Posterior Features Research Articles

Metastases to the Breast from Extramammary Nonhematological Malignancies: Case Series.

ObjectiveThis article aims to provide a better understanding of ultrasonography and immunohistochemistry of secondary nonhematological tumors of breast.MethodsThe study reviewed the ultrasound findings and immunohistochemical features of nonhematological metastatic breast tumor cases found in patients of West China Hospital, Sichuan University from 2007 to 2019. Each case was categorized as secondary breast malignancy using histopathological results.ResultsFourteen cases were identified from West China Hospital database. Ten cases originated in the lung, 2 cases in the stomach, 1 case in the ovary and 1 case of neuroendocrine carcinomas. Fourteen masses were evaluated. Ultrasound findings showed that tumors were hypoechoic (14/14), irregular (13/14), indistinct margin (13/14), along a long axis parallel to the skin (11/14), lacked vascularity via color doppler flow imaging (9/14). Eight cases showed no posterior features. Calcification was found in 1 case of lung adenocarcinoma that had metastasized to the breast. Abnormal axillary lymph nodes were detected in 5 cases. Immunohistochemical analysis showed that estrogen receptor (ER) and progesterone receptor (PR) were both negative in 11 cases, including gastric and lung cancer metastasis. One case of ovarian metastasis was positive for ER and negative for PR. Six patients were positive for cytokeratin 7 (CK7) and negative for cytokeratin 20 (CK20), including lung and ovarian carcinoma metastasis. Thyroid transcription factor-1 (TTF-1) was positive in 9 of 10 pulmonary carcinoma metastases. The patient of ovarian metastasis was positive for Wilms’ tumour 1 (WT-1) and carbohydrate antigen 125 (CA125). Two cases from gastric metastasis were positive for caudal-type homeobox 2 (CDX2).ConclusionAlthough breast ultrasound is not useful in distinguishing metastases from primary breast cancer, it is helpful in diagnosing breast lesions as oncological diseases and provide evidence for further examination of patients. Immunohistochemistry plays an important role in distinguishing secondary breast cancer from primary, especially in patients without tumor history.

Bayesian estimation of the biasing parameter for ridge regression: A novel approach

Multicollinearity, a common problem encountered in regression analysis, has many adverse effects on the ordinary least squares estimator. According to the literature, the ridge regression estimator is one of the useful remedies to overcome this problem. The present study is aimed to use the Bayesian approach for ridge regression and to use estimation of biasing parameters in the Bayesian paradigm by incorporating the prior information of the parameters involved. In contrary to the available Bayesian estimators, our proposed estimator permits easy computation of many posterior features of interest in regression to overcome the problem of multicollinearity. The performance of this technique has been compared with the well-known ridge regression estimators by executing an extensive simulation study. The numerical results provided an exceptional performance of the proposed technique using the mean squared error criterion. An example has been used to illustrate the proposed technique.

Thyroid imaging reporting and data system (TIRADS) for ultrasound features of nodules: multicentric retrospective study in China.

To establish a practical and simplified Chinese thyroid imaging reporting and data system (C-TIRADS) based on the Chinese patient database. A total of 2141 thyroid nodules that were neither cystic nor spongy were used in the current study. These specimens were derived from 2141 patients in 131 alliance hospitals of the Chinese Artificial Intelligence Alliance for Thyroid and Breast Ultrasound. The ultrasound features, including location, orientation, margin, halo, composition, echogenicity, echotexture, echogenic foci and posterior features were assessed. Univariate and multivariate analyses were performed to investigate the association between ultrasound features and malignancy. The regression equation, the weighting, and the counting methods were used to determine the malignant risk of the thyroid nodules. The areas under the receiver operating characteristic curve (Az values) were calculated. Of the 2141 thyroid nodules, 1572 were benign, 565 were malignant, and 4 were borderline. Vertical orientation, ill-defined, or irregular margin (including extrathyroidal extension), microcalcifications, solid, and markedly hypoechoic were positively associated with malignancy, while comet-tail artifacts were negatively associated with malignancy. The logistic regression equation yielded the highest Az value of 0.913, which was significantly higher than that obtained using the weighting method (0.893) and the counting method (0.890); however, no significant difference was found between the latter two. The C-TIRADS, based on the counting method, was designed following the principle of balancing the diagnostic performance and sensitivity of the risk stratification with the ease of use. A relatively simple C-TIRADS was established using the counting value of positive and negative ultrasound features.

