Search

Breast cancer is the second most common cancer in Peruvian women. Due to limitations in national breast cancer screening programs, especially in rural areas, more than 50% of cases of breast cancer in Peru are diagnosed in advanced stages. In collaboration with a local clinic registered as a nongovernmental organization (CerviCusco), RAD-AID International aims to create a sustainable diagnostic structure to improve breast cancer screening in Cuzco. With the support of local, national, and international partners that have collaborated in analyzing radiological resources, raising awareness in the population, acquiring equipment, training clinical staff, and building referral networks, our teams of radiologists, included in the RAD-AID team, have participated in training CerviCusco staff in breast ultrasound, thus enabling additional training for radiology residents through a regulated international collaboration.

Breast reduction surgery is a common procedure in plastic surgery clinics, and there are varying practices regarding preoperative mammography and breast ultrasound in patients who have no history of cancer and no symptoms other than those caused by macromastia. In this study, we retrospectively analyzed the imaging findings of patients who presented to the plastic surgery outpatient clinic due to macromastia between January 1, 2006 and June 1, 2020 and underwent mammography and/or breast ultrasound for preoperative screening and breast magnetic resonance imaging for further examination. Patients with a history of breast cancer diagnosed prior to preoperative screening or any other breast disease were excluded. Radiologically suspicious findings were significantly more common in patients over 40 years of age and significantly less frequent in the group under 50 years of age. When the patients were grouped by decade of life, the frequency of radiologically suspicious findings was significantly lower in the 20-29 group and significantly higher in the 40-49 and 50-59 groups. Malignancy was not detected by histopathological examination in any patient. Proliferative lesions were detected in 10 reduction mammoplasty specimens (2.4%) of 7 patients (3.1%). The correlation between radiological and histopathological findings may be weak in macromastic patients. Most suspicious radiological findings appear to be the population between 40 to 59 years of age.

In the AI diagnosis of breast cancer, instead of ultrasound images from non-standard acquisition process, the Breast Image Reporting and Data System (BI-RADS) reports are widely accepted as the input data since it can give standardized descriptions for the breast ultrasound samples. The BI-RADS reports are usually stored as the format of Knowledge Graph (KG) due to the flexibility, and the KG embedding is a common procedure for the AI analysis on BI-RADS data. However, since most existing embedding methods are based on the local connections in KG, in the situation of limited labeled samples, there is a clear need for embedding based diagnosis method which is capable of representing the global interactions among all entities/relations and associating the labeled/unlabeled samples. To diagnose the breast ultrasound samples with limited labels, in this paper we propose an efficient framework Knowledge Tensor Embedding with Association Enhancement Diagnosis (KTEAED), which adopts tensor decomposition into the embedding to achieve the global representation of KG entities/relations, and introduces the association enhancement strategy to prompt the similarities between embeddings of labeled/unlabeled samples. The embedding vectors are then utilized to diagnose the clinical outcomes of samples by predicting their links to outcomes entities. Through extensive experiments on BI-RADS data with different fractions of labels and ablation studies, our KTEAED displays promising performance in the situations of various fractions of labels. In summary, our framework demonstrates a clear advantage of tackling limited labeled samples of BI-RADS reports in the breast ultrasound diagnosis.

In breast radiology, ultrasound detection of biopsy markers or clips for localization purposes is often challenging, especially in the axilla. The purpose of this research was to test the hypothesis that the surface roughness of biopsy clips would elicit a twinkling signature on color Doppler, making them more readily identifiable by ultrasound. Ultrasound color Doppler imaging of 12 biopsy markers was performed and consensus scoring of the degree of twinkling (0 [no twinkling] to 4 [exuberant twinkling]) was obtained for each of the markers. The surface roughness characteristics of the markers were measured using 3-D coherence scanning interferometry. The 3 markers scoring at least 3 for twinkling in vitro were cork, Q and Vision. Of these 3 markers, only the cork marker scored a 4 ex vivo and in cadaveric tissue. Surface roughness metrics demonstrated a positive estimated correlation with the twinkling scores (rho = 0.33, 95% CI = [–0.48 to 0.84]). Of the 12 markers tested, the markers that twinkled corresponded to surface roughness measured with non-contact 3-D optical imaging. Qualitatively, lower color scales and color frequencies optimized twinkling, but the most specific qualitative predictor of confidence in twinkling was insensitivity to changes in color scale and color frequency values.

Mammography remains the only validated screening tool for breast cancer, however, there are limitations to mammography. One of the limitations of mammography is the variable sensitivity based on breast density. Supplemental screening may be considered based on the patient’s risk level and breast density. For average-risk women with nondense breasts, the sensitivity of digital breast tomosynthesis (DBT) screening is high; additional supplemental screening is not warranted in this population. For average-risk women with dense breasts, given the decreased sensitivity of mammography/DBT, this population may benefit from additional supplemental screening with contrast-enhanced mammography, screening ultrasound (US), breast MRI, or abbreviated breast MRI. In intermediate-risk women, there is emerging evidence suggesting that women in this population may benefit from breast MRI or abbreviated breast MRI. In intermediate-risk women with dense breasts, given the decreased sensitivity of mammography/DBT, this population may benefit from additional supplemental screening with contrast-enhancedmammography or screening US. There is strong evidence supporting screening high-risk women with breast MRI regardless of breast density. Contrast-enhanced mammography, whole breast screening US, or abbreviated breast MRI may be also considered. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision include an extensive analysis of current medical literature from peer reviewed journals and the application of well-established methodologies (RAND/UCLA Appropriateness Method and Grading of Recommendations Assessment, Development, and Evaluation or GRADE) to rate the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where evidence is lacking or equivocal, expert opinion may supplement the available evidence to recommend imaging or treatment.

Background The objective of our study was to describe the workup, management, and outcomes of pediatric patients with breast masses undergoing operative intervention. Materials and methods A retrospective cohort study was conducted of girls 10-21 y of age who underwent surgery for a breast mass across 11 children's hospitals from 2011 to 2016. Demographic and clinical characteristics were summarized. Results Four hundred and fifty-three female patients with a median age of 16 y (IQR: 3) underwent surgery for a breast mass during the study period. The most common preoperative imaging was breast ultrasound (95%); 28% reported the Breast Imaging Reporting and Data System (BI-RADS) classification. Preoperative core biopsy was performed in 12%. All patients underwent lumpectomy, most commonly due to mass size (45%) or growth (29%). The median maximum dimension of a mass on preoperative ultrasound was 2.8 cm (IQR: 1.9). Most operations were performed by pediatric surgeons (65%) and breast surgeons (25%). The most frequent pathology was fibroadenoma (75%); 3% were phyllodes. BI-RADS scoring ≥4 on breast ultrasound had a sensitivity of 0% and a negative predictive value of 93% for identifying phyllodes tumors. Conclusions Most pediatric breast masses are self-identified and benign. BI-RADS classification based on ultrasound was not consistently assigned and had little clinical utility for identifying phyllodes.

