Computerized characterization of breast masses on three-dimensional ultrasound volumes

We are developing computer vision techniques for the characterization of breast masses as malignant or benign on radiologic examinations. In this study, we investigated the computerized characterization of breast masses on three-dimensional (3-D) ultrasound (US) volumetric images. We developed 2-D and 3-D active contour models for automated segmentation of the mass volumes. The effect of the initialization method of the active contour on the robustness of the iterative segmentation method was studied by varying the contour used for its initialization. For a given segmentation, texture and morphological features were automatically extracted from the segmented masses and their margins. Stepwise discriminant analysis with the leave-one-out method was used to select effective features for the classification task and to combine these features into a malignancy score. The classification accuracy was evaluated using the area Az under the receiver operating characteristic (ROC) curve, as well as the partial area index Az(0.9), defined as the relative area under the ROC curve above a sensitivity threshold of 0.9. For the purpose of comparison with the computer classifier, four experienced breast radiologists provided malignancy ratings for the 3-D US masses. Our dataset consisted of 3-D US volumes of 102 biopsied masses (46 benign, 56 malignant). The classifiers based on 2-D and 3-D segmentation methods achieved test Az values of 0.87+/-0.03 and 0.92+/-0.03, respectively. The difference in the Az values of the two computer classifiers did not achieve statistical significance. The Az values of the four radiologists ranged between 0.84 and 0.92. The difference between the computer's Az value and that of any of the four radiologists did not achieve statistical significance either. However, the computer's Az(0.9) value was significantly higher than that of three of the four radiologists. Our results indicate that an automated and effective computer classifier can be designed for differentiating malignant and benign breast masses on 3-D US volumes. The accuracy of the classifier designed in this study was similar to that of experienced breast radiologists.     

Computerized-aid diagnosis of breast mass using ultrasound image

This paper presents a comparative study of the diagnostic results of the ultrasologists with/without using a novel enhancement algorithm for breast ultrasonic images based on fuzzy entropy principle and textural information. Totally, 350 ultrasound images of 115 cases were analyzed including 59 benign and 56 malignant lesions. The original breast images were fuzzified, the edge and textural information were extracted, and the images were enhanced. The original and enhanced images were assessed and evaluated by ultrasologists using double blind method before and after enhancement. The diagnostic sensitivity and specificity were calculated by the areas (Az) under the receiver operating characteristic (ROC) curves. And the two diagnostic results before and after enhancement were compared by Chi-square test in a 2 x 2 table. The results demonstrated that the discrimination rate of breast masses had been highly improved after employing the novel enhancement algorithm. The result indicates the sensitivity could be raised from 74.3% to 89.3% with the false-positive rate 14.3%, and the area (Az) under the ROC curve of diagnosis also increased from 0.84 to 0.93. The novel enhancement algorithm can increase the classification accuracy and decrease the rate of missing and misdiagnosis, and it is useful for breast cancer control.     

Computer-aided diagnosis of cervical lymph nodes on ultrasonography

A computerized system differentiating cervical lymph nodes on ultrasonography as malignant or benign was developed from a database of 210 cases. Ten quantitative features representing sonographic features of size, margin, nodal border, shape, medulla ratio, medulla distribution, echogenicity, echogeneity, vascular density, and vascular pattern, were respectively calculated under the node contour segmented by an improved snake model. A rough margin based support vector machine was trained to distinguish between malignant and benign nodes using the 10 computerized features. The receiver operating characteristic (ROC) analysis was used to evaluate the performance. The developed system showed the normalized area under the ROC curve (Az, which is used as a summarized measure of the accuracy, ranges from 0.5 to 1.0) of 0.892. Compared with the radiologist's performance of Az of 0.784 this system has the potential to be an aid to radiologists in the task of distinguishing between malignant and benign cervical nodes on ultrasonography.     

