PURPOSE:To develop and internally validate a super-resolution ultrasound microvascular imaging (SR-UMI) model for noninvasive preoperative prediction of sentinel lymph node (SLN) involvement in breast cancer and to assess incremental value over clinical variables. MATERIALS AND METHODS:In this prospective single-center study (January-June 2025), 162 consecutive patients with pathologically confirmed breast cancer underwent contrast-enhanced SR-UMI of the primary tumor prior to axillary surgery and SLNB. SonoVue (2.4 mL) was administered as an antecubital venous bolus. Examinations were performed on an Ultimus 9E ultrasound system using a 5-15 MHz linear transducer at low MI (0.08). Three predictor sets were evaluated: clinical-only (9 variables), SR-UMI-only (98 features), and combined (107 predictors). Elastic net-regularized logistic regression (EN-LR) was prespecified as the primary model and evaluated using nested stratified cross-validation (outer 5-fold, inner 3-fold) with pooled out-of-fold (OOF) predictions, assessing discrimination, calibration, and decision-curve analysis (DCA). RESULTS:SLN involvement was present in 55/162 patients (34.0%). EN-LR achieved AUC 0.662, PR-AUC 0.471, and Brier 0.232 for clinical-only predictors; SR-UMI-only improved performance (AUC 0.800; PR-AUC 0.572; Brier 0.185). The combined model performed similarly (AUC 0.802; PR-AUC 0.574; Brier 0.185). At the Youden operating point (threshold 0.514), the combined model yielded sensitivity 0.782, specificity 0.766, PPV 0.632, and NPV 0.872. Bootstrap OOF comparisons showed significant AUC improvements for SR-UMI-only versus clinical-only and combined vs. clinical-only, whereas combined vs. SR-UMI-only was not significant. Calibration showed a negative intercept and slope > 1 (combined: -0.637, 1.270). DCA demonstrated higher net benefit for EN-LR than treat-all/treat-none across threshold probabilities 0.05-0.60. CONCLUSION:SR-UMI microvascular features enabled good internal-validation performance and significantly improved discrimination over clinical/biopsy variables. The combined model offered no meaningful gain over SR-UMI only. External validation with recalibration is warranted.

Anterior disc displacement with reduction (ADDwR) most frequently occurs in temporomandibular joint disorder (TMD) and poses a major clinical challenge. Both botulinum toxin (BTX) and hypertonic dextrose (HD) injections have been reported for the treatment of ADDwR. However, the clinical confirmation of precise injection into the lateral pterygoid muscle and bilaminar zone is difficult. This study evaluated ultrasound-guided injection of BTX and HD for the treatment of ADDwR. Thirty patients with ADDwR received real-time ultrasound-guided injection of 30 units of BTX and 0.2 ml of 50

Understanding how the kidney adapts to microgravity is essential for safeguarding astronaut health. Although previous studies have emphasized functional alterations, direct evidence regarding renal structural or hemodynamic changes in humans under simulated microgravity remains limited. This study aimed to evaluate the short-term effects of simulated microgravity on renal macroscopic morphology and hemodynamics using portable ultrasound during a 7-day −6° head-down tilt bed rest (HDT BR) protocol. Eighteen healthy male participants underwent continuous −6° HDT BR for 7 days. Bilateral renal structural parameters (length, anteroposterior diameter, transverse diameter, volume, parenchymal and cortical thickness) and hilar Doppler parameters, including peak systolic velocity, end-diastolic velocity, time-averaged maximum velocity, time-averaged mean velocity, resistive index, pulsatility index and systolic/diastolic ratio, were assessed before and after HDT BR. Vital signs were monitored concurrently. After 7 days of HDT BR, heart rate decreased significantly, whereas diastolic blood pressure and mean arterial pressure increased (P < 0.05). However, no significant differences were observed in any renal macrostructural or hilar Doppler parameters on either side (all P > 0.05). Despite systemic cardiovascular adjustments, renal macroscopic morphology and hilar hemodynamics remained stable after 7 days of simulated microgravity. These findings suggest short-term stability of renal macrostructural and hilar hemodynamic parameters under the specific conditions studied, without detectable changes by ultrasound. This study provides human data that contribute to the understanding of renal responses under short-term simulated microgravity conditions.

