Customised weight-based volume contrast media protocol for multiphase abdominal computed tomography.

INTRODUCTION: Multiphase computed tomography (CT) using fixed volume contrast media may lead to high radiation exposure and toxicity in patients with low body weight. We evaluated a customised weight-based protocol for multiphase CT in terms of radiation exposure, image quality and cost savings. METHODS: A total of 224 patients were recruited. An optimised CT protocol was applied using 100 kV and 1 mL/kg of contrast media dosing. The image quality and radiation dose exposure of this CT protocol were compared to those of a standard 120 kV, 80 mL fixed volume protocol. The radiation dose information and CT Hounsfield units were recorded. The signal-to-noise ratio, contrast-to-noise ratio (CNR) and figure of merit (FOM) were used as comparison metrics. The images were assessed for contrast opacification and visual quality by two radiologists. The renal function, contrast media volume and cost were also evaluated. RESULTS: The median effective dose was lowered by 16% in the optimised protocol, while the arterial phase images achieved significantly higher CNR and FOM. The radiologists' evaluation showed more than 97% absolute agreement with no significant differences in image quality. No significant differences were found in the pre- and post-CT estimated glomerular filtration rate. However, contrast media usage was significantly reduced by 1,680 mL, with an overall cost savings of USD 421 in the optimised protocol. CONCLUSION: The optimised weight-based protocol is cost-efficient and lowers radiation dose while maintaining overall contrast enhancement and image quality.

Artificial Intelligence-Guided Segmentation and Path Planning Software for Transthoracic Lung Biopsy.

PURPOSE: To validate the sensitivity and specificity of a 3-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) software for lung lesion detection and to establish concordance between AI-generated needle paths and those used in actual biopsy procedures. MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories. RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60). CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.

Radioport: a radiomics-reporting network for interpretable deep learning in BI-RADS classification of mammographic calcification.

Objective.Generally, due to a lack of explainability, radiomics based on deep learning has been perceived as a black-box solution for radiologists. Automatic generation of diagnostic reports is a semantic approach to enhance the explanation of deep learning radiomics (DLR).Approach.In this paper, we propose a novel model called radiomics-reporting network (Radioport), which incorporates text attention. This model aims to improve the interpretability of DLR in mammographic calcification diagnosis. Firstly, it employs convolutional neural networks to extract visual features as radiomics for multi-category classification based on breast imaging reporting and data system. Then, it builds a mapping between these visual features and textual features to generate diagnostic reports, incorporating an attention module for improved clarity.Main results.To demonstrate the effectiveness of our proposed model, we conducted experiments on a breast calcification dataset comprising mammograms and diagnostic reports. The results demonstrate that our model can: (i) semantically enhance the interpretability of DLR; and, (ii) improve the readability of generated medical reports.Significance.Our interpretable textual model can explicitly simulate the mammographic calcification diagnosis process.

Natural language processing in narrative breast radiology reporting in University Malaya Medical Centre.

Radiology reporting is narrative, and its content depends on the clinician's ability to interpret the images accurately. A tertiary hospital, such as anonymous institute, focuses on writing reports narratively as part of training for medical personnel. Nevertheless, free-text reports make it inconvenient to extract information for clinical audits and data mining. Therefore, we aim to convert unstructured breast radiology reports into structured formats using natural language processing (NLP) algorithm. This study used 327 de-identified breast radiology reports from the anonymous institute. The radiologist identified the significant data elements to be extracted. Our NLP algorithm achieved 97% and 94.9% accuracy in training and testing data, respectively. Henceforth, the structured information was used to build the predictive model for predicting the value of the BIRADS category. The model based on random forest generated the highest accuracy of 92%. Our study not only fulfilled the demands of clinicians by enhancing communication between medical personnel, but it also demonstrated the usefulness of mineable structured data in yielding significant insights.

A Radiomics Study: Classification of Breast Lesions by Textural Features from Mammography Images.