Differentiation of thyroid nodules using Tl-201 scintigraphy quantitative analysis and fine-needle aspiration biopsy

We studied the differentiation of thyroid nodules using fine-needle aspiration biopsy (FNA) and Tl-201 scintigraphy quantitative analysis. One-hundred and thirty-one thyroid nodules were examined: 83 follicular lesions (58 benign and 25 malignant lesions) and 48 non-follicular lesions (8 benign and 40 malignant lesions). During Tl-201 scintigraphy examinations, an early and a delayed image were acquired 10 and 120 min after an intravenous injection, respectively. The T/N ratio (counts of nodular lesion/counts of contralateral normal thyroid tissue) of each image was calculated quantitatively. We assessed the ability of the Tl-201 scintigraphy and of the FNA analysis to differentiate benign and malignant lesions and determined the cut-off levels for the assays. For the follicular lesions, the area under the ROC (Receiver Operating Characteristic) curve (Az) for the Tl-201 scintigraphy data was greater than that for the FNA data. For the non-follicular lesions, the Az for the FNA data was greater than that for the Tl-201 scintigraphy data. We set cut-off levels at 1.370 for follicular lesions, and 1.070 for non-follicular lesions. The sensitivity and specificity were 76% and 82.7% for follicular lesions, and 90% and 87.5% for non-follicular lesions, respectively. The overall accuracy of the analysis was 84.0%.     

A large-scale study of the ultrawideband microwave dielectric properties of normal, benign and malignant breast tissues obtained from cancer surgeries

The development of microwave breast cancer detection and treatment techniques has been driven by reports of substantial contrast in the dielectric properties of malignant and normal breast tissues. However, definitive knowledge of the dielectric properties of normal and diseased breast tissues at microwave frequencies has been limited by gaps and discrepancies across previously published studies. To address these issues, we conducted a large-scale study to experimentally determine the ultrawideband microwave dielectric properties of a variety of normal, malignant and benign breast tissues, measured from 0.5 to 20 GHz using a precision open-ended coaxial probe. Previously, we reported the dielectric properties of normal breast tissue samples obtained from reduction surgeries. Here, we report the dielectric properties of normal (adipose, glandular and fibroconnective), malignant (invasive and non-invasive ductal and lobular carcinomas) and benign (fibroadenomas and cysts) breast tissue samples obtained from cancer surgeries. We fit a one-pole Cole-Cole model to the complex permittivity data set of each characterized sample. Our analyses show that the contrast in the microwave-frequency dielectric properties between malignant and normal adipose-dominated tissues in the breast is considerable, as large as 10:1, while the contrast in the microwave-frequency dielectric properties between malignant and normal glandular/fibroconnective tissues in the breast is no more than about 10%.     

Computerized scheme for determination of the likelihood measure of malignancy for pulmonary nodules on low-dose CT images

An automated computerized scheme has been developed for determination of the likelihood measure of malignancy of pulmonary nodules on low-dose helical CT (LDCT) images. Our database consisted of 76 primary lung cancers (147 slices) and 413 benign nodules (576 slices). With this automated computerized scheme, the location of a nodule was first indicated by a radiologist. The outline of the nodule was segmented automatically by use of a dynamic programming technique. Various objective features on the nodules were determined by use of outline analysis and image analysis, and the likelihood measure of malignancy was determined by use of linear discriminant analysis (LDA). The effect of many different combinations of features and the performance of LDA in distinguishing benign nodules from malignant ones were evaluated by means of receiver operating characteristic (ROC) analysis. The Az value (area under the ROC curve) obtained by the computerized scheme in distinguishing benign nodules from malignant ones was 0.828 when a single slice was employed for each of the nodules. However, the Az value was improved to 0.846 when multiple slices were used for determination of the likelihood measure of malignancy. The Az values obtained by the computerized scheme on LDCT images were significantly greater than the Az value of 0.70, which was obtained from our previous observer studies by radiologists in distinguishing benign nodules from malignant ones on LDCT images. The automated computerized scheme for determination of the likelihood measure of malignancy would be useful in assisting radiologists to distinguish between benign and malignant pulmonary nodules on LDCT images.     

Projection profile analysis for automated detection of abnormalities in chest radiographs

Abnormalities in chest images often present as abnormal opacity or abnormal asymmetry. We have developed a novel method for automated detection of abnormalities in chest radiographs by use of these features. Our method is based on an analysis of the projection profile obtained by projecting the pixels data of a frontal chest image on to the mediolateral axis. Two indices, lung opacity index and lung symmetry index, are computed from the projection profile. Lung opacity index and lung symmetry index are then combined to detect gross abnormalities in chest radiographs. The values of lung opacity index are found to be 0.38 +/- 0.05 and 0.37 +/- 0.06 for normal right and left lung, respectively. The values of lung symmetry index are found to be 0.018 +/- 0.014 for normal chest images. The discrimination for the combination of the two indices is evaluated by linear discriminant analysis and receiver operating characteristic (ROC) analysis. Area Az under the ROC curve with the combination of the two indices in the classification of normal and abnormal chest images is 0.963.     