Non-alcoholic fatty liver disease (NAFLD), recently redefined as metabolic dysfunction-associated steatotic liver disease (MASLD), is strongly associated with metabolic dysfunction and altered body fat distribution. However, MASLD-based reclassification was not performed due to incomplete cardiometabolic data. Transient elastography non-invasively assesses hepatic steatosis and stiffness, but its metabolic associations remain unclear. In this retrospective cross-sectional study, 238 NAFLD patients and 165 non-NAFLD controls were analyzed. Clinical, biochemical, and body composition data (bioelectrical impedance analysis) were collected. Liver steatosis (CAP) and stiffness (E value) were measured using FibroScan®. Group comparisons, correlation analyses, and multivariable regression models were performed. Logistic regression identified independent factors associated with NAFLD, and model performance was evaluated using ROC analysis. NAFLD patients showed significantly higher BMI, blood pressure, triglycerides, total cholesterol, LDL-C, and regional fat mass (including trunk and limb compartments) compared with controls (all P < 0.05). CAP was positively correlated with HbA1c, total cholesterol, and LDL-C (all P < 0.05). In multivariable analysis, total cholesterol (β = 9.26, P = 0.018) and LDL-C (β = 6.55, P = 0.021) were independently associated with CAP. Logistic regression identified sex, hypertension, BMI, LDL-C, left upper-limb fat mass, and liver stiffness as independent factors associated with NAFLD. The combined clinical model achieved the highest discriminatory performance (AUC = 0.91, 95

Ultrasound-guided Vacuum-Assisted Breast Biopsy has been widely utilized as a key modality for breast nodule resection. Nevertheless, its application remains relatively contraindicated in patients who have undergone breast prosthesis placement. This study aimed to evaluate the feasibility and safety of ultrasound‑guided vacuum‑assisted breast biopsy (US‑VABB) for the resection of breast nodules ≤ 1.5 cm with BI-RADS 3-4a in patients with retroglandular breast implants. A single-center retrospective observational study was conducted on patients with breast nodules who underwent US-VABB in the Department of Ultrasound, Beijing Friendship Hospital, Capital Medical University from January 2020 to October 2024. A total of 18 patients (18 nodules) who had previously undergone breast implant placement with implants located behind the glandular tissue were included. The complete nodule resection rate, implant-related complications, postoperative pathological results, and short-term follow-up data were analyzed. Primary outcomes included complete resection rate and implant-related complications, while secondary outcomes included pathological findings and short-term follow-up results. The maximum diameter of the nodules in the 18 patients ranged from 0.5 to 1.5 cm (mean: 1.1 ± 0.4 cm), and all nodules were completely resected in a single operation, with no evidence of residual lesions on imaging. No serious complications such as breast implant rupture or leakage occurred during or after the operation. The implant rupture rate was 0% (0/18), and minor complications occurred in 16.7% of patients. Postoperative pathology revealed fibroadenoma (n=11), breast adenosis (n=3), intraductal papilloma (n=2), atypical ductal hyperplasia (n=1), and ductal carcinoma in situ (DCIS, n=1). The patient with DCIS underwent additional resection, with no residual tumor detected. These findings demonstrate that US-VABB is a safe and feasible minimally invasive approach for patients with retroglandular breast implants presenting with breast nodules ≤1.5 cm and BI-RADS 3-4a, with high resection success and low complication rates.