This study investigates the feasibility of using texture radiomics features extracted from mammography images to distinguish between benign and malignant breast lesions and to classify benign lesions into different categories and determine the best machine learning (ML) model to perform the tasks. Six hundred and twenty-two breast lesions from 200 retrospective patient data were segmented and analysed. Three hundred fifty radiomics features were extracted using the Standardized Environment for Radiomics Analysis (SERA) library, one of the radiomics implementations endorsed by the Image Biomarker Standardisation Initiative (IBSI). The radiomics features and selected patient characteristics were used to train selected machine learning models to classify the breast lesions. A fivefold cross-validation was used to evaluate the performance of the ML models and the top 10 most important features were identified. The random forest (RF) ensemble gave the highest accuracy (89.3%) and positive predictive value (66%) and likelihood ratio of 13.5 in categorising benign and malignant lesions. For the classification of benign lesions, the RF model again gave the highest likelihood ratio of 3.4 compared to the other models. Morphological and textural radiomics features were identified as the top 10 most important features from the random forest models. Patient age was also identified as one of the significant features in the RF model. We concluded that machine learning models trained against texture-based radiomics features and patient features give reasonable performance in differentiating benign versus malignant breast lesions. Our study also demonstrated that the radiomics-based machine learning models were able to emulate the visual assessment of mammography lesions, typically used by radiologists, leading to a better understanding of how the machine learning model arrive at their decision.

Microaxial Left Ventricular Assist Device in Cardiogenic Shock: A Systematic Review and Meta-Analysis.

Microaxial left ventricular assist devices (LVAD) are increasingly used to support patients with cardiogenic shock; however, outcome results are limited to single-center studies, registry data and select reviews. We conducted a systematic review and meta-analysis, searching three databases for relevant studies reporting on microaxial LVAD use in adults with cardiogenic shock. We conducted a random-effects meta-analysis (DerSimonian and Laird) based on short-term mortality (primary outcome), long-term mortality and device complications (secondary outcomes). We assessed the risk of bias and certainty of evidence using the Joanna Briggs Institute and the GRADE approaches, respectively. A total of 63 observational studies (3896 patients), 6 propensity-score matched (PSM) studies and 2 randomized controlled trials (RCTs) were included (384 patients). The pooled short-term mortality from observational studies was 46.5% (95%-CI: 42.7-50.3%); this was 48.9% (95%-CI: 43.8-54.1%) amongst PSM studies and RCTs. The pooled mortality at 90 days, 6 months and 1 year was 41.8%, 51.1% and 54.3%, respectively. Hemolysis and access-site bleeding were the most common complications, each with a pooled incidence of around 20%. The reported mortality rate of microaxial LVADs was not significantly lower than extracorporeal membrane oxygenation (ECMO) or intra-aortic balloon pumps (IABP). Current evidence does not suggest any mortality benefit when compared to ECMO or IABP.

MRI Breast: Current Imaging Trends, Clinical Applications, and Future Research Directions.

Magnetic Resonance Imaging (MRI) is the most sensitive and advanced imaging technique in diagnosing breast cancer and is essential in improving cancer detection, lesion characterization, and determining therapy response. In addition to the dynamic contrast-enhanced (DCE) technique, functional techniques such as magnetic resonance spectroscopy (MRS), diffusion-weighted imaging (DWI), diffusion kurtosis imaging (DKI), and intravoxel incoherent motion (IVIM) further characterize and differentiate benign and malignant lesions thus, improving diagnostic accuracy. There is now an increasing clinical usage of MRI breast, including screening in high risk and supplementary screening tools in average-risk patients. MRI is becoming imperative in assisting breast surgeons in planning breast-conserving surgery for preoperative local staging and evaluation of neoadjuvant chemotherapy response. Other clinical applications for MRI breast include occult breast cancer detection, investigation of nipple discharge, and breast implant assessment. There is now an abundance of research publications on MRI Breast with several areas that still remain to be explored. This review gives a comprehensive overview of the clinical trends of MRI breast with emphasis on imaging features and interpretation using conventional and advanced techniques. In addition, future research areas in MRI breast include developing techniques to make MRI more accessible and costeffective for screening. The abbreviated MRI breast procedure and an area of focused research in the enhancement of radiologists' work with artificial intelligence have high impact for the future in MRI Breast.