To compare the diagnostic performance of mammography (MG) alone versus MG combined with adjunctive imaging modalities, including handheld ultrasound (HHUS), automated breast ultrasound (ABUS), digital breast tomosynthesis (DBT), contrast-enhanced mammography (CEM), and magnetic resonance imaging (MRI) in women with non-dense and dense breasts.Medline, Embase, PubMed, CINAHL, Scopus, and the Web of Science databases were searched up to October 2019. Quality assessment was performed using QUADAS-2. RevMan 5.3 was used to conduct a meta-analysis of the studies.In dense breasts, adding adjunctive modalities significantly increased cancer detection rates (CDRs): HHUS (relative risk [RR] = 1.49; 95% confidence interval [CI], 1.19-1.86; P = .0005); ABUS (RR = 1.44; 95% CI, 1.16-1.78; P = .0008); DBT (RR = 1.38; 95% CI, 1.14-1.67; P = .001); CEM (RR = 1.37; 95% CI, 1.12-1.69; P = .003); and MRI (RR = 2.16; 95% CI, 1.81-2.58; P.00001). The recall rate was significantly increased by HHUS (RR = 2.03; 95% CI, 1.89-2.17; P.00001), ABUS (RR = 1.90; 95% CI, 1.81-1.99; P.00001), and MRI (RR = 2.71; 95% CI, 1.73-4.25; P.0001), but not by DBT (RR = 1.14; 95% CI, 0.95-1.36; P = .15). In non-dense breasts, HHUS and MRI showed significant increases in CDRs but not DBT: HHUS (RR = 1.14; 95% CI, 1.01-1.29; P = .04); MRI (RR = 1.78; 95% CI, 1.14-2.77; P = .01); and DBT (RR = 1.09; 95% CI, 1.13-1.75; P = .08). The recall rate was also significantly increased by HHUS (RR = 1.43; 95% CI, 1.28-1.59; P.00001) and MRI (RR = 3.01; 95% CI, 1.68-5.39; P = .0002), whereas DBT showed a non-significant reduction (RR = 0.83; 95% CI, 0.65-1.05; P = .12).Adding adjunctive modalities to MG increases CDRs in women with dense and non-dense breasts. Ultrasound and MRI increase recall rates across all breast densities; however, MRI results in higher values for both CDRs and recall rates.

Breast cancer is one of the most serious disease affecting women’s health. Due to low cost, portable, no radiation, and high efficiency, breast ultrasound (BUS) imaging is the most popular approach for diagnosing early breast cancer. However, ultrasound images are low resolution and poor quality. Thus, developing accurate detection system is a challenging task. In this paper, we propose a fully automatic segmentation algorithm consisting of two parts: fuzzy fully convolutional network and accurately fine-tuning post-processing based on breast anatomy constraints. In the first part, the image is pre-processed by contrast enhancement, and wavelet features are employed for image augmentation. A fuzzy membership function transforms the augmented BUS images into the fuzzy domain. The features from convolutional layers are processed using fuzzy logic as well. The conditional random fields (CRFs) post-process the segmentation result. The location relation among the breast anatomy layers is utilized to improve the performance. The proposed method is applied to the dataset with 325 BUS images, and achieves state-of-the-art performance compared with that of existing methods with true positive rate 90.33%, false positive rate 9.00%, and intersection over union (IoU) 81.29% on tumor category, and overall intersection over union (mIoU) 80.47% over five categories: fat layer, mammary layer, muscle layer, background, and tumor.

Background Breast cancer is a deadly disease responsible for statistical yearly global death. Identification of cancer tumors is quite tasking, as a result, concerted efforts are thus devoted. Clinicians have used ultrasounds as a diagnostic tool for breast cancer, though, poor image quality is a major limitation when segmenting breast ultrasound. To address this problem, we present a semantic segmentation method for breast ultrasound (BUS) images. Method The BUS images were resized and then enhanced with the contrast limited adaptive histogram equalization method. Subsequently, the variant enhanced block was used to encode the preprocessed image. Finally, the concatenated convolutions produced the segmentation mask. Results The proposed method was evaluated with two datasets. The datasets contain 264 and 830 BUS images respectively. Dice measure (DM), Jaccard measure, and Hausdroff distance were used to evaluate the methods. Results indicate that the proposed method achieves high DM with 89.73% for malignant and 89.62% for benign BUSs. Moreover, the results obtained validate the capacity of the proposed method to achieve higher DM in comparison with reported methods. Conclusion The proposed algorithm provides a deep learning segmentation procedure that can segment tumors in BUS images effectively and efficiently.

Objective To assess the effectiveness of diagnostic breast ultrasound training provided for general practitioners and nurses in Rwanda via intensive in-person and subsequent online supervision and mentorship. Methods Four breast radiologists from Brigham and Women’s Hospital trained two general practitioner physicians and five nurses in Rwanda over 9 total weeks of in-person training and 20 months of remote mentorship using electronic image review with emailed feedback. Independently recorded assessments were compared to calculate the sensitivity and specificity of trainee assessments, with radiologist assessments as the gold standard. We compared performance in the first versus second half of the training. Results Trainees’ performance on written knowledge assessments improved after training (57.7% versus 98.1% correct, P = .03). Mean sensitivity of trainee-performed ultrasound for identifying a solid breast mass was 90.6% (SD 4.2%) in the first half of the training (period 1) and 94.0% (SD 6.7%) in period 2 (P = .32). Mean specificity was 94.7% (SD 5.4%) in period 1 and 100.0% (SD 0) in period 2 (P = .10). Mean sensitivity for identifying a medium- or high-suspicion solid mass increased from 79.2% (SD 11.0%) in period 1 to 96.3% (SD 6.4%) in period 2 (P = .03). Specificity was 84.4% (SD 15.0%) in period 1 and 96.7% (SD 5.8%) in period 2 (P = .31). Discussion Nonradiologist clinicians (doctors and nurses) in a rural sub-Saharan African hospital built strong skills in diagnostic breast ultrasound over 23 months of combined in-person training and remote mentorship. The sensitivity of trainees’ assessments in identifying masses concerning for malignancy improved after sustained mentorship. Assessment of impact on patient care and outcomes is ongoing.

Idiopathic granulomatous mastitis (IGM), or granulomatous lobular mastitis is a rare, benign, inflammatory condition of the breast, without an identifiable underlying etiology. The clinical and imaging diagnosis of this entity is challenging with the presentation frequently mimicking inflammatory breast carcinoma (IBC). Mammography and breast ultrasound (US) have an important role in its detection, however, biopsy is imperative for histopathological confirmation. We present three cases of biopsy proven IGM, highlighting the variability of the clinical and imaging features,brieflyreview the relevant literature and discuss the challenges associated with its diagnosis and management.

This study aimed to investigate the effect of calcifications on shear-wave elastography in evaluating breast lesions. We retrospectively reviewed ultrasound images of 673 breast lesions and compared the elasticity between lesions with and without calcifications in three subgroups: benign lesions, in situ carcinomas and invasive carcinomas. Breast lesions were confirmed histologically (n = 401) or by follow-up images for more than 2 y (n = 272). Calcifications were present in 25.3% (170/673) of the lesions. The Emean values with and without calcifications, respectively, were as follows: 62.8 and 29.8 kPa in benign lesions (p = 0.000), 114.6 and 52.8 kPa in in situ carcinomas (p = 0.037) and 171.9 and 146.4 kPa in invasive carcinomas (p = 0.018). The presence of calcifications significantly increased the Emean of breast lesions. Shear-wave elastography should be carefully interpreted in benign lesions with calcifications and in situ carcinomas without calcifications.

Breast ultrasound (BUS) is a powerful screening tool for examination of breast lesions. Recently, research attention has been paid to combining doctor’s opinions and machine learning technology to build up a better computer-aided diagnosis (CAD) system. In this paper, we propose an improved approach that uses human-rating BI-RADS scores to classify the BUS samples. A BI-RADS feature scoring scheme is firstly adopted to standardize the descriptions on breast lesions, and then the diagnostic patterns are mined by a biclustering algorithm in the collected BI-RADS feature score dataset. With an input sample, the diagnostic patterns could be activated to different degrees which represent the high-level features by calculating the distance between input sample and patterns. The high-level features of the sample are input into a multi-layer perception neural network (MLPNN) and we use a cost matrix to convert the output from probabilities to classification cost. The structure of the MLPNN and the values of elements in cost matrix are optimized by Particle Swarm Optimization, and it finally classifies the input of BUS sample. According to the comparative experiments with other CAD approaches and the experienced sonographers, the proposed approach achieved the best sensitivity, indicating that it can serve as an assistant diagnostic system in clinical practices.