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.     

Boundary modelling and shape analysis methods for classification of mammographic masses

The problem of computer-aided classification of benign and malignant breast masses using shape features is addressed. The aim of the study is to look at the exceptions in shapes of masses such as circumscribed malignant tumours and spiculated benign masses which are difficult to classify correctly using common shape analysis methods. The proposed methods of shape analysis treat the object's boundary in terms of local details. The boundaries of masses analysed using the proposed methods were manually drawn on mammographic images by an expert radiologist (JELD). A boundary segmentation method is used to separate major portions of the boundary and to label them as concave or convex segments. To analyse the shape information localised in each segment, features are computed through an iterative procedure for polygonal modelling of the mass boundaries. Features are based on the concavity fraction of a mass boundary and the degree of narrowness of spicules as characterised by a spiculation index. Two features comprising spiculation index (SI) and fractional concavity (f_cc) developed in the present study when used in combination with the global shape feature of compactness resulted in a benign/malignant classification accuracy of 82%, with an area (A_z) of 0.79 under the receiver operating characteristics (ROC) curve with a database of the boundaries of 28 benign masses and 26 malignant tumours. SI alone resulted in a classification accuracy of 80% with A_z of 0.82. The combination of all the three features achieved 91% accuracy of circumscribed versus spiculated classification of masses based on shape.     

Classification of breast masses in ultrasonic B scans using Nakagami and K distributions

Classification of breast masses in greyscale ultrasound images is undertaken using a multiparameter approach. Five parameters reflecting the non-Rayleigh nature of the backscattered echo were used. These parameters, based mostly on the Nakagami and K distributions, were extracted from the envelope of the echoes at the site, boundary, spiculated region and shadow of the mass. They were combined to create a linear discriminant. The performance of this discriminant for the classification of breast masses was studied using a data set consisting of 70 benign and 29 malignant cases. The Az value for the discriminant was 0.96 +/- 0.02, showing great promise in the classification of masses into benign and malignant ones. The discriminant was combined with the level of suspicion values of the radiologist leading to an Az value of 0.97 +/- 0.014. The parameters used here can be calculated with minimal clinical intervention, so the method proposed here may therefore be easily implemented in an automated fashion. These results also support the recent reports suggesting that ultrasound may help as an adjunct to mammography in breast cancer diagnostics to enhance the classification of breast masses.     

Mammaglobin expression in gynecologic malignancies and malignant effusions detected by nested reverse transcriptase-polymerase chain reaction

The detection of micrometastatic disease remains a challenge for the diagnosis and monitoring of malignant disease. RT-PCR for human mammaglobin (hMAM) was recently shown to provide a sensitive method for assessing circulating breast cancer cells in peripheral blood. This study was aimed at investigating hMAM expression in normal and malignant tissue from the female genital tract and the prostate as well as in malignant effusions derived from gynecologic malignancies. hMAM expression was analyzed with nested RT-PCR in 152 samples of normal (n = 73) and malignant epithelial tissues (n = 79) and in 33 specimens of various normal mesenchymal tissue types. We found hMAM expression was not restricted to the normal mammary gland and breast carcinoma but was also detectable in most specimens of benign and malignant epithelial tissue from the ovary (97% versus 95%), uterus (both 100%), and cervix (91% versus 90%). Notably, hMAM expression was also found in benign prostatic hyperplasia (45%) and in prostate cancer (55%). A much lower expression rate was found in various normal and benign mesenchymal tissues (12%). In keeping with our previous data, hMAM expression was absent in all control samples (n = 124) of peripheral blood and bone marrow from healthy volunteers and patients with hematologic malignancies. In pleural or peritoneal effusions (n = 42) from patients with carcinomas of the breast, endometrium, or ovary, hMAM positivity was noticed in the majority of cases (74%), whereas only 52% of the specimens were cytologically positive for tumor cells. In conclusion, hMAM expression assessed by nested RT-PCR is a sensitive molecular marker for detecting micrometastatic tumor spread into pleural effusions and ascites from patients with breast cancer and various other gynecologic neoplasms.     