Predicting Treatment Outcomes in Rapid Syllable Transition Treatment: An Individual Participant Data Meta-Analysis.

PURPOSE: The purpose of this study is to identify predictors of treatment outcomes in Rapid Syllable Transition Treatment (ReST) for childhood apraxia of speech through an individual participant data meta-analysis. METHOD: A systematic literature search identified nine ReST studies for inclusion. Individual participant data were obtained, and studies were coded for methodological design, baseline participant characteristics, service delivery factors, and treatment outcomes. Bivariate analyses were conducted to identify potential predictor variables. Multiple linear regressions were then performed to identify predictors of treatment outcomes. RESULTS: Data for 36 participants from seven studies were included in the statistical analyses. In multivariate modeling, better performance on treated pseudowords posttreatment was predicted by higher baseline expressive language and Goldman-Fristoe Test of Articulation scores, lower speech inconsistency and percentage of vowels correct, and higher pretreatment accuracy on pseudoword targets. Better performance on untreated real words posttreatment was predicted by higher pretreatment accuracy on real words. Gains in performance and retention of gains were not significantly predicted by any individual variable or combination of variables. CONCLUSIONS: Baseline speech and expressive language skills and accuracy on pseudowords and real words were significant predictors of absolute posttreatment performance. Regardless of baseline characteristics, all children were statistically as likely to achieve gains during ReST and retain these gains for up to 4 weeks posttreatment. Large-scale prospective research is required to further examine the effects of dose frequency and co-occurring language impairments on treatment outcomes and the complex co-effects of percentage of vowels correct with other potential predictors. SUPPLEMENTAL MATERIAL: https://doi.org/10.23641/asha.19611714.

Comparing catheter related bloodstream infection rate between cuffed tunnelled and non-cuffed tunnelled peripherally inserted central catheter.

OBJECTIVE: To compare catheter related blood stream infection (CRBSI) rate between cuffed tunnelled and non-cuffed tunnelled PICC. METHODS: We prospectively followed 100 patients (50:50 cuffed and non-cuffed PICC) and compared CRBSI rate between these groups. Daily review and similar catheter care were performed until a PICC-related complication, completion of therapy, death or defined end-of-study date necessitate removal. CRBSI was confirmed in each case by demonstrating concordance between isolates colonizing the PICC at the time of infection and from peripheral blood cultures. RESULTS: A total of 50 cuffed PICC were placed for 1864 catheter-days. Of these, 12 patients (24%) developed infection, for which 5 patients (10%) had a CRBSI for a rate of 2.7 per 1000 catheter-days. Another 50 tunnelled non-cuffed PICCs were placed for 2057 catheter-days. Of these, 7 patients (14%) developed infection, for which 3 patients (6%) had a CRBSI. for a rate of 1.5 per 1000 catheter-days. The mean time to development of infection is 24 days in cuffed and 19 days in non-cuffed groups. The mean duration of utilization was significantly longer in non-cuffed than in cuffed group (43 days in non-cuffed vs 37 days in cuffed group, p = 0.008). CONCLUSIONS: Cuffed PICC does not further reduce the rate of local or bloodstream infection. Tunnelled non-cuffed PICC is shown to be as effective if not better at reducing risk of CRBSI and providing longer catheter dwell time compared to cuffed PICC.

Diagnostic Accuracy of Shear Wave Elastography as an Adjunct Tool in Detecting Axillary Lymph Nodes Metastasis.