OBJECTIVES:An increased gradient of alcohol intake distinguished distinct clinical outcome risks across steatotic liver disease (SLD) subcategories, including metabolic dysfunction-associated steatotic liver disease (MASLD), MASLD with increased alcohol intake (MetALD), and alcohol liver disease (ALD). However, association between alcohol intake and pre-sarcopenia risk was not studied. METHODS:All adult participants with complete data of alcohol intake, controlled transient elastography and dual-energy X-ray absorptiometry were collected from the National Health and Nutrition Examination Survey 2017-2018. The pre-sarcopenia burden was compared between SLD and non-SLD, also across SLD subcategories. Association between alcohol intake and pre-sarcopenia risk was evaluated by logistic regression and restricted cubic spline analysis. RESULTS:Among 1506 evaluable participants, there were 836 non-SLD participants, 354 MASLD, 185 MetALD, 115 ALD and 16 cryptogenic SLD participants. The prevalence of pre-sarcopenia in SLD was higher than that in non-SLD (14.93% vs. 5.02%). Regardless of sex, three SLD subcategories had the lower appendicular lean mass index than non-SLD group. The pre-sarcopenia prevalence was only higher among males in SLD subcategories than non-SLD group. An L-shaped negative nonlinear relationship between alcohol intake and pre-sarcopenia was observed in females (0-28 g/day), but not in males. Logistic regression showed physical inactivity, lower creatinine, higher weight-adjusted waist index and sex male were associated with increased pre-sarcopenia risk. CONCLUSION:Regardless of sex, MASLD, MetALD or ALD had a higher pre-sarcopenia burden than non-SLD. A nonlinear relationship between low-moderate alcohol intake and pre-sarcopenia risk was revealed in females.

Background:Accurate and noninvasive quantification of hepatic steatosis is essential for managing metabolic dysfunction-associated steatotic liver disease (MASLD). This study evaluated the diagnostic accuracy, spatial stability, and clinical correlates of ultrasound-derived fat fraction (UDFF) in MASLD patients. Methods:In this prospective study of an Asian population, we enrolled 109 patients with MASLD and 20 healthy controls. UDFF was measured across hepatic segments V-VIII, with the mean value (UDFF mean) calculated. Magnetic resonance imaging-proton density fat fraction (MRI-PDFF) served as the reference standard. Diagnostic performance, agreement, and determinants were assessed using receiver operating characteristic (ROC) curves, Bland-Altman analysis, and multivariable regression. Results:UDFF mean increased stepwise with MRI-PDFF-defined steatosis grades (P<0.0001). The areas under the curve (AUCs) for detecting ≥S1, ≥S2, and S3 steatosis were 1.00, 0.99, and 0.99, respectively. Optimal cut-off values were 5.09%, 11.18%, and 18.46%. UDFF demonstrated excellent reproducibility with an intraclass correlation coefficient (ICC) of 0.98 and showed no significant systematic bias on Bland-Altman analysis. Alanine aminotransferase (ALT), gamma-glutamyl transferase (GGT), age, and sex were independently associated with UDFF (all P<0.05). Conclusions:UDFF provides a stable and accurate ultrasound-based assessment of hepatic fat burden in MASLD, with excellent agreement with MRI-PDFF and high spatial reproducibility, supporting its clinical utility for noninvasive risk stratification and longitudinal monitoring.

BACKGROUND:Graft fibrosis is a critical pathological endpoint of chronic injury after liver transplantation (LT). While serum-based scores are validated in native liver diseases, their efficacy in LT recipients remains controversial. This study compared the diagnostic performance of shear wave elastography (SWE) with common serological indices (APRI, FIB-4, GPR) for detecting significant graft fibrosis (≥S2) in adult and pediatric recipients. METHODS:We retrospectively analyzed 111 LT recipients (63 adults, 48 children) who underwent liver biopsy and concurrent SWE/biochemical testing. Fibrosis was staged by the Scheuer classification. Diagnostic accuracy was evaluated using Spearman correlation and receiver operating characteristic (ROC) curves, stratified by recipient and graft age. RESULTS:SWE demonstrated the strongest correlation with histological fibrosis stage (ρ = 0.76, p < 0.001), significantly outperforming all serological indices. For the detection of significant fibrosis, SWE achieved an AUC of 0.927 (95% CI: 0.879-0.975), superior to GPR (0.759), APRI (0.691), and FIB-4 (0.594). Notably, FIB-4 showed no significant correlation with fibrosis (ρ = -0.02, p = 0.818). SWE maintained high diagnostic accuracy across adult and pediatric recipients, with optimal cut-off values of 10.14 kPa and 10.92 kPa. Moreover, SWE exhibited stable performance across different graft ages, whereas serological indices showed marked variability in the early post-transplant period. CONCLUSION:SWE provides a superior and more stable assessment of graft fibrosis compared to conventional serological models in both adult and pediatric LT recipients. Given its high NPV, SWE serves as a robust first-line tool for long-term non-invasive graft surveillance.