Purpose To assess the use and outcomes of ultrasound for the evaluation of breast signs and symptoms in pediatric females. Methods A retrospective database review identified all patients ≤18-years-old who underwent breast ultrasound at an academic institution over a 20-year period. Each symptomatic site was designated a case and analyses were performed on each case. Imaging findings were obtained from the radiology reports. Clinical and pathology data were obtained from the medical records. Descriptive statistics were performed. Results The final cohort comprised 124 cases in 101 patients. Mean age was 15 years (range 1–18). The most common indication for ultrasound was a palpable lump (71%). Thirty-seven cases (30%) demonstrated no sonographic correlate to the symptom; 36 (29%) had a benign correlate. The most common benign correlates were abscess/phlegmon and cyst. All cases of abscess/phlegmon had infectious symptoms. Fifty-one cases (41%) demonstrated a sonographic mass that was not characteristically benign. Of these indeterminate masses, 27 were recommended for biopsy, 13 for short-interval follow-up, and 6 had no recommendation. Of 27 biopsied masses, 63% were fibroadenomas. No symptoms were due to malignancy. Therefore, the NPV of ultrasound was 100% and the PPV 0%. Conclusion In this cohort of pediatric and adolescent patients, malignancy was never the cause of breast symptoms. Imaging yielded false positives with a biopsy recommendation in 22% of cases. Ultrasound provided value in evaluating infectious symptoms. Given the extreme rarity of breast cancer in this population, surveillance may be a safe alternative for most indeterminate lesions.

Breast malignancy is the second most common cause of cancer death in women. However, less common breast masses can mimic carcinoma and can pose diagnostic challenges. This case-based review describes a spectrum of rare breast neoplastic and non-neoplastic masses ranging from malignant to benign entities. Malignant masses in this review include adenoid cystic carcinoma, spindle cell lipoma, granular cell tumor, angiosarcoma, glomus tumor, adenosquamous carcinoma, and myofibroblastoma. Benign masses include sarcoidosis, diabetic mastopathy, and cat scratch disease. Demographics and, when relevant, clinical presentation are summarized. Breast imaging appearance on mammography and ultrasound are highlighted along with radiology-pathology correlation with the appearance and characteristics of the histopathological specimen of these rare masses.

Unlike other modalities in breast imaging, breast ultrasound is very operator dependent. Proper characterization and management of breast lesions depends on the knowledge and skill of the radiologist performing the exam. Breast ultrasound optimization continues to evolve as the technology of ultrasound machines improves. The American College of Graduate Medical Education (ACGME) program requirements for graduate medical education in diagnostic radiology recently updated requirements to include competency in ultrasound physics, knobology, and image generation. As trainees are held to high ultrasound optimization standards, practicing radiologists who perform breast ultrasound exams must keep up to date on current breast ultrasound optimization techniques to avoid mischaracterizing and mismanaging breast ultrasound findings. In this paper, ultrasound optimization techniques, including patient positioning, transducer frequency, transducer contact and pressure, depth, gain, focus, tissue harmonic imaging, spatial compounding, dynamic range, speed of sound imaging, Doppler evaluation, and elastography will be described. Multiple ultrasound case examples will be used to illustrate application of these skills. After reading this paper, the reader will be able to apply these techniques to their own breast ultrasound practice, improving characterization and management of breast lesions in their patients.

Mucinous and medullary breast cancers (BCs) have different histological substrates that manifest as different imaging features on mammography, ultrasound, and MRI. The aim of the present review is to demonstrate the differences between these two rare BC subtypes and to describe the microscopic features, review the imaging methods for detection of both cancer subtypes, illustrate the imaging findings and present useful pearls and pitfalls. Out of a total of 30 patients with mucinous BC and nine with medullary BC, we have selected typical and also unusual imaging features that best represent these cancers. The patients underwent a mammography and breast ultrasound followed by magnetic resonance imaging. We briefly exhibit histological characteristics for a better understanding of the imaging aspects.

Breast cancer is the second prevalent type of cancer among women. Breast Ultrasound (BUS) imaging is one of the most frequently used diagnostic tools to detect and classify abnormalities in the breast. To improve the diagnostic accuracy, Computer Aided Diagnosis (CAD) system is helpful for breast cancer detection and classification. Normally, a CAD system consists of four stages: pre-processing, segmentation, feature extraction, and classification. In this chapter, the pre-processing step includes speckle noise removal using Speckle Reducing Anisotropic Diffusion (SRAD). The goal of segmentation is to locate the Region of Interest (ROI) and Active contour-based segmentation is used in this work. The texture features are extracted and fed to a classifier to categorize the images as Normal, Benign and Malignant. In this work three classifiers namely K-Nearest Neighbors (KNN) algorithm, Decision tree algorithm and Random Forest classifier are used and the performance is compared based on the accuracy of classification.

The purpose of this study was to investigate the diagnostic performance of the automated breast ultrasound system (ABUS) compared with hand-held ultrasonography (HHUS) and mammography (MG) for breast cancer in women aged 40 y or older. A total of 594 breasts in 385 patients were enrolled in the study. HHUS, ABUS and MG exams were performed for these patients. Follow-up and pathologic findings were used as the reference standard. Based on the reference standard, 519 units were benign or normal and 75 were malignant. The sensitivity, specificity, accuracy and Youden index were 97.33%, 89.79%, 90.74% and 0.87 for HHUS; 90.67%, 92.49%, 92.26% and 0.83 for ABUS; 84.00%, 92.87%, 91.75% and 0.77 for MG, respectively. The specificity of ABUS was significantly superior to that of HHUS (p = 0.024). The area under the receiver operating characteristic curve was 0.936 for HHUS, which was the highest, followed by 0.916 for ABUS and 0.884 for MG. However, the difference was not statistically significant (p > 0.05). In conclusion, the diagnostic performance of ABUS for breast cancer was equivalent to HHUS and MG and potentially can be used as an alternative method for breast cancer diagnosis.

Nonlinear mechanical properties of breast tissue can be employed to diagnose and differentiate breast tumors. To obtain such nonlinear mechanical properties, it is necessary to track tissue motion under large deformation. In this study, a multi-compression strategy was utilized to produce large tissue deformation and a method to estimate three-dimensional (3D) motion of tissue under large deformation was introduced. Given multiple volumes of ultrasound data, the proposed method first estimates volume-to-volume incremental displacements using a 3D region-growing motion-tracking method. Then, possible outliers among all incremental displacements are removed to avoid error accumulation. Once large displacement errors have been removed, all incremental displacements are registered together to obtain accumulated displacements under large tissue deformation (e.g. > 10%). The proposed method was tested with one set of in vivo tumor-bearing ultrasound data acquired from a human subject. A total of 10 small-strain deformation steps were performed to obtain the final accumulated displacement field, in which the breast lesion and its surrounding were deformed by approximately 6% and 16%, respectively. The contrast-to-noise ratio (CNR) and signal-to-noise ratio (SNR) of the elasticity images obtained with the proposed method are all higher than those with a 2D tracking method. Furthermore, in three orthogonal views of accumulated axial strain images, the breast lesion was clearly visible with good correspondence between the axial strain and B-mode images.

Purpose The purpose of this study was to identify practice trends and opinions concerning breast sonoelastography in two different health care systems, one in Europe (France) and the other in North America (Province of Quebec/Canada). Materials and methods We distributed an 11-item online survey among French and Canadian breast radiologists. The survey comprised of four sections: (i) personal practice characteristics, (ii) breast sonoelastography usage in daily practice and evaluation of its usefulness, (iii) limitations and roles of sonoelastogrpahy in their clinical practice, and (iv) types of elastographic technique and interpretation. Results We found that sonoelastography of the breast appears unpopular among Canadian radiologists, and poorly credible among French radiologists, who perceive it as an unreliable technique. To date, its real impact in clinical practice remains uncertain. Conclusion Continued learning and awareness of the indications, advantages and limitations of breast sonoelastography may motivate breast radiologists to adopt its use.