OBJECTIVES: This study evaluates the diagnostic performance of shear wave elastography (SWE) in differentiating between benign and axillary lymph node (ALN) metastasis in breast carcinoma. MATERIALS AND METHODS: Breast lesions and axillae of 107 patients were assessed using B-mode ultrasound and SWE. Histopathology was the diagnostic gold standard. RESULTS: In metastatic axillary lymph nodes, qualitative SWE using color patterns had the highest area under curve (AUC) value, followed by B-mode Ultrasound (cortical thickening >3 mm) and quantitative SWE using Emax of 15.2 kPa (AUC of 81.3%, 70.1%, and 61.2%, respectively). Qualitative SWE exhibited better diagnostic performance than the other two parameters, with sensitivity of 96.0% and specificity of 56.1%. Combination of B-mode Ultrasound (using cortical thickness of >3 mm as cut-off point) and qualitative SWE (Color patterns of 2 to 4) showed sensitivity of 71.6%, specificity of 95%, PPV of 96%, NPV of 66.7%, and accuracy of 80.4%. CONCLUSION: Qualitative SWE assessment exhibited higher accuracy compared to quantitative values. Qualitative SWE as an adjunct to B-mode ultrasound can further improve the diagnostic accuracy of metastatic ALN in breast cancer.

Automatic COVID-19 Detection Using Exemplar Hybrid Deep Features with X-ray Images.

COVID-19 and pneumonia detection using medical images is a topic of immense interest in medical and healthcare research. Various advanced medical imaging and machine learning techniques have been presented to detect these respiratory disorders accurately. In this work, we have proposed a novel COVID-19 detection system using an exemplar and hybrid fused deep feature generator with X-ray images. The proposed Exemplar COVID-19FclNet9 comprises three basic steps: exemplar deep feature generation, iterative feature selection and classification. The novelty of this work is the feature extraction using three pre-trained convolutional neural networks (CNNs) in the presented feature extraction phase. The common aspects of these pre-trained CNNs are that they have three fully connected layers, and these networks are AlexNet, VGG16 and VGG19. The fully connected layer of these networks is used to generate deep features using an exemplar structure, and a nine-feature generation method is obtained. The loss values of these feature extractors are computed, and the best three extractors are selected. The features of the top three fully connected features are merged. An iterative selector is used to select the most informative features. The chosen features are classified using a support vector machine (SVM) classifier. The proposed COVID-19FclNet9 applied nine deep feature extraction methods by using three deep networks together. The most appropriate deep feature generation model selection and iterative feature selection have been employed to utilise their advantages together. By using these techniques, the image classification ability of the used three deep networks has been improved. The presented model is developed using four X-ray image corpora (DB1, DB2, DB3 and DB4) with two, three and four classes. The proposed Exemplar COVID-19FclNet9 achieved a classification accuracy of 97.60%, 89.96%, 98.84% and 99.64% using the SVM classifier with 10-fold cross-validation for four datasets, respectively. Our developed Exemplar COVID-19FclNet9 model has achieved high classification accuracy for all four databases and may be deployed for clinical application.

Desmoid Type Fibromatosis of the Breast Masquerading as Breast Carcinoma: Value of Dynamic Magnetic Resonance Imaging and Its Correlation.

Desmoid type fibromatosis of the breast is a rare stromal tumor that accounts for <0.2% of all breast tumors. Bilateral and multicentric lesions are extremely rare, with only less than ten cases reported in the literature. Although benign, it is locally aggressive with frequent recurrence in up to almost one-third of the cases. We experienced our first case of bilateral multicentric breast fibromatosis in a 19-year-old woman, with a paternal aunt diagnosed with breast cancer at age 30, who presented to our institution with the chief complaint of retracted nipples for 1 year. The patient denied any history of trauma to her chest. Sonography showed suspicious bilateral hypoechoic masses. Magnetic resonance imaging (MRI) was performed for further evaluation because of the extensive involvement of both the breasts. This report aimed to illustrate the main clinical, radiological, and histopathological characteristics of this rare disease to increase awareness of this entity and discuss the role of MRI.

Semi-supervised GAN-based Radiomics Model for Data Augmentation in Breast Ultrasound Mass Classification.