To develop and evaluate a multiclass deep neural network model that utilizes preoperative ultrasound features to recommend the most suitable surgical approach for patients with papillary thyroid microcarcinoma (PTMC), thereby providing empirical guidance for surgical method selection and promoting personalized treatment strategies. Data from a cohort of 1,434 cN0 PTMC patients from Beijing Friendship Hospital, Capital Medical University were retrospectively analysed. After dataset standardization, bootstrap resampling and recursive feature elimination (RFE) were performed to identify robust predictors (selected in > 90

Objective: To enhance the diagnostic accuracy of new nodules on the surgical side after breast cancer surgery using machine learning techniques and to explore the role of multifeature fusion. Methods: Data from 137 breast cancer postoperative patients with new nodules from January 2016 to April 2024 were analyzed. Clinical, ultrasound, immunohistochemistry, and surgical features were combined. Multiple machine learning models, including support vector machine (SVM), random forest, gradient boosting, AdaBoost, and XGBoost, were trained and tested. Model performance was evaluated using stratified ten-fold cross-validation. Ablation experiments assessed the impact of different feature combinations on diagnostic performance. Results: The SVM model performed best, with an AUC of 0.8664, an accuracy of 0.8099, a sensitivity of 0.565, and a specificity of 0.9267. Ablation experiments indicated that multifeature fusion significantly improved diagnostic performance, especially when combining clinical, ultrasound, immunohistochemistry, and surgical features. Gradient boosting and random forest models showed slightly inferior performance, while AdaBoost had balanced but lower effectiveness. Conclusion: Machine learning, particularly the multifeature fusion SVM model, shows significant potential in diagnosing new nodules after breast cancer surgery. It can assist doctors in developing more effective treatment plans, improving patient outcomes. Future studies should expand sample sizes, include multicenter data, and explore advanced algorithms to further enhance diagnostic performance.

OBJECTIVES:This study aimed to develop and validate machine-learning (ML) models that integrate ultrasonic radiofrequency (RF) time-series signals with gray-scale image features for the preoperative differentiation of breast lesions classified as category 4A of the Breast Imaging Reporting and Data System. METHODS:A dataset comprising RF signals, 2D ultrasound features, and pathological diagnoses from 130 BI-RADS 4A lesions (128 patients) was analyzed. Five ML models (logistic regression [LR], support vector machine [SVM], k-nearest neighbor [k-NN], and gradient boosting [GB]) were evaluated. RESULTS:Among 31 features (28 RF-derived and 5 2D image features), 6 key features were selected through feature selection. The LR model achieved the highest area under the curve (0.81, 95% confidence interval: 0.66-1.00), though no statistically significant differences were observed among models (DeLong test, p > .05). Artificial intelligence-assisted diagnosis improved accuracy across physician seniority levels (p < .05): junior (≤3 years: 52.28% versus baseline 27.28%), intermediate (4-10 years: 79.54% versus 45.46%), and senior (≥10 years: 81.91% versus 63.63%). CONCLUSION:The integration of RF time series and 2D features via LR demonstrates potential to reduce unnecessary biopsies by enhancing diagnostic precision, particularly for less experienced clinicians.

Dobutamine, an inotropic agent, is known to enhance cardiac function. However, its concurrent effects on cervical artery hemodynamics and cerebral microcirculation, along with their potential correlation, remain unclear. This study aimed to investigate these relationships in healthy volunteers under dobutamine stress. In this self-controlled study, cervical artery hemodynamic parameters, including vessel diameters, peak systolic velocity, end-diastolic velocity (EDV), mean flow velocity (MV), resistance index and pulsatility index of cervical arteries parameters of 20 healthy volunteers were obtained via ultrasound. Whole-brain cerebral blood flow (wCBF_ASL) and cerebral blood flow in regions of interest (CBF_ROI) were obtained by magnetic resonance imaging using arterial spin labeling before and during the dobutamine stress test. Blood flow (BF) in the cervical arteries were calculated from the MV and the vessel diameter. Ultrasound-derived cerebral blood flow (CBF_US) was defined as the sum of the BF from the left and right internal carotid arteries (ICA) and the vertebrobasilar artery. Overall cerebral blood flow, measured by both CBF_US and wCBF_ASL, remained unchanged during dobutamine stress (P > 0.05). However, dobutamine induced significant reductions in CBF_ROI in specific regions, including the right middle temporal pole, left middle temporal pole, and left cerebellum (P < 0.05). Notably, linear regression analysis revealed that the change in EDV of the right internal carotid artery (ICA-R) was a significant positive predictor of the CBF change in the right middle temporal pole (B = 0.32, p = 0.042). Dobutamine administration can induce regional cerebral hypoperfusion despite stable global cerebral blood flow. Alterations in ICA hemodynamic parameters are correlated with these regional perfusion deficits. These findings suggest that monitoring cervical artery hemodynamics during dobutamine administration may offer insights into regional cerebral perfusion changes, and could potentially be explored as a complementary tool for risk stratification in patients undergoing dobutamine stress tests.