Computer-aided-diagnostic (CAD) techniques are of great help in facilitating the diagnosis of breast ultrasound (BUS) images. Conventional CAD approaches segment the region of interest (ROI), extract image features, and finally train a classifier for outputting the final diagnostic decision. Although some reported CAD systems have achieved high accuracy, their performance heavily depended on the source of training data. Meanwhile, the classification procedures formed by low-level features are hardly explicable. A novel CAD approach for BUS data with human-in-the-loop is therefore proposed in this paper. Differing from conventional CAD systems, user participation is involved to manually give the scores for selected Breast Imaging Reporting and Data System (BI-RADS) features. Three experienced radiologists obtained 1062 breast ultrasound data samples with BI-RADS feature scores, which formed a quantified score dataset for mining diagnostic patterns based on a constant column biclustering method. The discovered diagnostic patterns (i.e., the biclusters) are input into a fuzzy reasoning system to infer the final diagnostic decision (i.e., benign or malignant). In addition, a particle swarm optimization (PSO) algorithm is employed to optimize the parameters of the membership function and judgment threshold for the fuzzy reasoning. The proposed system skips the image processing by utilizing the artificial scoring datasets, and the BUS images from different sources can be classified. Meanwhile, more understandable and acceptable results can be given by the fuzzy reasoning. In the experiment, 10-fold cross-validation was used to evaluate system performance. The average accuracy reached 96.81%, specificity 95.45%, sensitivity 97.72%, positive predictive value (PPV) 97.03%, and negative predictive value (NPV) 96.57%, outperforming previously reported methods.

Three-dimensional automated breast ultrasound system (3D ABUS) is an innovation in breast ultrasound that has been developed to uncouple detection from image acquisition and to address the limitations of handheld ultrasound (HHUS). 3D ABUS provides a large field of view using high frequency transducers, producing high-resolution images and covering a large portion of the breast with one sweep. As more data become available on breast density and the impact of supplemental screening, 3D ABUS has gained wider acceptance as an adjunct tool to mammography. Computer-aided detection software significantly reduces interpretation time, improving the workflow for the utilization of 3D ABUS as a supplemental screening tool. In the diagnostic setting, 3D ABUS offers valuable impact in the detectability of breast lesions and the differentiation of malignant from benign lesions, with a high inter-observer agreement. State-of-the art technique, including uniform compression and proper positioning, tends to reduce artifactual posterior shadowing, while combined 3D ABUS-mammography interpretation improves radiologists' diagnostic performance. Promising results have supported the enhanced efficiency of 3D ABUS in detecting the extent of breast cancer and assessing response to neoadjuvant chemotherapy, whereas its correlation with molecular subtypes of breast cancer is remarkable. Future perspectives include the integration of radiomics and deep learning in the further development of 3D ABUS.

Aim of the study Over the past 50 years, the application of mammography – an X-ray of the breast – to screen healthy women has been a successful strategy to reduce breast cancer mortality. The aim of this study was to review the literature on novel imaging approaches that have the potential to replace mammography. Methods An online literature search was carried out using PubMed, Google Scholar, ScienceDirect and Google Patents. The search keywords included “breast cancer”, “imaging” and “screening”, with 51 journal articles and five United States patents being selected for review. Seventeen relevant online sources were also identified and referenced. Results In addition to full-field digital mammography (FFDM), a further nine imaging modalities were identified for review. These included: digital breast tomosynthesis (DBT); breast computed tomography (BCT); automated breast ultrasound (ABUS); fusion of FFDM and ABUS; fusion of DBT and ABUS; magnetic resonance imaging (MRI); optical imaging; radio-wave imaging; and tactile sensor imaging. Important parameters were considered: diagnostic success (sensitivity and specificity), especially in dense breasts; time to acquire the images; and capital cost of the equipment. Conclusions DBT is rapidly replacing FFDM although it still misses invasive cancers in dense tissue. The fusion of ABUS, either with FFDM or DBT, will lead to sensitivity and specificity approaching 100%. The fusion of opto-acoustic imaging with ultrasound holds considerable promise for the future.

The aim of our study was to compare strain elastography (SE), acoustic radiation force impulse-inducing Virtual Touch Imaging ([VTI] Siemens Medical Solutions, Mountain View, CA, USA), Virtual Touch Imaging Quantification ([VTIQ] Siemens Medical Solutions) and combined methods in the evaluation of ultrasound (US) Breast Imaging-Reporting and Data System (BI-RADS) category 4 lesions to explore an applicable way to reduce unnecessary biopsy by reducing false positives of conventional US without yielding false-negative cases. A total of 267 patients with 278 BI-RADS category 4 lesions (151 benign and 127 malignant) were evaluated with conventional B-mode US, SE, VTI and VTIQ implemented on a Siemens Acuson S2000 US system. Diagnostic performance, including area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were evaluated. Overall, VTI alone exhibited the highest NPV (91.74%), although combined elastic methods exhibited higher NPV than single methods, with the highest NPV at 100% when the VTI, SE and VTIQ methods were combined. Compared with conventional US, PPV increased from 45.7% (127 of 278) to 63.18% (127 of 201) when adding combined elastography (VTI + SE +VTIQ). In addition, 52.5% (63/120) and 50.8% (61/120) of BI-RADS 4 A lesions were downgraded when using combined methods (VTI + SE and VTI + SE + VTIQ, respectively) without missing any cancer. However, 2 intraductal papillomas and 1 phyllodes tumor were not identified. In conclusion, the combination of different elastic methods have the potential to downgrade BI-RADS 4A lesions to reduce false-positive biopsies without increasing the risk of missing cancers.

This manuscript reports preliminary results obtained by combining estimates of two or three (among seven) quantitative ultrasound (QUS) parameters in a model-free, multi-parameter classifier to differentiate breast carcinomas from fibroadenomas (the most common benign solid tumor). Forty-three subjects scheduled for core biopsy of a suspicious breast mass were recruited. Radiofrequency echo signal data were acquired using clinical breast ultrasound systems equipped with linear array transducers. The Reference Phantom Method was used to obtain system-independent estimates of the specific attenuation (ATT), the average backscatter coefficients (ABSC), the effective scatterer diameter (ESD) and an effective scatterer diameter heterogeneity index (ESDHI) over regions of interest within each mass. In addition, the envelope amplitude signal-to-noise ratio (SNR), the Nakagami shape parameter, m, and the maximum collapsed average (maxCA) of the generalized spectrum were also computed. Classification was performed using the minimum Mahalanobis distance to the centroids of the training classes and tested against biopsy results. Classification performance was evaluated with the area under the receiver-operating characteristic (ROC) curve. The best performance with a two-parameter classifier used the ESD and ESDHI and resulted in an area under the ROC curve of 0.98 [0.95–1.00, 95% confidence interval]. Classification performance improved with three parameters (ATT, ESD, and ESDHI) yielding an area under the ROC curve of 0.999 [0.995–1.000].These results suggest that system independent QUS parameters, when combined in a model-free classifier, are a promising tool to characterize breast tumors. A larger study is needed to further test this idea.