BACKGROUND AND OBJECTIVE: The capability of deep learning radiomics (DLR) to extract high-level medical imaging features has promoted the use of computer-aided diagnosis of breast mass detected on ultrasound. Recently, generative adversarial network (GAN) has aided in tackling a general issue in DLR, i.e., obtaining a sufficient number of medical images. However, GAN methods require a pair of input and labeled images, which require an exhaustive human annotation process that is very time-consuming. The aim of this paper is to develop a radiomics model based on a semi-supervised GAN method to perform data augmentation in breast ultrasound images. METHODS: A total of 1447 ultrasound images, including 767 benign masses and 680 malignant masses were acquired from a tertiary hospital. A semi-supervised GAN model was developed to augment the breast ultrasound images. The synthesized images were subsequently used to classify breast masses using a convolutional neural network (CNN). The model was validated using a 5-fold cross-validation method. RESULTS: The proposed GAN architecture generated high-quality breast ultrasound images, verified by two experienced radiologists. The improved performance of semi-supervised learning increased the quality of the synthetic data produced in comparison to the baseline method. We achieved more accurate breast mass classification results (accuracy 90.41%, sensitivity 87.94%, specificity 85.86%) with our synthetic data augmentation compared to other state-of-the-art methods. CONCLUSION: The proposed radiomics model has demonstrated a promising potential to synthesize and classify breast masses on ultrasound in a semi-supervised manner.

Customised weight-based volume contrast media protocol in CT of chest, abdomen and pelvis examination.

INTRODUCTION: Fixed volume (FV) contrast media administration during CT examination is the standard practice in most healthcare institutions. We aim to validate a customised weight-based volume (WBV) method and compare it to the conventional FV methods, introduced in a regional setting. METHODS: 220 patients underwent CT of the chest, abdomen and pelvis (CAP) using a standard FV protocol, and subsequently, a customised 1.0 mL/kg WBV protocol within one year. Both image sets were assessed for contrast enhancement using CT attenuation at selected regions-of-interest (ROIs). The visual image quality was evaluated by three radiologists using a 4-point Likert scale. Quantitative CT attenuation was correlated with the visual quality assessment to determine the HU's enhancement indicative of the image quality grades. Contrast media usage was calculated to estimate cost-savings from both protocols. RESULTS: Mean patient age was 61 ± 14 years, and weight was 56.1 ± 8.7 kg. FV protocol produced higher contrast enhancement than WBV, p < 0.001. CT images' overall contrast enhancement was negatively correlated with body weight for FV protocol while the WBV protocol produced more consistent enhancement across different body weight. More than 90% of the images from both protocols were graded "Excellent". WBV protocol also enabled a 28% cost reduction with cost savings of US$1238. CONCLUSION: The customised WBV protocol produced CT images which were comparable to FV protocol for CT CAP examinations. A median CT value of 100 HU can be an indicator of good image quality for the WBV protocol.

Primary Breast Angiosarcoma: Utilisation of Pre-surgical Magnetic Resonance Imaging (MRI) for Accurate Tumour Characterization and Planning - A Case Report and Literature Review.

BACKGROUND: Primary breast angiosarcoma is a rare malignancy with non-specific clinical and radiological findings. CASE REPORT: A 30-year-old lady presented with left breast pain and lumpiness for over one year. She has had several breast ultrasounds (US) and was treated for acute mastitis and abscess. Subsequently, in view of the rapid growth of the lump and worsening pain, she was re-investigated with US, elastography, digital breast tomosynthesis (DBT) and MRI. MRI raised the suspicion of angiosarcoma. The diagnosis was confirmed after biopsy and she underwent mastectomy. DISCUSSION: Literature review on imaging findings of breast angiosarcoma, especially on MRI, is discussed. MRI features showed heterogeneous low signal intensity on T1 and high signal intensity on T2. Dynamic contrast enhancement (DCE) features included either early enhancement with or without washout in the delayed phase, and some reported central areas of non-enhancement. CONCLUSION: This case report emphasises on the importance of MRI in clinching the diagnosis of breast angiosarcoma, and hence, should be offered sooner to prevent diagnostic delay.

Evaluation of automated volumetric breast density software in comparison with visual assessments in an Asian population: A retrospective observational study.