The Utility of the Fifth Edition of the BI-RADS Ultrasound Lexicon in Category 4 Breast Lesions: A Prospective Multicenter Study in China

The objective of this study was to evaluate the utility of the fifth edition of the Breast Imaging-Reporting and Data System (BI-RADS) in clinical breast radiology by using prospective multicenter real-time analyses of ultrasound (US) images. We prospectively studied 2049 female patients (age range, 19-86 years; mean age 46.88 years) with BI-RADS category 4 breast masses in 32 tertiary hospitals. All the patients underwent B-mode, color Doppler US, and US elastography examination. US features of the mass and associated features were described and categorized according to the fifth edition of the BI-RADS US lexicon. The pathological results were used as the reference standard. The positive predictive values (PPVs) of subcategories 4a-4c were calculated. A total of 2094 masses were obtained, including 1124 benign masses (54.9%) and 925 malignant masses (45.1%). For BI-RADS US features of mass shape, orientation, margin, posterior features, calcifications, architectural distortion, edema, skin changes, vascularity, and elasticity assessment were significantly different for benign and malignant masses (p< 0.05). Typical signs of malignancy were irregular shape (PPV, 57.2%), spiculated margin (PPV, 83.7%), nonparallel orientation (PPV, 63.9%), and combined pattern of posterior features (PPV, 60.6%). For the changed or newly added US features, the PPVs for intraductal calcifications were 80%, 56.4% for internal vascularity, and 80% for a hard pattern on elastography. The associated features such as architectural distortion (PPV, 89.3%), edema (PPV, 69.2%), and skin changes (PPV, 76.2%) displayed high predictive value for malignancy. The rate of malignant was 7.4% (72/975) in category 4a, 61.4% (283/461) in category 4b, and 93.0% (570/613) in category 4c. The PPV for category 4b was higher than the likelihood ranges specified in BI-RADS and the PPVs for categories 4a and 4c were within the acceptable performance ranges specified in the fifth edition of BI-RADS in our study. Not only the US features of the breast mass, but also associated features, including vascularity and elasticity assessment, have become an indispensable part of the fifth edition of BI-RADS US lexicon to distinguish benign and malignant breast lesions. The subdivision of category 4 lesions into categories 4a, 4b, and 4c for US findings is helpful for further assessment of the likelihood of malignancy of breast lesions.

The Performance of Elastographic Diagnostic of Breast Tumor in Dr. Soetomo Teaching Hospital Surabaya

Background: Elastography in breast cancer cases has not become a routine examination that is conducted in the radiodiagnostic unit in Dr. Soetomo Teaching Hospital Surabaya. These last few years, elastography has been an addition examination modality which is promising to assess breast lesions that are detected byan ultrasound. Objective: The aim of the present study is to observe the performance of elastography in breast tumor cases. Method: This cross-sectional study was conducted in Dr. Soetomo Teaching Hospital Surabaya. The elastography is applied in 65 females (the average age is 49,1 years old) and it was found 66 lesions with a definitive diagnosis (34 benign tumors, 32 malignant tumors) which was proved through a fine-needle aspiration biopsy. The grayscale result is classified into benign and malignant categorizations with examining five descriptors including shape, margin, orientation, echo pattern, and posterior features. Results: The elastography score showed that the sensitivity is 87,5 %, the specificity is 94,1 %, and the accuracy is 90,9 % The stain ratio showed 93,8 %, 94,1 %, 90,9 % in sequence. On the other hand, the grayscale result showed 96,9 %, 91,2 %, and 95,5 %. The combination of elastography and grayscale showed a better performancewith the 97,1% of sensitivity, 94,1 % of specificity, and 93,8 % of accuracy. There was a significant correlation between the lesion size and the quality of elastography result (P = .034) while there was no correlation with the lesion depth (P = .624). Conslusion: The combination of elastography and grayscale have a better diagnostic performance in distinguishing benign breast tumor with malignant breast tumor.

Correlation between imaging features and molecular subtypes of breast cancer in young women (≤30years old).

