compared to ER-positive breast cancer. These unique features support the concept that ER-negative tumors are a morphologically and phenotypically distinct entity and provide a rationale for the study and use of newer promising agents in the treatment of ER-negative breast cancer.     

Sclerosing mucoepidermoid carcinoma with eosinophilia of the thyroid: Case report of a rare lesion with novel genetic mutation

Sclerosing mucoepidermoid carcinoma with eosinophilia (SMECE) is a rare primary cancer of the thyroid. This tumor is analogous to other primary tumors of the salivary glands, breast, pancreas, and esophagus. We present a case of this rare tumor with characteristic clinical features, ultrasound images, cytopathology, histopathology, and a heretofore undocumented somatic gene mutation. Additionally, we provide a succinct review of the controversial literature for this uncommon lesion.     

Breast tumors with a solid and uniform carcinoid pattern. Ultrastructural and immunohistochemical study of two cases

Two cases of breast tumors with a uniform solid carcinoid pattern and argyrophilic dense-core granules were analyzed by immunohistochemistry in order to compare their characteristics with known features of other carcinoid tumors and ordinary breast carcinomas. The tumors were positive for keratin-type intermediate filaments, neuron-specific enolase and alpha-chain of human chorion gonadotropin but negative for vimentin and S-100 protein. Laminin was found only in a rim between tumor cell islands and stroma but not among the cells. It is concluded that these tumors are histologically, ultrastructurally and immunohistochemically similar to other carcinoid tumors. The present results suggest that both breast carcinoids and carcinomas may have a common precursor in the mammary secretory unit.     

Computerized Determination Scheme for Histological Classification of Breast Mass Using Objective Features Corresponding to Clinicians’ Subjective Impressions on Ultrasonographic Images

It is often difficult for clinicians to decide correctly on either biopsy or follow-up for breast lesions with masses on ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of breast mass by using objective features corresponding to clinicians’ subjective impressions for image features on ultrasonographic images. Our database consisted of 363 breast ultrasonographic images obtained from 363 patients. It included 150 malignant (103 invasive and 47 noninvasive carcinomas) and 213 benign masses (87 cysts and 126 fibroadenomas). We divided our database into 65 images (28 malignant and 37 benign masses) for training set and 298 images (122 malignant and 176 benign masses) for test set. An observer study was first conducted to obtain clinicians’ subjective impression for nine image features on mass. In the proposed method, location and area of the mass were determined by an experienced clinician. We defined some feature extraction methods for each of nine image features. For each image feature, we selected the feature extraction method with the highest correlation coefficient between the objective features and the average clinicians’ subjective impressions. We employed multiple discriminant analysis with the nine objective features for determining histological classification of mass. The classification accuracies of the proposed method were 88.4 % (76/86) for invasive carcinomas, 80.6 % (29/36) for noninvasive carcinomas, 86.0 % (92/107) for fibroadenomas, and 84.1 % (58/69) for cysts, respectively. The proposed method would be useful in the differential diagnosis of breast masses on ultrasonographic images as diagnosis aid.     

Granular cell tumors of the breast. Steroid receptor analysis and localization of carcinoembryonic antigen, myoglobin, and S100 protein

Granular cell tumors occur in a variety of sites, including the breast (6%). Origins from histiocytic, myogenic, fibroblastic, and neurogenic elements have been proposed. Female predominance suggests that estrogenic hormones are involved. Four granular cell tumors of the breast and one in an axillary lymph node were studied for sex steroid receptor content, myoglobin, carcinoembryonic antigen, and S100 protein localization. Antimyoglobin antibody did not localize in these tumors. Carcinoembryonic antigen and S100 protein localized in the cytoplasm of these tumors. Neither estrogen nor progesterone receptor protein were present in these tumors in detectable amounts. Ultrastructural features of these granular cell tumors in the breast are similar to those described for extramammary granular cell tumors. These studies agree with previous data that suggest a neurogenic origin for granular cell tumors.     

Classification of breast masses in mammograms using genetic programming and feature selection

Mammography is a widely used screening tool and is the gold standard for the early detection of breast cancer. The classification of breast masses into the benign and malignant categories is an important problem in the area of computer-aided diagnosis of breast cancer. A small dataset of 57 breast mass images, each with 22 features computed, was used in this investigation; the same dataset has been previously used in other studies. The extracted features relate to edge-sharpness, shape, and texture. The novelty of this paper is the adaptation and application of the classification technique called genetic programming (GP), which possesses feature selection implicitly. To refine the pool of features available to the GP classifier, we used feature-selection methods, including the introduction of three statistical measures—Student’s t test, Kolmogorov–Smirnov test, and Kullback–Leibler divergence. Both the training and test accuracies obtained were high: above 99.5% for training and typically above 98% for test experiments. A leave-one-out experiment showed 97.3% success in the classification of benign masses and 95.0% success in the classification of malignant tumors. A shape feature known as fractional concavity was found to be the most important among those tested, since it was automatically selected by the GP classifier in almost every experiment.     

Clinical trial of time-resolved scanning optical mammography at 4 wavelengths between 683 and 975 nm

The first time-resolved optical mammograph operating beyond 900 nm (683, 785, 913, and 975 nm) is presently being used in a clinical trial to test the diagnostic potential of the technique in detecting and characterizing breast lesions. Between November 2001 and October 2002, 101 patients with malignant and benign lesions were analyzed retrospectively. Scattering plots, as derived from a homogeneous model, and late gated intensity images, to monitor spatial changes in the absorption properties, are routinely used. The intensity images available at four wavelengths provide sensitivity to the main tissue constituents (oxy- and deoxyhemoglobin, water, and lipids), in agreement with expected tissue composition and physiology, while the scattering plots mirror structural changes. Briefly, tumors are usually identified due to the strong blood absorption at short wavelengths, cysts to the low scattering, and fibroadenomas to low absorption at 913 nm and high at 975 nm, even though the optical features of fibroadenomas seem not to be uniquely defined. The effectiveness of the technique in localizing and discriminating different lesion types is analyzed as a function of various parameters (lesion size, compressed breast thickness, and breast parenchymal pattern). .     

"Missed" diagnoses of phyllodes tumor on breast biopsy: pathologic clues to its recognition

Fibroadenoma and phyllodes tumors of the breast exhibit a continuum of pathologic features. We examined phyllodes tumors initially called fibroadenoma for features that may accurately classify the tumor as phyllodes tumor on the first biopsy specimen. The phyllodes tumors initially called fibroadenoma for features that may accurately classify the tumor as phyllodes tumors on the first biopsy specimen are examined. Fifteen patients with phyllodes tumors were studied, initially called FA or another term short of PT. These tumors were compared with 16 true fibroadenomas, all with needle-core biopsy followed by excision. Resected phyllodes tumors were larger on average than fibroadenoma, 6.8 cm (range = 1.7-16.2 cm) versus 2.6 cm (range = 1.0-4.8 cm). In needle-core biopsy cases, sampling was limited, even in large breast masses. p53 and cleaved caspase-3 were noncontributory. Ki-67 showed higher proliferation indices in phyllodes tumors versus fibroadenoma (4.8% vs 0.6%). Features suggesting phyllodes tumors include tissue fragmentation, increased stromal cellularity especially around glands, stromal overgrowth, and increased mitoses. Increased sampling of a large tumor will likely yield more correct diagnoses.