This study aims to compare Quantra, as an automated volumetric breast density (Vbd) tool, with visual assessment according to ACR BI-RADS density categories and to determine its potential usage in clinical practice.Five hundred randomly selected screening and diagnostic mammograms were included in this retrospective study. Three radiologists independently assigned qualitative ACR BI-RADS density categories to the mammograms. Quantra automatically calculates the volumetric density data into the system. The readers were blinded to the Quantra and other readers assessment. Inter-reader agreement and agreement between Quantra and each reader were tested. Region under the curve (ROC) analysis was performed to obtain the cut-off value to separate dense from a non-dense breast. Results with P value <.05 was taken as significant.There were 40.4% Chinese, 27% Malays, 19% Indian and 3.6% represent other ethnicities. The mean age of the patients was 57. 15%, 45.6%, 30.4%, and 9% of patients fall under BI-RADS A, B, C and D density category respectively. Fair agreement with Kappa (κ) value: 0.49, 0.38, and 0.30 were seen for Reader 1, 2 and 3 versus Quantra. Moderate agreement with κ value: 0.63, 0.64, 0.51 was seen when the data were dichotomized (density A and B to "non-dense", C and D to "dense"). The cut-off Vbd value was 13.5% to stratify dense from non-dense breasts with a sensitivity of 86.2% and specificity of 83.1% (AUC 91.4%; confidence interval: 88.8, 94.1).Quantra showed moderate agreement with radiologists visual assessment. Hence, this study adds to the available evidence to support the potential use of Quantra as an adjunct tool for breast density assessment in routine clinical practice in the Asian population. We found 13.5% is the best cut-off value to stratify dense to non-dense breasts in our study population. Its application will provide an objective, consistent and reproducible results as well as aiding clinical decision-making on the need for supplementary breast ultrasound in our screening population.

Shear wave elastography for characterization of breast lesions: Shearlet transform and local binary pattern histogram techniques.

Shear wave elastography (SWE) examination using ultrasound elastography (USE) is a popular imaging procedure for obtaining elasticity information of breast lesions. Elasticity parameters obtained through SWE can be used as biomarkers that can distinguish malignant breast lesions from benign ones. Furthermore, the elasticity parameters extracted from SWE can speed up the diagnosis and possibly reduce human errors. In this paper, Shearlet transform and local binary pattern histograms (LBPH) are proposed as an original algorithm to differentiate malignant and benign breast lesions. First, Shearlet transform is applied on the SWE images to acquire low frequency, horizontal and vertical cone coefficients. Next, LBPH features are extracted from the Shearlet transform coefficients and subjected to dimensionality reduction using locality sensitivity discriminating analysis (LSDA). The reduced LSDA components are ranked and then fed to several classifiers for the automated classification of breast lesions. A probabilistic neural network classifier trained only with seven top ranked features performed best, and achieved 98.08% accuracy, 98.63% sensitivity, and 97.59% specificity in distinguishing malignant from benign breast lesions. The high sensitivity and specificity of our system indicates that it can be employed as a primary screening tool for faster diagnosis of breast malignancies, thereby possibly reducing the mortality rate due to breast cancer.

Shearwave Elastography Increases Diagnostic Accuracy in Characterization of Breast Lesions.

The purpose of this study was to investigate the diagnostic efficacy of shearwave elastography (SWE) in differentiating between benign and malignant breast lesions.One hundred and fifty-nine lesions were assessed using B-mode ultrasound (US) and SWE parameters were recorded (Emax, Emean, Emin, Eratio, SD). SWE measurements were then correlated with histopathological diagnosis.The final sample contained 85 benign and 74 malignant lesions. The maximum stiffness (Emax) with a cutoff point of ≥ 56.0 kPa (based on ROC curves) provided sensitivity of 100.0%, specificity of 97.6%, positive predictive value (PPV) of 97.4%, and negative predictive value (NPV) of 100% in detecting malignant lesions. A cutoff of ≥80 kPa managed to downgrade 95.5% of the Breast Imaging-Reporting and Data System (BI-RADS) 4a lesions to BI-RADS 3, negating the need for biopsy. Using a combination of BI-RADS and SWE, the authors managed to improve the PPV from 2.3% to 50% in BI-RADS 4a lesions.SWE of the breast provides highly specific and sensitive quantitative values that are beneficial in the characterization of breast lesions. Our results showed that Emax is the most accurate value for differentiating benign from malignant lesions.