To analyze the features of digital mammography (DM) plus digital breast tomosynthesis (DBT), ultrasonography (US) and magnetic resonance imaging (MRI) of breast cancer in young women (≤30years old) and the correlation with molecular subtypes. We performed a retrospective study of imaging features of consecutive young women aged ≤30years who were treated and surgically confirmed with breast cancer between January 2013 and December 2019 in our institution. All patients were Chinese women. DM + DBT and US were available for 170 lesions, MRI for 41 lesions. The imaging features were analysed by univariate and multivariate logistic regression analyses to find the predictive factors of the molecular subtypes. The predictive factors of the luminal B(HER2-) subtype (n = 51) were the mass with microcalcifications, irregular shape, spiculated margins, and shadowing posterior features (all P < 0.01). The predictive factors of the luminal B(HER2+) subtype (n = 26) were the spiculated margins (DBT + DM), angular margins (US), shadowing posterior features, and high vascularity (all P < 0.05). The predictive factors of the luminal A subtype (n = 37) were the mass without microcalcifications, spiculated margins, shadowing posterior features, and low vascularity (all P < 0.05). The predictive factors of the triple-negative subtype (n = 31) were the mass without microcalcifications, oval/round shape, circumscribed margins, enhancement of posterior features, and rim enhancement (MRI) (all P < 0.005). The predictive factors of the human-epidermal-growth-factor-receptor-2-enriched subtype (n = 26) were the only microcalcifications, microlobulated margins, and combined posterior feature (all P < 0.05). Compared with the general population of breast cancer, this young female population presents a different molecular phenotype distribution. Some imaging features of breast cancer in young women ≤30years old can be used to predict certain tumor molecular subtypes.

S-Detect characterization of focal solid breast lesions: a prospective analysis of inter-reader agreement for US BI-RADS descriptors.

To assess inter-reader agreement for US BI-RADS descriptors using S-Detect: a computer-guided decision-making software assisting in US morphologic analysis. 73 solid focal breast lesions (FBLs) (mean size: 15.9mm) in 73 consecutive women (mean age: 51years) detected at US were randomly and independently assessed according to the BI-RADS US lexicon, without and with S-Detect, by five independent reviewers. US-guided core-biopsy and 24-month follow-up were considered as standard of reference. Kappa statistics were calculated to assess inter-operator agreement, between the baseline and after S-Detect evaluation. Agreement was graded as poor (≤ 0.20), moderate (0.21-0.40), fair (0.41-0.60), good (0.61-0.80), or very good (0.81-1.00). 33/73 (45.2%) FBLs were malignant and 40/73 (54.8%) FBLs were benign. A statistically significant improvement of inter-reader agreement from fair to good with the use of S-Detect was observed for shape (from 0.421 to 0.612) and orientation (from 0.417 to 0.7) (p < 0.0001) and from moderate to fair for margin (from 0.204 to 0.482) and posterior features (from 0.286 to 0.522) (p < 0.0001). At baseline analysis isoechoic (0.0485) and heterogeneous (0.1978) echo pattern, microlobulated (0.1161) angular (0.1204) and spiculated (0.1692) margins and combined pattern (0.1549) for posterior features showed the worst agreement rate (poor). After S-Detect evaluation, all variables but isoechoic pattern showed an agreement class upgrade with a statistically significant improvement of inter-reader agreement (p < 0.0001). S-Detect significantly improved inter-reader agreement in the assessment of FBLs according to the BI-RADS US lexicon but evaluation of margin and echo pattern needs to be further improved, particularly isoechoic pattern.

A Novel Computer-Aided-Diagnosis System for Breast Ultrasound Images Based on BI-RADS Categories