Objectives To determine the number and characteristics of cancers detected and the optimal imaging evaluation in women presenting with focal breast pain (FBP). Materials and methods We performed a retrospective review of 4720 women who underwent imaging for FBP from 2001 to 2013. Women 18 and over with one or two foci of breast pain and no concurrent breast symptoms were included. 944 patients met criteria. We recorded the imaging work-up, presence and type of finding at the site of pain, BI-RADS® assessment, and pathological outcomes. Subsequent imaging and clinical follow up was recorded. Results Imaging evaluation consisted of sonogram alone in 286 women, mammogram alone in 231 women, and both in 427 women. 113 women had an imaging finding at the site of pain; 103 were designated benign or probably benign. 12 biopsies of corresponding findings were performed: 9 benign, 1 invasive lobular carcinoma, 1 invasive ductal carcinoma, 1 ductal carcinoma in situ. All three malignancies were seen mammographically; 2 had an ultrasound correlate. At initial evaluation, 4 incidental breast cancers were diagnosed remote from the site of FBP. All were seen on mammogram and 2 of 4 had an ultrasound correlate. On follow up evaluation, 9 cancers were diagnosed at the site of pain and 13 incidental cancers were diagnosed. Conclusion FBP is rarely associated with malignancy. Targeted ultrasound may be deferred in women 40 and older with FBP, no other clinical findings, and a negative mammogram.

Automatic and accurate breast ultrasound (BUS) image segmentation is crucial to achieve effective ultrasound-based computer aided diagnosis (CAD) systems for breast cancer. However, segmenting the tumor in BUS images is often challenging due to several artifacts that degrade the quality of ultrasound images. In this study, a new two-phase method is proposed to enable automatic and accurate segmentation of BUS images by decomposing the image into superpixels with high boundary recall ratio and employing edge- and region-based information to outline the tumor. The first phase of the method obtains an initial outline of the tumor by decomposing the BUS image into coarse superpixels to enable effective estimation of their tumor likelihoods and employing a customized graph cuts algorithm to segment the superpixels. The segmentation of the superpixels is carried out using edge-based information that quantifies the image contour cue and region-based information that characterizes the texture content of the superpixels. In the second phase, the tumor outline is improved by decomposing the BUS image into fine superpixels that enable high boundary recall ratio and employing the customized graph cuts algorithm to segment the superpixel located around the initial tumor outline. Furthermore, an edge-based active contour model is used to smooth the tumor outline. The performance of the proposed method was evaluated using a database that includes 160 BUS images (86 benign and 74 malignant). The results indicate that the first phase of the proposed method was able to detect the tumor in all BUS images and obtain mean values of the true positive ratio (TPR), false positive ratio (FPR), false negative ratio (FNR), similarity ratio (SIR), Hausdorff error (HE), and mean absolute error (ME) equal to 91.68, 11.16, 8.32, 84.52, 17.59, and 4.67, respectively. In fact, the results obtained by the first phase of the proposed method outperform four existing BUS image segmentation algorithms. Moreover, the second phase of the proposed method was able to improve the tumor outlines of the first phase and achieve mean TPR, FPR, FNR, SIR, HE, and ME values of 96.04, 7.99, 3.96, 91.41, 11.66, and 3.65, respectively. These results suggest the feasibility of employing the proposed method, which enables automatic and accurate tumor segmentation in BUS images, to develop effective CAD systems for breast cancer.

Ultrasound is the most widely used imaging modality for screening of breast tumors. However, due to the presence of speckle noise in an ultrasound image, the diagnostic information gets masked and the interpretation of the breast abnormalities becomes difficult for the radiologist. The texture of the tumor region and the shape/margin characteristics are considered to be important parameters for the analysis of the breast tumors. In the present work, exhaustive experimentation has been carried out for the design of CAD systems for classification of breast tumors by considering (a) original images only, (b) despeckled images only and (c) both original and despeckled images together (hybrid approach). Total 100 breast ultrasound images (40 benign and 60 malignant) have been used for the analysis. Initially, these images have been despeckled using six filters namely Lee sigma, BayesShrink, DPAD, FI, FB and HFB filters. Total 162 features (149 texture and 13 morphological features) have been computed from both original and despeckled breast ultrasound images and SVM classifier has been used extensively for the classification. The results of the study indicate that the hybrid approach of CAD system design using texture features computed from original images combined with morphological features computed from images despeckled by DPAD filter yield optimal performance for classification of benign and malignant breast tumors with a classification accuracy of 96.0%. From the promising results of the study it can be concluded that the proposed hybrid CAD system design could be used as a second opinion tool in clinical setting.

Purpose To evaluate whether in the setting of negative diagnostic mammogram for breast pain additional ultrasound is necessary. Methods Retrospective IRB-approved review of our database identified 8085 women who underwent ultrasound evaluation for breast pain from 1/1/2013-12/31/2013. Of 8085 women, 559 women had mammogram evaluation preceding the ultrasound and these women comprise the basis of this study. The patient′s age, type of mammogram examination (screening or diagnostic), Breast Imaging-Reporting and Data System (BI-RADS) breast density (BD), type of breast pain (focal, diffuse, cyclical, unilateral, bilateral), additional breast symptoms (palpable concern, nipple discharge, skin changes, others), mammogram or ultrasound findings and final BI-RADS assessment, follow-up imaging, and follow-up biopsy results were reviewed and recorded. Results The median age of patients was 46 years old (range: 27-97). Patients recalled from negative screening mammogram were 29.8% (167/559). Patients with preceding negative diagnostic mammogram were 70.2% (392/559). The BI-RADS BD distribution was BD1: 5.5%, BD2: 39.9%, BD3: 46.0%, BD4: 8.6%. Final BI-RADS assessments were BI-RADS 1/2 (79%), BI-RADS 3 (12.9%), BI-RADS 4 (8.1%), BI-RADS 5 (0%). Majority (66.9%, 374/559) of the patient had breast pain alone. Additional breast symptoms were also noted as follows: palpable concern (24%), nipple discharge (3.9%), skin changes or other (5.2%). On follow-up evaluation, 26 findings were recommended for tissue sampling yielding 2 malignancies (0.4%, 2/559) in 2 patients. In the setting of negative mammogram and clinical symptom of breast pain alone yielded no malignances (NPV, 100%, 374/374) and was not impacted by BD. In patients with additional symptoms accompanying pain, malignancies were present despite negative mammogram in 2 patients; nipple discharge (4.5%, 1/22), and palpable concern (0.7%, 1/134). Conclusion In the setting of negative mammogram and breast pain alone, additional evaluation with ultrasound is likely low yield and may be unnecessary. However, with additional symptoms such as palpable concern or nipple discharge, ultrasound is likely an important adjunct modality for identifying mammographically occult tumors.

PURPOSE This study evaluated the training and assessment role of anthropomorphic breast ultrasound phantoms that simulated both the morphological and sonographic characteristics of breast tissue, including lesions, in a group of radiology residents at a large academic medical center. METHODS This was a prospective study involving nine residents across second to fourth years of a radiology residency program. Two devices (phantom 1 and phantom 2) were designed and constructed to produce similar realistic sonographic images of breast morphology with a range of embedded pathologies to provide a realistic training experience. Baseline assessments of all residents' ability to detect and characterize lesions in phantom 1 were carried out, followed by a 2-hour teaching session on the same phantom. All residents underwent a posttraining, final assessment on phantom 2 to evaluate changes in their lesion detection rate and ability to correctly characterize the lesions. RESULTS The results demonstrated there was a significant increase in both the pooled detection and correct characterization score for all residents pre- and posttraining of 26% ± 14% and 17% ± 8%, P < .0003, respectively. Posttraining assessment surveys revealed that residents rated the training experience highly. CONCLUSIONS This study suggests that there is a benefit in including a simulation training workshop with a novel anthropomorphic breast ultrasound training device to a radiology resident education program. Finally, the phantoms used in this study are useful for training and assessment purposes because they provide a lifelike simulation of breast tissue to practice ultrasound imaging without direct exposure to patients, in an environment with no pressure.