OBJECTIVE:To investigate the diagnostic value of quantitative analysis using ultra-resolution microscopy (URM) in differentiating benign from malignant breast lesions. MATERIAL AND METHODS:This prospective study enrolled 60 patients with 60 breast lesions who underwent contrast-enhanced ultrasound (CEUS) using SonoVue (Bracco Imaging, Italy) between June 2024 and August 2024. Quantitative parameters of microvascular density and velocity maps were generated for the lesion interior, rim region, and combined interior and rim area using URM software on CEUS images. The parameters were analyzed for differences between benign and malignant breast lesions, and their diagnostic efficacy was evaluated. RESULTS:Multivariate analysis indicated that breast malignancy was associated with microvascular ratio and complexity level. The area under the curve (AUC) for the combined diagnostic method that included microvascular parameters at the lesion margin (Rim group) and BI-RADS classification + Rim was higher than other diagnostic approaches (AUC = 0.92), although there was no significant difference when compared with the combined approach of evaluating parameters within the lesion and at the margin alongside BI-RADS (Mass + Rim + BI-RADS group, P = .293). The BI-RADS group showed high sensitivity (100%) and negative predictive value (100%); the Mass group (parameters within the lesion) demonstrated higher sensitivity (87.0%), and the Rim group (parameters at the lesion margin) exhibited the highest specificity (91.9%). CONCLUSION:URM shows potential in distinguishing between benign and malignant breast lesions, offering a precise assessment of lesion hemodynamics and providing valuable information for clinical diagnosis and treatment.

OBJECTIVE:The relationship between liver health and glycaemic control in elderly patients with diabetes remains poorly understood. In this study, the value of liver elastography in identifying associations with poor glycaemic control among elderly patients with type 2 diabetes mellitus was investigated. SUBJECTS AND METHODS:In total, 90 elderly patients (aged ≥ 60 years) with type 2 diabetes mellitus were enrolled in this prospective observational study. All participants underwent liver elastography using FibroScan® and continuous glucose monitoring (CGM). Liver stiffness measurements (LSMs) and the controlled attenuation parameter (CAP) were obtained. Glycaemic control was assessed through multiple parameters, including the time in range (TIR), time above range (TAR), glycaemic variability, and mean glucose levels. Poor glycaemic control was defined as a TIR < 70%. The mean age of the participants was 64.0 ± 10.5 years, with 65.6% being female. The mean liver stiffness was 6.1 ± 7.8 kPa, and the mean CAP was 266.0 ± 54.7 dB/m. RESULTS:Patients with higher liver stiffness (>8.0 kPa) had a significantly lower TIR (68.7% versus 83.5%, p<0.001) than those with normal liver stiffness (<5.5 kPa). LSMs were strongly negatively correlated with the TIR (r = -0.42, p < 0.001) and positively correlated with the mean glucose level (r = 0.38, p < 0.001). Multivariate analysis revealed that increased liver stiffness was independently associated with poor glycaemic control (adjusted OR = 1.28, 95% CI: 1.14-1.44; p < 0.001). CONCLUSION:ROC analysis revealed an exploratory LSM cut-off value of 6.8 kPa for association with poor glycaemic control (AUC = 0.76; sensitivity = 71.2%; specificity = 78.9%). LSMs via transient elastography are independently associated with poor glycaemic control in elderly patients with type 2 diabetes. An LSM threshold of 6.8 kPa may help identify patients who are more likely to present with poor glycaemic control.