The breast ultrasound is not only one of major devices for breast tissue imaging, but also one of important methods in breast tumor screening. It is non-radiative, non-invasive, harmless, simple, and low cost screening. The American College of Radiology (ACR) proposed the Breast Imaging Reporting and Data System (BI-RADS) to evaluate far more breast lesion severities compared to traditional diagnoses according to five-criterion categories of masses composition described as follows: shape, orientation, margin, echo pattern, and posterior features. However, there exist some problems, such as intensity differences and different resolutions in image acquisition among different types of ultrasound imaging modalities so that clinicians cannot always identify accurately the BI-RADS categories or disease severities. To this end, this article adopted three different brands of ultrasound scanners to fetch breast images for our experimental samples. The breast lesion was detected on the original image using preprocessing, image segmentation, etc. The breast tumor’s severity was evaluated on the features of the breast lesion via our proposed classifiers according to the BI-RADS standard rather than traditional assessment on the severity; i.e., merely using benign or malignant. In this work, we mainly focused on the BI-RADS categories 2–5 after the stage of segmentation as a result of the clinical practice. Moreover, several features related to lesion severities based on the selected BI-RADS categories were introduced into three machine learning classifiers, including a Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN) combined with feature selection to develop a multi-class assessment of breast tumor severity based on BI-RADS. Experimental results show that the proposed CAD system based on BI-RADS can obtain the identification accuracies with SVM, RF, and CNN reaching 80.00%, 77.78%, and 85.42%, respectively. We also validated the performance and adaptability of the classification using different ultrasound scanners. Results also indicate that the evaluations of F-score based on CNN can obtain measures higher than 75% (i.e., prominent adaptability) when samples were tested on various BI-RADS categories.

Evaluation of Ultrasound-guided 8-Gauge Vacuum-assisted Excision System for the Removal of US-detectable Breast Lesions.

To assess the ability of ultrasound (US)-guided vacuum-assisted breast excision (VAE) to remove Breast Imaging Reporting and Data System (BI-RADS) ≥3 breast lesions in order to analyze US features most frequently associated with complete excision. A total of 266 BI-RADS ≥3 lesions without microcalcifications underwent US-VAE. US-VAE and gold standard pathological results were compared. US features of lesions were analyzed. The complete excision rate was 93.61%; the VAE agreement rate was 99.62%. Circumscribed margins, regular shape, parallel orientation, and the absence of posterior features were favorable US features associated with complete excision. Lesions completely excised were: BI-RADS 3 ≤21.10 mm and BI-RADS 4 ≤18.70 mm with one unfavorable US characteristic, and BI-RADS 4 lesions ≤13.5 mm with two unfavorable US features hindered complete removal. Two atypical ductal hyperplasias (<10 mm, one unfavorable feature) and eight ductal carcinomas in situ (≤8.7 mm, one/two unfavorable features) were completely removed. US-VAE is highly accurate for diagnostic purpose and, in some cases, highly successful for complete lesion excision. This success also depends on the US characteristics and size of the lesion.

Ultrasound Lexicon in diagnosis and management of breast fibroadenoma: when to follow up and when to biopsy

BackgroundTo detect the accuracy of breast ultrasound in diagnosis of fibroadenoma and differentiate between typical and atypical ones. The impact of ultrasound criteria on patient management. (Biopsy versus follow up). A prospective study were done to 71 patients. Diagnosis was reached either by performing follow up study or after revision of core biopsy/surgical specimens.ResultsIn our study, we had 35 ultrasound detected atypical fibroadenoma, seven out of the 35 (20 %) proven to be complex fibroadenoma by pathology while in another 20 patients, 36 fibroadenomas with typical criteria were detected by both ultrasound and regular follow up. The most ultrasound features which showed statistical significance were the posterior shadowing feature (100% atypical versus 25% typical with significant p value < 0.01), and vessel arrangement (85.7% versus 0% have central arrangement with significant p value < 0.01) helped to differentiate between simple and complex ones. We calculate the sensitivity, specificity, PPV, and NPV to be 100%, 74%, 46%, and 100%.ConclusionArrangement of vessels and posterior features are the most important criteria to differentiate simple and complex FAD.

Neural Network Based End-to-End Query by Example Spoken Term Detection

This article focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. State-of-the-art approaches primarily rely on dynamic time warping (DTW) based template matching techniques using phone posterior or bottleneck features extracted from a deep neural network (DNN). We use both monolingual and multilingual bottleneck features, and show that multilingual features perform increasingly better with more training languages. Previously, it has been shown that the DTW based matching can be replaced with a CNN based matching while using posterior features. Here, we show that the CNN based matching outperforms DTW based matching using bottleneck features as well. In this case, the feature extraction and pattern matching stages of our QbE-STD system are optimized independently of each other. We propose to integrate these two stages in a fully neural network based end-to-end learning framework to enable joint optimization of those two stages simultaneously. The proposed approaches are evaluated on two challenging multilingual datasets: Spoken Web Search 2013 and Query by Example Search on Speech Task 2014, demonstrating in each case significant improvements.