压迫式弹性成像与声脉冲辐射力成像技术在乳腺肿瘤良恶性鉴别中的价值比较

目的:探讨分析压迫式弹性成像（CE）与声脉冲辐射力成像（ARFI）技术在乳腺肿瘤良恶性鉴别中的价值。方法:选择门诊或住院行超声检查发现的有乳腺肿块患者71例共89个病灶,经病理组织学确认良性病灶57个,恶性病灶32个。对各病灶进行彩色多普勒超声检查,并采取CE及ARFI技术,分别计算病灶弹性应变率比值（SR）及声触诊组织定量（VTQ）值,采用ROC曲线分析SR、VTQ对良恶性肿瘤的诊断效能。结果:恶性组病灶VTQ值与SR值均显著高于良性组（P<0.05）。采用ROC曲线分析VTQ、SR对乳腺良恶性肿瘤诊断效能,VTQ诊断曲线下面积（AUC）为0.918,95% CI为0.871~0.980（P<0.05）,最佳截断值为3.97,在此最佳截断值下,VTQ诊断敏感性94.64%、诊断特异性90.63%;SR诊断AUC为0.899,95% CI为0.854~0.956（P<0.05）,最佳截断值为4.12,在此最佳截断值下,SR诊断敏感性92.86%、诊断特异性84.38%。VTQ和SR诊断敏感性、特异性比较差异无统计学意义（P>0.05）。结论:两种超声诊断技术对乳腺良恶性肿瘤均具有较高的诊断价值,其诊断效能相似,临床上可联合使用,以实现优势互补,提高对乳腺癌的早期检出率。     

Semi-Automatic Region-of-Interest Segmentation Based Computer-Aided Diagnosis of Mass Lesions from Dynamic Contrast-Enhanced Magnetic Resonance Imaging Based Breast Cancer Screening

Cancer screening with magnetic resonance imaging (MRI) is currently recommended for very high risk women. The high variability in the diagnostic accuracy of radiologists analyzing screening MRI examinations of the breast is due, at least in part, to the large amounts of data acquired. This has motivated substantial research towards the development of computer-aided diagnosis (CAD) systems for breast MRI which can assist in the diagnostic process by acting as a second reader of the examinations. This retrospective study was performed on 184 benign and 49 malignant lesions detected in a prospective MRI screening study of high risk women at Sunnybrook Health Sciences Centre. A method for performing semi-automatic lesion segmentation based on a supervised learning formulation was compared with the enhancement threshold based segmentation method in the context of a computer-aided diagnostic system. The results demonstrate that the proposed method can assist in providing increased separation between malignant and radiologically suspicious benign lesions. Separation between malignant and benign lesions based on margin measures improved from a receiver operating characteristic (ROC) curve area of 0.63 to 0.73 when the proposed segmentation method was compared with the enhancement threshold, representing a statistically significant improvement. Separation between malignant and benign lesions based on dynamic measures improved from a ROC curve area of 0.75 to 0.79 when the proposed segmentation method was compared to the enhancement threshold, also representing a statistically significant improvement. The proposed method has potential as a component of a computer-aided diagnostic system.     

A neural network to predict symptomatic lung injury.

A nonlinear neural network that simultaneously uses pre-radiotherapy (RT) biological and physical data was developed to predict symptomatic lung injury. The input data were pre-RT pulmonary function, three-dimensional treatment plan doses and demographics. The output was a single value between 0 (asymptomatic) and 1 (symptomatic) to predict the likelihood that a particular patient would become symptomatic. The network was trained on data from 97 patients for 400 iterations with the goal to minimize the mean-squared error. Statistical analysis was performed on the resulting network to determine the model's accuracy. Results from the neural network were compared with those given by traditional linear discriminate analysis and the dose-volume histogram reduction (DVHR) scheme of Kutcher. Receiver-operator characteristic (ROC) analysis was performed on the resulting network which had Az = 0.833 +/- 0.04. (Az is the area under the ROC curve.) Linear discriminate multivariate analysis yielded an Az = 0.813 +/- 0.06. The DVHR method had Az = 0.521 +/- 0.08. The network was also used to rank the significance of the input variables. Future studies will be conducted to improve network accuracy and to include functional imaging data.     

