Journal of Ultrasound in Medicine最新文献

Objectives: The unavoidable pressure at the ultrasound transducer-skin interface leads to a decrease in the accuracy of superficial blood flow visualization. To achieve high-resolution skin superficial blood flow ultrasound imaging, this study introduces a novel solid hydrogel coupling medium designed to overcome issues of inaccurate blood flow caused by probe pressure and near-field acoustic interference.

Methods: A solid hydrogel coupling pad, SA-PAM (sodium alginate and acrylamide), was fabricated and its mechanical characterization was performed using tensile testing. The superficial blood flow ultrasound imaging was tested under varying pressure conditions using ultrasound localization microscopy (ULM) combined with long-lasting microbubble contrast agents on rat dorsal skin.

Results: The hydrogel coupling medium demonstrated superior acoustic coupling performance, reducing near-field interference and improving imaging quality. Compared with conventional liquid coupling agents, the SA-PAM hydrogel significantly enhanced the visualization of microvascular structures in both the dermis and subcutaneous layers, even under applied pressure. Three-dimensional super-resolution ultrasound imaging revealed detailed microvascular flow, with improved continuity and higher vessel density at deeper skin layers.

Conclusions: The SA-PAM hydrogel coupling pad offers a novel solution for ultrasound imaging of superficial skin blood flow, providing high-resolution vascular imaging of the skin and reduced image distortion caused by probe pressure. This strategy has promising potential for early detection of diabetes-related microvascular lesions and for the precise monitoring of inflammatory skin diseases, thereby it would support clinical treatment planning and therapeutic evaluation.

Objectives: To evaluate the diagnostic value of a machine learning (ML) model based on multi-modal ultrasound features in differentiating benign from malignant cervical lymph nodes, and to provide a visual interpretation of model decisions using shapley additive explanations (SHAP).

Methods: This retrospective study included 190 patients with suspected cervical lymph node lesions who obtained a pathological result at the Fourth Affiliated Hospital of Harbin Medical University between August 2022 and January 2025. All patients underwent 2D ultrasound, color Doppler flow imaging (CDFI), microvascular flow imaging (MVFI), and contrast-enhanced ultrasound (CEUS). Clinical data (age and sex) and multi-modal ultrasound features were collected. Univariate analysis was used to identify variables significantly associated with lymph node malignancy. Ten ML algorithms were developed and compared to construct predictive models. Model performance was evaluated using multiple metrics such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and F1 score. The SHAP framework was applied to interpret the decision-making process of the optimal model.

Results: Univariate analysis identified 18 features significantly associated with malignancy, including age, short axis, L/S ratio, morphology, cortical thickness, cortical echogenicity, calcification, cystic change, hyperechoic foci, reticular/cord-like echogenicity, hilum visibility, CDFI vascular pattern, pulsatility index (PI), MVFI vascular pattern, vascularity index (VI), CEUS enhancement pattern, enhancement uniformity, and necrotic regions. Among the 10 ML algorithms, the gradient boosting machine (GBM) model achieved the best diagnostic performance, with an AUC of 0.987 (95% CI: 0.967-1.000), accuracy of 0.929, sensitivity of 0.879, specificity of 0.965, and F1 score of 0.935 on the test set. The GBM model significantly outperformed an experienced ultrasound physician (AUC = 0.904, p = .03). SHAP interpretation revealed that the most influential features for prediction included CEUS enhancement pattern, L/S ratio, age, PI, and VI. The case-based analysis further demonstrated that malignant lymph nodes were commonly associated with a combination of centripetal heterogeneous enhancement on CEUS, L/S <2, presence of hyperechoic foci, mixed-type vascularity on MVFI, and elevated VI values.

Conclusion: The GBM model based on multi-modal ultrasound features enables accurate differentiation between benign and malignant cervical lymph nodes. SHAP provides a transparent, visual interpretation of model decisions, demonstrating a novel methodological framework that integrates multi-modal data with explainable AI, supporting its potential as a reliable tool for clinical decision-making.

Objectives: Fetal growth restriction (FGR), commonly caused by placental insufficiency, is a critical obstetric condition requiring accurate and timely detection to mitigate adverse outcomes. Placental sonoelastography, an advanced ultrasound technique that evaluates tissue stiffness, has emerged as a promising tool for assessing placental health.

Methods: A systematic review and meta-analysis was conducted following PRISMA guidelines to evaluate the usefulness of placental elastography in FGR. We performed a comprehensive search of PubMed, Embase, Scopus, and Web of Science up to January 2025 for in-vivo studies comparing placental elastography in the FGR and healthy control groups. Data from the included studies were pooled using random-effects models to calculate standardized mean differences (SMD) and mean differences (MD) in placental stiffness. Additionally, correlation coefficients were pooled, and diagnostic accuracy metrics, including sensitivity and specificity, were synthesized using a bivariate random-effects model.