Association between ultrasound findings, tumor type, grade, and biological markers in patients with breast cancer

BackgroundThis prospective study included 65 female patients with primary breast cancer. Ultrasound was performed for all patients. Ultrasound findings were analyzed according to the ACR BI-RADS lexicon 5th edition and correlated with tumor type, grade, and biological markers (ER, PR, HER-2/neu, and Ki67). The purpose of this study is to assess the association between ultrasound findings, tumor type, grade, and the state of biological markers in patients with breast cancer.ResultsIrregular shape and speculated margins are more frequently associated with invasive duct carcinoma than DCIS (p value < 0.001). There were no association between the ultrasound findings (shape, margin, orientation, echopattern, and posterior features) and the tumor grade (p value 1.0, 0, 0.544, 1.0, and 1.0), respectively. Irregular shape is more frequently seen in ER and PR positive breast cancers (p value = 0.036 and 0.026, respectively). Non-circumscribed margins were frequently seen in PR positive breast cancers (p value = 0.068). No statistically significant difference between US descriptors and HER-2/neu-positive cases.ConclusionIrregularly shaped tumors with speculated margins are frequently seen in invasive duct carcinoma and also more frequently seen in ER-, PR-, and Ki67-positive cases. No relation between ultrasound descriptors and the tumor grade of invasive duct carcinoma. Also, there were no relation between ultrasound descriptors and the state of HER-2/neu.

NIMG-17. CLINICOPATHOLOGIC AND ULTRASOUND VARIABLES ASSOCIATED WITH THE UNFAVORABLE PATHOLOGY IN NEUROBLASTOMA

Abstract BACKGROUND The International Neuroblastoma Pathology Classification has a prognostic impact that distinguishes two neuroblastoma categories: favorable histology (FH) and unfavorable histology (UFH). The aim of this study was to identify the clinicopathological and ultrasound variables that were associated with the UFH. METHODS With ethic approval, the clinical, pathologic, and ultrasonographic data of the 104 patients with the pathologic diagnosis of neuroblastoma were retrospectively analyzed. Pathologic findings were ascertained by the paraffin pathologic, fluorescent in situ hybridization (FISH), and the immunohistochemical stain analysis. Tumors were assessed for the following ultrasonographic characteristics: size, boundary, shape, internal echo, acoustic pattern, posterior features, calcification, internal blood flow, and pushing peripheral organs. Univariate and multivariate logistic regression analyses were used to assess the clinicopathologic and ultrasound variables that were associated with UFH. RESULTS There were 27 neuroblastoma cases (26.0%) of the UFH group. The independent clinicopathologic variables for the UFH were: older than one year (Odds ratio [OR]=32.84, p=0.003), presence of metastases (OR=4.92, p=0.032), and the MYCN amplification ratio &gt;5 (OR=47.06, p=0.003). The independent ultrasound feature of neuroblastoma which associated with UFH was the ill-defined boundary (OR=4.64, p=0.047) and tumor size ≥50mm (OR=15.77, p=0.05). CONCLUSION Patients older than one year, with the presence of metastases, and the MYCN amplification ratio &gt;5 on the FISH analysis as well as the ill-defined boundary and tumor size ≥50mm on an ultrasound assessment were associated with the UFH in neuroblastoma. These characteristics of the neuroblastoma should be considered in patient stratification and prognostic evaluation. Key words: Neuroblastoma; Unfavorable histology; Ultrasound

An infrared target intrusion detection method based on feature fusion and enhancement

Infrared target intrusion detection has significant applications in the fields of military defence and intelligent warning. In view of the characteristics of intrusion targets as well as inspection difficulties, an infrared target intrusion detection algorithm based on feature fusion and enhancement was proposed. This algorithm combines static target mode analysis and dynamic multi-frame correlation detection to extract infrared target features at different levels. Among them, LBP texture analysis can be used to effectively identify the posterior feature patterns which have been contained in the target library, while motion frame difference method can detect the moving regions of the image, improve the integrity of target regions such as camouflage, sheltering and deformation. In order to integrate the advantages of the two methods, the enhanced convolutional neural network was designed and the feature images obtained by the two methods were fused and enhanced. The enhancement module of the network strengthened and screened the targets, and realized the background suppression of infrared images. Based on the experiments, the effect of the proposed method and the comparison method on the background suppression and detection performance was evaluated, and the results showed that the SCRG and BSF values of the method in this paper had a better performance in multiple data sets, and it’s detection performance was far better than the comparison algorithm. The experiment results indicated that, compared with traditional infrared target detection methods, the proposed method could detect the infrared invasion target more accurately, and suppress the background noise more effectively.