This study aims to explore the capability of raw radiofrequency (RF) information in the diagnosis of the severity of Metabolic Dysfunction-Associated Steatotic Liver Disease (MASLD), especially its effectiveness in differentiating patients with varying severity of fatty liver disease. The study included patients from the Beijing Friendship Hospital affiliated with the Capital Medical University, comprising 49 with mild fatty liver, 59 with moderate or severe fatty liver. categorized based on the magnetic resonance imaging (MRI) criteria. RF features were extracted from raw RF signal data using envelope statistics and spectral parameter calculation methods. In the data preprocessing stage, median imputation was used for handling missing values, and features were standardized. For feature selection, the Recursive Feature Elimination (RFE) method combined with the logistic regression model was used to select key features from all standardized features. During the model construction phase, a logistic regression model was used for training. For model evaluation and testing, a 100-times random sampling iteration method was used to calculate the average values and 95 This study indicates that combining RF information with logistic regression effectively diagnoses varying severities of fatty liver disease, offering a valuable clinical reference through careful feature selection and model evaluation.

ObjectiveTo predict post-thyroidectomy complications in papillary thyroid microcarcinoma (PTMC) patients using a deep learning model based on preoperative ultrasonographic features. This study addresses the global rise in PTMC incidence and the challenges in treatment decision-making with high-resolution ultrasonography.MethodThis study enrolled 1638 patients with clinically staged cN0 PTMC who received surgical treatment from 1997 to 2019 at Beijing Friendship Hospital. Deep learning model was developed using fully connected neural network. Feature selection included 1000 iterations of Bootstrap sampling and Recursive Feature Elimination (RFE) to identify the top 10 features. Data preprocessing involved normalization and imputation for missing values. SMOTE addressed class imbalance. The model was trained and tested on random data split, with performance metrics including Accuracy (ACC), Area Under the Curve (AUC), Sensitivity (SEN), and Specificity (SPE), visualized through a ROC curve and confusion matrix.ResultsThe fully connected deep neural network model demonstrated high accuracy (ACC 0.81), Area Under the Curve (AUC 0.74), sensitivity (SEN 0.65), and specificity (SPE 0.83) and visualized by ROC curve and confusion matrix. These results highlight the model's reliability and potential as an effective tool in predicting postoperative complications and assisting in clinical decision-making for PTMC patients.ConclusionThis study highlights the potential of deep learning in enhancing medical predictions and personalized healthcare. Despite promising results, limitations include a single-center data source and unconsidered factors like lifestyle and genetics. Future research should expand data sources, include more influencing factors, and refine algorithms to improve accuracy and applicability in thyroid cancer treatment. Our study underscores the potential of artificial intelligence, particularly artificial neural networks, in enhancing medical predictions. This AI model has the capability of forecast postoperative complications in cases of papillary thyroid microcarcinoma by analyzing preoperative ultrasonographic features, and demonstrated promising accuracy and reliability. This research paves the way for AI's more profound impact on personalized healthcare and surgical risk assessment. image

Background The status of axillary lymph nodes (ALN) plays a critical role in the management of patients with breast cancer. It is an urgent demand to develop highly accurate, non-invasive methods for predicting ALN status Purpose To evaluate the efficacy of ultrasound radiofrequency (URF) time-series parameters, in combination with clinical data, in predicting ALN metastasis in patients with breast cancer. Material and Methods We prospectively gathered clinicopathologic and ultrasonic data from patients diagnosed with breast cancer. Various machine-learning (ML) models were developed using all available features to determine the most efficient diagnostic model. Subsequently, distinct prediction models were created using the optimal ML model, and their diagnostic performances were evaluated and compared. Results The study encompassed 240 patients, of whom 88 had lymph node metastases. A leave-one-out cross-validation (LOOCV) method was used to split the entire dataset into training and testing subsets. The random forest ML model outperformed the other algorithms, with an area under the curve (AUC) of 0.92. Prediction models based on clinical, ultrasonic, URF parameters, clinical + ultrasonic, clinical + URF, and ultrasonic + URF parameters had AUCs of 0.56, 0.79, 0.78, 0.90, 0.80, and 0.84, respectively, in the testing set. The comprehensive diagnostic model (clinical + ultrasonic + URF parameters) demonstrated strong diagnostic capability, with an AUC of 0.94 in the testing set, exceeding any single prediction model. Conclusion The combined model (clinical + ultrasonic + URF parameters) could be used preoperatively to predict lymph node status, offering valuable input for the design of individualized surgical approaches.