Ultrasound imaging is most popular technique used for breast cancer screening. Lesion segmentation is challenging step in characterization of breast ultrasound (US) based Computer Aided Diagnosis (CAD) systems due to presence of speckle noise, shadowing effect etc. The aim of this study is to develop an automatic lesion segmentation technique in breast US with high accuracy even in presence of noises, artifacts and multiple lesions. This article presents a novel clustering method called Multi-scale Gaussian Kernel induced Fuzzy C-means (MsGKFCM) for segmentation of lesions in automatically extracted Region of Interest (ROI) in US to delimit the border of the mass. Further, a hybrid approach using MsGKFCM and Multi-scale Vector Field Convolution (MsVFC) is proposed to obtain an accurate lesion margin in breast US images. Initially, the images are filtered using speckle reducing anisotropic diffusion (SRAD) technique. Subsequently, MsGKFCM is applied on filtered images to segment the mass and detect an appropriate cluster center. The detected cluster center is further used by MsVFC to determine the accurate lesion margin. The proposed technique is evaluated on 127 US images using measures such as Jaccard Index, Dice similarity, Shape similarity, Hausdroff difference, Area difference, Accuracy, F-measure and analysis of variance (ANOVA) test. The empirical results suggest that the proposed approach can be used as an expert system to assist medical professionals by providing objective evidences in breast lesion detection. Results obtained are so far looking promising and effective in comparison to state-of-the-art algorithms.

The main purpose of this study was to retropectively compare the clinical and pathologic characteristics of ductal carcinoma in situ (DCIS) detected on mammography and ultrasound (US) in asymptomatic patients. From February 2014 to September 2016, 236 asymptomatic patients with primary pure DCIS and dense breasts were included. The patients were classified into two groups. The mammography group (n = 165) included patients with DCIS detected on mammography, and the US group (n = 71) included patients with DCIS detected on US only. Clinicopathologic characteristics were compared between the two groups. Subgroup analyses were performed with a cutoff age of 50 y and a cutoff tumor size of 20 mm. In 236 patients, younger age, smaller tumor size, low nuclear grade, no comedo necrosis and progesterone receptor positivity were observed more in the US group (p0.05). HER2 and Ki67 positivity was observed more frequently in the mammography group (p0.05). Similar results were obtained in 168 patients with DCIS20 mm and in patients ≥50 y. In patients50 y, smaller tumor size, low nuclear grade and no comedo necrosis were observed significantly more often in the US group. DCIS in the US group significantly more often manifested low nuclear grade, no comedo necrosis and hormone receptor positivity, whereas HER2 and Ki67 positivity was observed significantly more often in the mammography group.

In the present work, the performance assessment of despeckle filtering algorithms has been carried out for (a) noise reduction in breast ultrasound images and (b) segmentation of benign and malignant tumours from breast ultrasound images. The despeckle filtering algorithms are broadly classified into eight categories namely local statistics based filters, fuzzy filters, Fourier filters, multiscale filters, non-linear iterative filters, total variation filters, non-local mean filters and hybrid filters. Total 100 breast ultrasound images (40 benign and 60 malignant) are processed using 42 despeckle filtering algorithms. A despeckling filter is considered to be appropriate if it preserves edges and features/structures of the image. Edge preservation capability of a despeckling filter is measured by beta metric (β) and feature/structure preservation capability is quantified using image quality index (IQI). It is observed that out of 42 filters, six filters namely Lee Sigma, FI, FB, HFB, BayesShrink and DPAD yield more clinically acceptable images in terms of edge and feature/structure preservation. The qualitative assessment of these images has been done on the basis of grades provided by the experienced participating radiologist. The pre-processed images are then fed to a segmentation module for segmenting the benign or malignant tumours from ultrasound images. The performance assessment of segmentation algorithm has been done quantitatively using the Jaccard index. The results of both quantitative and qualitative assessment by the radiologist indicate that the DPAD despeckle filtering algorithm yields more clinically acceptable images and results in better segmentation of benign and malignant tumours from breast ultrasound images.

Introduction Hundreds of thousands of Ontario women receive breast screening imaging each year. The patient's medical history is a vital tool used to personalize breast screening approaches. This study evaluated the accuracy of self-reported medical and imaging history in patients about to receive breast imaging procedures in a large urban Canadian hospital. The patient experience with using a blank screening form vs. a novel prefilled screening form was also evaluated. Methods and Materials The study was conducted in two phases. Phase 1 compared patient-reported information (via the blank screening form) to information previously captured in the Radiology Information and Picture Archiving Communication Systems to assess data accuracy. In phase 2, study questionnaires were used to collect data on the patients' experience with the screening form in two cohorts (between the blank and a novel prefilled screening form). Results Data accuracy: for mammography (n = 60), 40% of the patients could accurately recall when and where their last mammogram was performed. For breast ultrasound (n = 43) and breast magnetic resonance imaging (n = 20), significantly fewer patients could accurately recall the date their last test was performed (14% and 10%, respectively). Of those who had previous breast surgery (n = 18), 100% were able to recall whether the surgery resulted in a benign or malignant diagnosis, and 61% were able to accurately recall the year they had the breast surgery. Patient Experience Of the returned questionnaires, 65 provided feedback on the blank screening form while 55 provided feedback on the prefilled form. Ninety percent preferred to fill out the new prefilled screening form. The themes acknowledged a general improvement in the screening form, a decrease in frustration associated with having to recall their medical history, and the patients felt that the institution better understood their medical history. Conclusions The findings of this research indicate that asking patients to complete a blank medical screening form is a highly inaccurate method of gathering that important information. When that information was prefilled for the patient to review and update, patient frustration and stress were decreased, while satisfaction and confidence in the organization were increased.

Rationale and Objectives This study aimed to determine the average time for breast radiologists of varied experience to interpret automated breast ultrasound (ABUS) examinations. Materials and Methods A reader performance study was conducted on female patients, with ACR BI-RADS 4 breast density classifications of C or D, who received both an ABUS screening examination and a digital mammogram from 2013 to 2014 at an academic institution. Three faculty breast radiologists with varied levels of ABUS experience (advanced, intermediate, novice) read all ABUS examinations, with interpretation times and final impressions (categorized as “normal” or “abnormal”) recorded for each examination. Results Ninety-nine patients were included, with all readers demonstrating an average ABUS interpretation time of less than 3 minutes. Compared to the other two readers, the intermediate reader had a significantly longer mean interpretation time at 2.6 minutes (95% confidence interval 2.4–2.8; P Conclusions Overall, mean ABUS interpretation time by radiologists of all experience levels was short, at less than 3 minutes per examination, which should not deter radiologists from incorporating ABUS examinations into a busy clinical environment.

Breast cancer poses a great threat on women health due to its high malignant rate. In China, ultrasound screening is the commonly-used method for breast cancer diagnosis, and the localization and segmentation of the lesions in ultrasound images are helpful for breast cancer detection. In this paper, an Attention Enhanced U-net with hybrid dilated convolution (AE U-net with HDC) model was proposed and employed to segment the breast tumors in ultrasound images. First, based on Attention U-net, we added a new loss function to update the weight matrix in the AGs module, in order to enhance the weight of the lesion area. Combined with fine-tuning training method, the precision of breast ultrasound image lesion region segmentation was improved from 82.38% to 86.28% and the M-IOU was improved from 76.27% to 81.81%. Second, three groups of HDC with expansion rates of [1,2,5] were integrated into AE U-net to replace the four convolution operations. HDC module brought larger receptive field and reduced the loss of spatial information. The experimental results proved that HDC module was helpful to improve the Acc of image segmentation results from 94.18% to 95.81% and the Recall from 78.69% to 80.48%. Combined with U-net, the F1 score, AUC, Acc and M-IOU of the network proposed in this paper had significantly improved. It proved that AE U-net with HDC model would have very important research value and application prospect for modern medicine.