Diagnostic performance of contrast-enhanced ultrasound and enhanced magnetic resonance for breast nodules

In the current study, we sought to evaluate the diagnostic efficacies of conventional ultrasound (US), contrastenhanced US (CEUS), combined US and CEUS and magnetic resonance imaging (MRI) in detecting focal solid breast lesions. Totally 117 patients with 120 BI-RADS category 4A-5 breast lesions were evaluated by conventional US and CEUS, and MRI, respectively. SonoVue was used as contrast agent in CEUS and injected as an intravenous bolus; nodule scan was performed 4 minutes after bolus injection. A specific sonographic quantification software was used to obtain color-coded maps of perfusion parameters for the investigated lesion, namely the time-intensity curve. The pattern of contrast enhancement and related indexes regarding the time-intensity curve were used to describe the lesions, comparatively with pathological results. Histopathologic examination revealed 46 benign and 74 malignant lesions. Sensitivity, specificity, and accuracy of US in detecting malignant breast lesions were 90.14%, 95.92%, and 92.52%, respectively. Meanwhile, CE-MRI showed sensitivity, specificity, and accuracy of 88.73%, 95.92%, and 91.67%, respectively. The area under the ROC curve for combined US and CEUS in discriminating benign from malignant breast lesions was 0.936, while that of MRI was 0.923, with no significant difference between them, as well as among groups. The time-intensity curve of malignant hypervascular fibroadenoma and papillary lesions mostly showed a fast-in/fast-out pattern, with no good correlation between them (kappa < 0.20). In conclusion, the combined use of conventional US and CEUS displays good agreement with MRI in differentiating benign from malignant breast lesions.     

Expression of ATM, p53, and the MRE11-Rad50-NBS1 complex in myoepithelial cells from benign and malignant proliferations of the breast

AIMS: To analyse the expression of proteins involved in DNA double strand break detection and repair in the luminal and myoepithelial compartments of benign breast lesions and malignant breast tumours with myoepithelial differentiation. METHODS: Expression of the ataxia telangiectasia (ATM) and p53 proteins was immunohistochemically evaluated in 18 benign and malignant myoepithelial tumours of the breast. Fifteen benign breast lesions with prominent myoepithelial compartment were also evaluated for these proteins, in addition to those in the MRE11-Rad50-NBS1 (MRN) complex, and the expression profiles were compared with those seen in eight independent non-cancer (normal breast) samples and in the surrounding normal tissues of the benign and malignant tumours examined. RESULTS: ATM expression was higher in the myoepithelial compartment of three of 15 benign breast lesions and lower in the luminal compartment of eight of these lesions compared with that found in the corresponding normal tissue compartments. Malignant myoepithelial tumours overexpressed ATM in one of 18 cases. p53 was consistently negative in benign lesions and was overexpressed in eight of 18 malignant tumours. In benign breast lesions, expression of the MRN complex was significantly more reduced in myoepithelial cells (up to 73%) than in luminal cells (up to 40%) (p=0.0005). CONCLUSIONS: Malignant myoepithelial tumours rarely overexpress ATM but are frequently positive for p53. In benign breast lesions, expression of the MRN complex was more frequently reduced in the myoepithelial than in the luminal epithelial compartment, suggesting different DNA repair capabilities in these two cell types.     

Loss of heterozygosity in normal breast epithelial tissue and benign breast lesions in BRCA1/2 carriers with breast cancer

Loss of heterozygosity (LOH) of the wild-type BRCA1/2 allele is a reproducible event in breast tumors of BRCA1/2 mutation carriers, but it is unknown if this allelic loss occurs only in association with recognizable histopathologic abnormalities. We evaluated the early genomic changes that occur in the mammary glands of patients with increased predisposition to breast cancer due to germline mutations in the BRCA1/2 genes. We tested the hypothesis that these genomic changes may be detected, not only in histologically abnormal and malignant breast tissues, but also in morphologically normal tissues and in areas with pathologically benign changes. Samples were obtained from five breast cancer patients: four BRCA1 carriers and one BRCA2 carrier. In each case, nontumor tissue areas surrounding the tumor or from other locations of the breast were isolated using laser capture microdissection. We evaluated 29 areas showing normal terminal ductal lobular units (TDLUs) or histopathologically benign changes (in particular, sclerosing adenosis), using a panel of polymorphic dinucleotide microsatellite markers for the BRCA1 gene and other chromosome 17 loci, for the BRCA2 gene and other chromosome 13 loci, and for the FHIT gene on 3p14.2. Overall, we analyzed a total of 105 samples of nontumor tissues; LOH was detected in 59 of the 105 (56%). In the normal TDLUs, 15 of 30 samples (50%) showed LOH; in the tissues with benign proliferative changes, such as sclerosing adenosis, 44 of 75 samples showed LOH (59%). Our results suggest that there is a field effect of early genetic events preceding morphologic changes in the mammary glands of BRCA mutation carriers.