Background Metabolic dysfunction-associated fatty liver disease (MAFLD) is the most common chronic liver disease in the world and carries an increased risk of liver-related events, but no approved medicine. Electroacupuncture has been used to treat non-alcoholic fatty liver disease, but its effect was uncertain because of the poor quality of prior studies. We designed this trial to evaluate the efficacy and safety of electroacupuncture for MAFLD.Methods/design This is a multicentre, randomised, sham acupuncture-controlled, patient-blinded clinical trial. Participants will take part in a total of 20 weeks of study, containing three phases: a 4-week run-in period, 12-week treatment (36 sessions of acupuncture) and 4-week follow-up. A total of 144 eligible patients diagnosed with MAFLD will be randomly allocated to the electroacupuncture or sham acupuncture groups. The primary outcome is the percentage of relative liver fat reduction on the MRI proton density fat fraction from baseline to 12 weeks. Secondary outcomes include magnetic resonance elastography, liver and metabolic biomarkers, anthropometry parameters, blinding assessment, credibility and expectancy, and adverse events. All patients who receive randomisation will be included in the intent-to-treat analysis.Discussion The finding of this trial will provide evidence of the efficacy and safety of electroacupuncture for the treatment of MAFLD. The results of this study will be published in peer-reviewed journals.Trial registration number www.chictr.org.cn, ChiCTR2200060353. It was registered on 29 May 2022.

OBJECTIVE:The aim of the work described here was to investigate the feasibility and diagnostic value of using contrast-enhanced ultrasound (CEUS) galactography with SonoVue in patients with pathologic nipple discharge (PND).METHODS:Twenty-eight patients who underwent breast surgery for PND from May 2019 to August 2021 were included. Routine ultrasound, ductoscopy and CEUS galactography were performed successively. Lesions were diagnosed and localized. The sensitivity, specificity and pre-operative localization value of each examination method were evaluated on post-operative pathology.RESULTS:CEUS galactography was successfully conducted in all 28 patients and revealed negative ductal ectasia, filling stop and filling defect. Ductoscopy revealed positive nodules in 21 cases and negative nodules in 7 cases. A total of 18 nodules were found by routine ultrasound, and the relationship between all nodules and the discharge duct was confirmed after CEUS galactography. Compared with the other two methods, CEUS galactography had higher sensitivity, positive predictive value and negative predictive value (100%, 81.82% and 100%, respectively), while it has the same specificity as routine ultrasound (both 60%). The pre-operative location of the nipple duct was consistent with the intra-operative findings in 28 patients after CEUS galactography.CONCLUSION:The ultrasound contrast agent SonoVue can be used for CEUS galactography in patients with PND. CEUS galactography can improve the detection of ductal nodules and locate the nipple discharge duct pre-operatively. As the technique does not emit radiation and SonoVue is easily metabolized and safe, CEUS galactography is better than conventional imaging for PND patients.

Early ultrasound screening for breast cancer reduces mortality significantly. The main evaluation criterion for breast ultrasound screening is the Breast Imaging-Reporting and Data System (BI-RADS), which categorizes breast lesions into categories 0-6 based on ultrasound grayscale images. Due to the limitations of ultrasound grayscale imaging, lesions with categories 4 and 5 necessitate additional biopsy for the confirmation of benign or malignant status. In this paper, the SAE-Net was proposed to combine the tissue microstructure information with the morphological information, thus improving the identification of high-grade breast lesions. The SAE-Net consists of a grayscale image branch and a spectral pattern branch. The grayscale image branch used the classical deep learning backbone model to learn the image morphological features from grayscale images, while the spectral pattern branch is designed to learn the microstructure features from ultrasound radio frequency (RF) signals. Our experimental results show that the best SAE-Net model has an area under the receiver operating characteristic curve (AUROC) of 12% higher and a Youden index of 19% higher than the single backbone model. These results demonstrate the effectiveness of our method, which potentially optimizes biopsy exemption and diagnostic efficiency.