Introduction Heavy menstrual bleeding is the major complaint in women with symptomatic fibroids. Ulipristal acetate (UPA) is a “selective progesterone receptor modulator” in which mixed agonist and antagonist activity appears to offer a novel approach to medical management of symptomatic uterine fibroids. There are currently no studies that have assessed its effect on the mammary gland in humans. Methods Prospective observational study conducted in a tertiary hospital, in which 14 consecutive patients diagnosed with uterine fibroids by transvaginal ultrasound were included. The patients received two cycles of UPA 5 mg/day for 3 months each, with a rest period of two months between both cycles. To assess the safety on the mammary gland, 3 mammary ultrasounds were performed at three different points: prior to the first cycle of UPA, between the two cycles and at the end of the second cycle. Results Of the 14 recruited patients, 9 completed the study period. Breast ultrasound reports were normal in all patients. In 4 patients (44.4%), the 3 breast ultrasounds were classified as BI-RADS 2. In 2 patients (22.2%) the 3 breast ultrasounds were classified as BI_RADS1; and in 3 patients (33.3%), the first breast ultrasound was classified as BI-RADS 3 and the last two as BI-RADS 2. Conclusion In conclusion, our study showed that 2 cycles of treatment with UPA in patients with symptomatic uterine fibroids is safe for normal breast tissue with an acceptable adverse effects profile. Nonetheless, further research is required to confirm our findings.

Purpose To determine if real-time breast ultrasound (RTUR) after second opinion reinterpretation of submitted static ultrasound images at a comprehensive cancer center impacts clinical management, specifically by detecting additional cancer and preventing unnecessary biopsy. Materials and methods In this IRB-approved and HIPAA-compliant retrospective study, 209 patients were included who had breast ultrasound studies from outside facilities submitted for second opinion review between January 2013 and May 2014, and who subsequently underwent RTUR at our institution within three months of the outside study. Findings on submitted exams were compared with those on RTUR and disagreements between them were annotated to indicate the presence or absence of suspicious lesions and recommendation for biopsy. Changes in management were defined as any additional biopsies performed or biopsies averted after RTUR and reported as frequencies and percentages using 95% confidence intervals. Results Following RTUR, 49 additional biopsies were performed in 43/209 patients (20.6%; 95% CI 15.1–26.1%). Additional cancer was found in 12/49 (24.5%) biopsies in 11/209 patients (5.3%; 95% CI 2.2–8.2%). Forty biopsies in 31/209 (14.8%; CI 10.0–19.7%) patients originally recommended were canceled after RTUR. Overall, a change in management after RTUR was observed in 68/209 patients (32.5%; 95% CI 26.1–38.9%), including patients with either additional biopsies performed or biopsies averted. Conclusion RTUR was found to be an important tool in the management of patients at our comprehensive cancer center. Although additional false-positive lesions may be detected on RTUR, a great number of patients will benefit from RTUR in finding additional cancers or avoiding unnecessary biopsies.

This is an overview of the guidelines for breast imaging before and after aesthetic (cosmetic) breast surgery, which includes but is not limited to implants, lipomodelling and mammoplasty procedures. The guidelines are based on a review of the literature and consensus of breast imaging and aesthetic breast surgery specialists. 1. Pre-aesthetic surgery 2. Post-aesthetic surgery If breast imaging or breast assessment is required, it should be performed in a designated breast facility with access to specialist breast imaging and a complete breast multidisciplinary team in accordance with national guidelines and recommendations.

The aim of this study is to determine the impact of a simulation-based ultrasound-guided (USG) breast biopsy training session on radiology trainee procedural knowledge, comfort levels, and overall procedural confidence and anxiety.Twenty-one diagnostic radiology residents from a single academic institution were recruited to participate in an USG breast biopsy training session. The residents filled out a questionnaire before and after the training session. Ten multiple-choice questions tested general knowledge in diagnostic breast ultrasound and USG breast biopsy concepts. Subjective comfort levels with ultrasound machine and biopsy device functionality, patient positioning, proper biopsy technique, image documentation, needle safety and overall procedural confidence and anxiety levels were reported on a 5-point Likert scale before and after training.Participants demonstrated significant improvement in number of correctly answered general knowledge questions after training (P.0001). Significant improvement was seen in resident comfort level in ultrasound machine functionality, patient positioning, biopsy device functionality, biopsy technique, image documentation, as well as overall confidence level (all P.05). Participants indicated a slight but not significant reduction in anxiety levels (P = .27).A simulation-based USG breast biopsy training session may improve radiology trainee procedural knowledge, comfort levels, and overall procedural confidence.

Purpose To investigate whether combined Digital breast tomosynthesis and Automated breast volume scanner (DBT-ABVS) are comparable to Magnetic resonance imaging (MRI) in staging breast cancer. Methods We retrospectively included seventy-three patients with histologically proven breast cancer who underwent preoperative DBT, ABVS and 1.5 T MRI in the period July 2015–July 2016. Two radiologists in consensus recorded the number, site and Breast imaging-reporting and data system (BI-RADS) category of breast findings during two independent reading strategies, i.e. DBT-ABVS vs. MRI. Using histology or 1-year follow up as the standard of reference, we calculated the accuracy for cancer of both imaging strategies. Bland-Altman analysis was used to evaluate the agreement between MRI vs. DBT or ABVS in cancer size assessment. Results Patients showed a total of 160 lesions (108 malignant and 52 benign). Malignant lesions were unifocal, multifocal, multicentric and biltateral in 53, 15, 4 and 1 cases, respectively. Diagnostic accuracy of DBT-ABVS vs. MRI was comparable for all cancers (90.0% [95%C.I. 84.3–94.2] vs. 93.8% [95%C.I. 88.8–97.0], respectively). DBT-ABVS showed lower sensitivity and positive predictive values for additional disease (76.5% [95%C.I. 58.8–89.3] vs. 91.7% [95%C.I. 84.6–96.1], and 78.8% [95%C.I. 61.0–91.0] vs 93.4% [95%C.I. 86.9–97.3], respectively). Compared to MRI, ABVS + DBT missed 6 lesions, including two invasive cancers and one extensive intravascular invasion associated to ductal carcinoma in situ. Bland-Altman analysis showed ABVS to agree with MRI at a higher extent than DBT in assessing cancer size. Conclusions Though less performing than MRI, DBT-ABVS showed acceptable diagnostic accuracy in staging breast cancer. This strategy might be used if MRI is unavailable or unfeasible.

Breast cancer is considered to be one of the most threatening issues in clinical practice. However, existing breast cancer diagnosis methods face questions of complexity, cost, human-dependency, and inaccuracy. Recently, many computerized and interdisciplinary systems have been developed to avoid human errors in both quantification and diagnosis. A computerized system can be further improved to optimize the efficiency of breast tumour identification. The current paper presents an effort to automate characterization of breast cancer from ultrasound images using multi-fractal dimensions and backpropagation neural networks. In this study, a total of 184 breast ultrasound images (72 abnormal (tumour cases) and 112 normal cases) were examined. Various setups were employed to achieve a decent balance between positive and negative rates of the diagnosed cases. The obtained results manifested in high rates of precision (82.04%), sensitivity (79.39%), and specificity (84.75%).