Acoustical Assessment of Voice Disorder With Continuous Speech Using ASR Posterior Features

Traditionally acoustical assessment of voice disorder relies on simple and homogeneous speech samples like sustained vowels. Continuous speech is believed to be more representative of the daily function of voice and more preferable in clinical practice. This paper describes an attempt on automating voice assessment with continuous speech utterances. The proposed system makes use of a novel type of features that are derived from phone posterior probabilities outputted by a deep neural network based automatic speech recognition ASR system. These ASR-based voice features are designed to effectively quantify the mismatch between disordered voice and normal voice. Prediction of voice disorder severity is carried out first at utterance-level and subsequently the prediction scores for individual utterances from a subject are combined to give an overallassessment on the subject. With a low-dimension ASR-based feature vector, the utterance-level prediction accuracy is comparable to that with conventional features with a much higher dimension. By jointly using the ASR features and conventional voice features, a subject-level prediction accuracy of over $\text{80}{\%}$ on three severity classes can be achieved. Subjects with mild disorder and those with severe disorder could be perfectly distinguished by the proposed method.

Ultrasonographic features of different pathological types of breast phyllodes tumors

Objective To investigate the ultrasonographic features of different pathological types of phyllodes tumors (PT) of breast. Methods The clinical manifestations and sonographic findings were analyzed retrospectively in 132 patients with 136 different subtype PTs. Ultrasonographic features of benign, borderline and malignant types were compared. Results All the lesions were classified into benign (46/136, 33.8%), borderline (62/136, 45.6%) and malignant (28/136, 20.6%). On sonography, most tumors were shown as oval or lobulated (77.9%), well-defined margins (70.6%), and posterior echo enhancement (72.1%). Cystic areas were observed in 36 lesions (26.5%). No significant difference was observed in age, lesion shape, echo patterns, posterior acoustic features or cystic area (P>0.05). Large size, indistinct margins and grade Ⅱ-Ⅲ vascularity were more frequent in borderline and malignant tumors (P=0.002, P=0.028, P<0.001, respectively). Conclusions Phyllodes tumors of breast have certain characteristics on ultrasonography.Large size, unclear margins and rich blood flow signals may indicate malignancy. Key words: Ultrasonography; Breast neoplasms; Phyllodes tumor

Diagnostic performance of ultrasound strain elastography for differentiation of malignant breast lesions.

Objective of the study was to assess the performance of ultrasound strain elastography combined with conventional B-mode ultrasound to diagnose suspicious breast lesions (BI-RADS 4 and 5). Between January 2015 and December 2017, a total of 86 patients (55±17.9 years) with solid or unclear, non-cystic breast lesions were enrolled in the study. The breast lesions were evaluated by B-mode ultrasound and subsequent ultrasound strain elastography. Ultrasound features including echo pattern, lesion shape, marginal characteristics, calcifications, orientation and posterior features are useful for differentiating benign breast lesions from malignant ones. Malignant ultrasound features are irregular shape, hypoechoic pattern, spiculated margin, nonparallel orientation and posterior shadowing. Lesions with benign features such a circumscribed margin were classified as low conspicuous. In patients with highly conspicuous malignant masses ultrasound-guided core needle biopsy or surgical excision was performed. Among the 86 patients, 60 masses were histologically proven and 36 of these were malignant. Of the malignant lesions 26 invasive carcinomas were of no special type (NST), 1 invasive lobular carcinoma, 3 ductal carcinomas in situ and 6 metastases. 20 of these patients had breast density classified as ACR 3 or 4. The mean size of the masses was 1.2 cm (range: 0.5-5 cm). Based on ultrasound B-mode imaging, the lesions were classified as BI-RADS category 4 (n = 20; three 4a, nine 4b and eight 4c) and BI-RADS category 5 (n = 16). One patient had to be reclassified after strain elastographxy to BI-RADS 3.The sensitivity of ultrasound with strain elastography and additional B-Mode ultrasound for the characterization of solid breast lesions was 97%, for conventional B-mode alone 92%; the respective specificities were 82% and 73%, respectively. Ultrasound elastography can be a supplementary approach to conventional ultrasound to improve the diagnostic accuracy of malignant breast lesions.