Background Women with disabilities (WWD) have reported lower mammography rates than the general population, however rates for women with cerebral palsy (CP) have not been specifically studied. Objective To evaluate mammography rates in women with CP and to identify strengths and barriers with their screening experience. Methods Women with CP 40 years or older (n = 118) participating in a prospective cross-sectional survey were queried regarding screening status, imaging modality, and accommodation needs and availability. Categorical variables were summarized and Chi-square testing used to assess factors contributing to screening compliance. The effect of functional factors on screening was evaluated using logistic regression. Results 77 women (65.3%) had mammograms within the past two years; 56 (47.5%) were screening mammograms. Severity of fine motor deficits was associated with lack of screening (OR 0.559, p = 0.019). 85 (72.0%) experienced positive staff attitudes. Facilities most often met needs for ramps, elevators, and/or wide doorways (92.9%), exam explanations (84.4%), and accessible parking (82.5%). Needs least often met included accommodations for standing (59.3%) or for difficulties with arm/shoulder positioning (57.1%), and wheelchair-accessible mammogram machines (59.1%). Conclusions The screening compliance rate for women with CP is low, although the 2-year mammography rate is comparable to that reported for WWD and the general female U.S. population. Women were usually offered respectful care. Adequate physical accommodations during the procedure were reported less often than overall facility environmental accommodations. These findings demonstrate the need for improved screening rates in women with CP, and highlight areas for improving their screening experience.

The purpose of this retrospective study was to evaluate the effect of pre-operative planning using real-time virtual sonography (RVS), a magnetic resonance imaging (MRI)/ultrasound (US) image fusion technique on breast-conserving surgery (BCS) in patients with non-mass enhancement (NME) on breast MRI. Between 2011 and 2015, we enrolled 12 consecutive patients who had lesions with NME that exceeded the US hypo-echoic area, in which it was particularly difficult to evaluate the tumor margin. During pre-operative planning before breast-conserving surgery, RVS was used to delineate the enhancing area on the breast surface after additional supine breast MRI was performed. We analyzed both the surgical margin positivity rate and the re-operation rate. All NME lesions corresponded to the index cancer. In all patients, the diameter of the NME lesion was greater than that of the hypo-echoic lesion. The median diameters of the NME and hypo-echoic lesions were 24 mm (range: 12–39 mm) and 8.0 mm (range: 4.9–18 mm), respectively (p = 0.0002). After RVS-derived skin marking was performed on the surface of the affected breast, lumpectomy and quadrantectomy were conducted in 7 and 5 patients, respectively. The surgical margins were negative in 10 (83%) patients. Two patients with positive margins were found to have ductal carcinoma in situ in 1 duct each, 2.4 and 3.2 mm from the resection margin, respectively. None of the patients required additional resection. Although further prospective studies are required, the findings of our preliminary study suggest that it is very well possible that the use of RVS-derived skin marking during pre-operative planning for BCS in patients with NME would have resulted in surgical outcomes similar to or better than those obtained without the use of such marking.

Breast cancer is one of the leading causes of cancer death among women worldwide. In clinical routine, automatic breast ultrasound (BUS) image segmentation is very challenging and essential for cancer diagnosis and treatment planning. Many BUS segmentation approaches have been studied in the last two decades, and have been proved to be effective on private datasets. Currently, the advancement of BUS image segmentation seems to meet its bottleneck. The improvement of the performance is increasingly challenging, and only few new approaches were published in the last several years. It is the time to look at the field by reviewing previous approaches comprehensively and to investigate the future directions. In this paper, we study the basic ideas, theories, pros and cons of the approaches, group them into categories, and extensively review each category in depth by discussing the principles, application issues, and advantages/disadvantages.

We analyze the performance of a mammographically-configured, automated breast ultrasound (McABUS) scanner combined with a digital breast tomosynthesis (DBT) system. The GE Invenia ultrasound system was modified for integration with GE DBT systems. The ultrasound and DBT imaging were performed in the same mammographic compression. Our small preliminary study included thirteen cases, six of which contained invasive cancers. From analysis of these cases, current limitations and corresponding potential improvements of the system were determined. A registration analysis was performed to compare the ease of McABUS to DBT registration for this system with that of two systems designed previously. It was observed that, in comparison to data from an earlier study, the McABUS to DBT registration alignment errors for both this system and for a previously built combined system were smaller than for a previously built standalone McABUS system.

To determine the value of mammography and breast ultrasound (US) in predicting outcomes in HER2 positive breast cancer patients (pts) within Neo-ALTTO trial.Mammography and US were required at baseline, week 6 and surgery. Two independent blinded investigators reviewed the measurements and assigned the corresponding response category. Pts showing complete or partial response according to RECIST (v1.1) were classified as responders. The association between imaging response at week 6 or prior to surgery was evaluated with respect to pathological complete response (pCR) and event-free Survival (EFS).Of the 455 pts enrolled in the trial, 267 (61%) and 340 (77%) had evaluable mammography and US at week 6; 248 (56%) and 309 (70%) pts had evaluable mammography and US prior to surgery. At week 6, 32% and 43% of pts were classified as responders by mammography and US, respectively. pCR rates were twice as high for responders than non-responders (week 6: 46% versus 23% by US, p 0.0001; 41% versus 24% by mammography, p = 0.007). Positive and negative predictive values of mammography and US prior to surgery were 37% and 35%, and 82% and 70%, respectively. No significant correlation was found between response by mammography and/or US at week 6/surgery and EFS.Mammography and US were underused in Neo-ALTTO although US had the potential to assess early response whereas mammography to detect residual disease prior to surgery. Our data still emphasise the need for further imaging studies on pts treated with neoadjuvant HER2-targeted therapy.

Purpose To assess the utility and pathological results from DBT VAB for lesions occult on 2D mammography and breast ultrasound (US). Materials and methods A retrospective review of 1116 consecutive stereotactic biopsies was performed over 27 months. DBT VAB was performed for 38 non-calcified lesions which were solely detected using DBT. Imaging findings and pathology results were reviewed. Results Pathologic findings were malignant in 8 of 38 lesions [masses (5) and distortion (3)]. High-risk findings found in 14 lesions. Conclusion DBT VAB is easily performed and the majority of cases yield actionable pathologies. Therefore, perform DBT VAB primarily when available.

Background and objective Conventional computer-aided diagnosis (CAD) systems for breast ultrasound (BUS) are trained to classify pathological classes, that is, benign and malignant. However, from a clinical perspective, this kind of classification does not agree totally with radiologists’ diagnoses. Usually, the tumors are assessed by using a BI-RADS (Breast Imaging-Reporting and Data System) category and, accordingly, a recommendation is emitted: annual study for category 2 (benign), six-month follow-up study for category 3 (probably benign), and biopsy for categories 4 and 5 (suspicious of malignancy). Hence, in this paper, a CAD system based on BI-RADS categories weighted by pathological information is presented. The goal is to increase the classification performance by reducing the common class imbalance found in pathological classes as well as to provide outcomes quite similar to radiologists’ recommendations. Methods The BUS dataset considers 781 benign lesions and 347 malignant tumors proven by biopsy. Moreover, every lesion is associated to one BI-RADS category in the set {2, 3, 4, 5}. Thus, the dataset is split into three weighted classes: benign, BI-RADS 2 in benign lesions; probably benign, BI-RADS 3 and 4 in benign lesions; and malignant, BI-RADS 4 and 5 in malignant lesions. Thereafter, a random forest (RF) classifier, denoted by RFw, is trained to predict the weighted BI-RADS classes. In addition, for comparison purposes, a RF classifier is trained to predict pathological classes, denoted as RFp. Results The ability of the classifiers to predict the pathological classes is measured by the area under the ROC curve (AUC), sensitivity (SEN), and specificity (SPE). The RFw classifier obtained AUC = 0.872 , SEN = 0.826 , and SPE = 0.919 , whereas the RFp classifier reached AUC = 0.868 , SEN = 0.808 , and SPE = 0.929 . According to a one-way analysis of variance test, the RFw classifier statistically outperforms (p Conclusions The division of the classification problem into three classes reduces the imbalance between benign and malignant classes; thus, the sensitivity is increased without degrading the specificity. Therefore, the CAD based on weighted BI-RADS classes improves the classification performance of the conventional CAD systems. Additionally, the proposed approach has the advantage of being capable of providing a multiclass outcome related to radiologists’ recommendations.