Radiologic Findings of a Rare Subtype of Invasive Breast Cancer with Poor Prognosis: Metaplastic Carcinoma of the Breast.

The purpose of this study was to evaluate the mammographic, sonographic and MRI findings of metaplastic breast carcinoma. In this retrospective review study, we analyzed the medical files of 9600 patients who were treated for invasive breast cancers. Clinical information, histopathologic and radiologic findings of 65 patients were included in this study. All existing radiologic images and medical reports were reviewed retrospectively. Thirty-three patients had MG, 58 patients had US and 7 patients had MRI imaging results. Mammographically, the most frequent presentations of MPBC were round shape, microlobulated margin and high density masses. Calcifications with or without masses were not a frequent finding. The most common sonographic findings were round shape, partially indistinct angular margin, hypoechoic and heterogeneous echo patterns and no posterior feature masses. All lesions were presented as masses rather than non-mass enhancements on magnetic resonance imaging. Features of masses had more malignant feature on MRI than other modalities in all 7 patients. Metaplastic breast carcinoma is one of the rarest poorly differentiated invasive breast carcinomas. Interestingly, these aggressive tumors demonstrate benign or moderately malign features on imaging methods. This appearance of MPBC can cause it to be misdiagnosed as a benign breast lesion especially in young women. MPBC should be kept in mind in the differential diagnosis of large palpable breast masses. Therefore, follow-up at short intervals and/or multimodality imaging studies which include breast MRI are important for the diagnosis of MPBC.

Applied value of routine ultrasound and shear wave elastography in the diagnosis of triple negative breast cancer

Objective To investigate the applied value of routine ultrasound and shear wave elastography (SWE) in the comparison between triple negative breast cancer (TNBC) and non-triple negative breast cancer (non-TNBC). Methods A total of 120 lesions in 120 patients with pathologically confirmed breast cancer were retrospectively reviewed, which were examined by routine ultrasound and SWE before surgery. According to immunohistochemical analysis, those were divided into TNBC group and non-TNBC group. The features of routine ultrasound(including shape, orientation, margin, boundary, echo pattern, microcalcification, posterior features of each lesion and blood flow characteristics) and the SWE index[including the average value of the lesion stiffness(Emean), the maximum value (Emax), the minimum value (Emin), the standard deviation (SD), and the ratio of the normal breast gland tissue (Eratio)] in the two groups were analyzed and compared. Results ①Two-dimensional ultrasound: TNBC lesions mostly showed the margin of microlobulated, abrupt boundaries and no internal microcalcification, but non-TNBC lesions were more likely to have an angular or spiculated margin, an echogenic halo of boundary and a few microcalcification in the interior, which were statistically different(P 0.05). ②The values of Emax, Emean and Eratio were statistically different(P<0.05), with AUCs of 0.811, 0.781, and 0.770, respectively. Conclusions Routine ultrasound and SWE can comprehensively analyze the morphology, blood flow and stiffness features of breast lesions, which provides more valid information to identify TNBC and non-TNBC. Key words: Ultrasonography; Shear wave elastography; Triple negative breast cancer

A robust unsupervised pattern discovery and clustering of speech signals

In this paper, a novel approach to unsupervised pattern discovery for speech signals is proposed. The proposed work deviates from the standard speech recognition task, and aims to cluster the speech utterances based on the vocabulary of a broad topic. It attempts to discover the matched sequence of phonetic units by making use of the repeated patterns between the speech signals. Identification of matched sequence of phonetic patterns helps in clustering the speech signals, automatically. The proposed approach uses the posterior features derived from Gaussian mixture model (GMM) to find the repeated structure between the speech signals. Image processing techniques are used to identify these matched acoustic patterns. An angle histogram-based method is used to extract the desired matched keyword/phrase patterns present in a pair of speech utterances. The performance of the proposed method is evaluated on Hindi and Bengali news speech corpora using standard objective measures, and also compared with state-of-the-art techniques. The matched pairs of speech utterances obtained by the proposed method are grouped into broader classes using an appropriate clustering technique. The final clusters represent the broader classes of information such as politics, sports, and weather.