Results: A total of 14 studies were included in the systematic review. The meta-analysis revealed significantly increased placental stiffness in FGR pregnancies. For Young's modulus, the pooled analysis of 9 studies yielded an SMD of 2.51 (95% CI: 0.72-4.30). For shear wave velocity, the pooled analysis of 6 studies revealed an SMD of 1.55 (95% CI: 0.83-2.28). Significant heterogeneity was noted in these analyses. Pooled data from 3 studies demonstrated a significant negative correlation between placental stiffness and birth weight (r = -0.453). The diagnostic accuracy, assessed from 4 studies, was high, with a pooled sensitivity of 92.0% and specificity of 98.9%.

Discussion: Placental sonoelastography stands out as a powerful, non-invasive technique that could significantly enhance the clinical assessment and surveillance of pregnancies at risk for FGR, potentially leading to more timely and effective interventions. This quantitative measure not only distinguishes FGR cases from healthy pregnancies with high accuracy but also correlates with meaningful neonatal outcomes.

Objectives: To compare the application value of 4-dimensional hysterosalpingo-contrast sonography (4D-HyCoSy) and x-ray hysterosalpingography (HSG) in intrauterine insemination (IUI) patients.

Methods: In this retrospective study, a total of 725 infertile patients who underwent IUI in Ganzhou Maternal and Child Health Hospital from January 2023 to June 2024 were divided into 2 groups based on the type of salpingography: 535 cases in the HSG group and 190 cases in the 4D-HyCoSy group. The clinical pregnancy rates, the number of IUI cycles required to achieve clinical pregnancy, and the incidence of adverse pregnancy outcomes were compared between the 2 groups.

Results: There were no significant differences in baseline data between the HSG group and the 4D-HyCoSy group. The clinical pregnancy rates were 19.43% for the HSG group and 17.89% for the 4D-HyCoSy group (p = 0.66). The number of IUI cycles required to achieve clinical pregnancy was 1.55 ± 0.65 for the HSG group and 1.62 ± 0.79 for the 4D-HyCoSy group (p = 0.65). The ectopic pregnancy rates were 2.8% for the HSG group and 2.9% for the 4D-HyCoSy group (p = 0.43). The biochemical pregnancy rates were 1.9% for the HSG group and 1.6% for the 4D-HyCoSy group (p = 0.42). The early miscarriage rates were 11.5% for the HSG group and 14.7% for the 4D-HyCoSy group (p = 0.63). No significant differences were found in any of these parameters.

Conclusion: The type of salpingography HSG and 4D-HyCoSy do not affect the clinical pregnancy outcomes in IUI. Therefore, it is recommended that HSG be phased out in favor of adopting 4D-HyCoSy as the first-line diagnostic test for tubal patency in pre-IUI evaluation.

Objectives: The primary objective of this prospective study was to identify the predictive value of the extent of absent end diastolic flow (AEDF) (T_a/T_total ratio) for the adverse perinatal outcome (APO) in growth-restricted fetuses with AEDF.

Methods: In this prospective study, a novel parameter T_a/T_total ratio, was measured in fetal growth-restricted (FGR) Fetuses with AEDF in the umbilical artery (UA) Doppler between 26 and 34 weeks. All pregnancies were monitored throughout gestation and continued to be followed up till neonatal period for any APO. Ta represents the duration of AEDF, and T_tot denotes the total duration of the cardiac cycle (T_total) in the UA Doppler, which was recorded at the last examination before delivery.

Results: Seventy-eight FGR fetuses with AEDF were included in the study. Mean gestational age (GA) at delivery, T_a/T_total ratio, and mean birth weight were 30.40 ± 4.02 weeks, 0.30 ± 0.10, and 992.82 ± 373.82 grams, respectively. Stillbirths 19 (25%) and neonatal deaths 6 (8%) were reported. T_a/T_total ratio cut-off of 0.42 predicted APO with 96% specificity, 82% positive predictive value (PPV), and 76% negative predictive value (NPV), though sensitivity was 36% (area under ROC curve, 0.70 [0.57-0.82], p < .001).

Conclusions: In fetuses with AEDF with normal DV Doppler, the extent of absent flow for ≥42% of the total cardiac cycle length might predict the risk of APO with high specificity and PPV.

Objectives: Pelvic congestion syndrome (PCS) is a prevalent but underdiagnosed cause of chronic pelvic pain. Venography remains the diagnostic reference, yet its invasiveness limits routine use. This study evaluated standardized duplex ultrasound and developed a scoring system to guide selective, evidence-based venographic referral.

Methods: In this prospective diagnostic-accuracy study, 60 women with chronic pelvic pain underwent standardized transabdominal and transvaginal duplex ultrasound, and 40 subsequently underwent selective venography as the reference standard. Ultrasound parameters included venous diameter, evoked caudal flow duration, flow direction, velocity, bilaterality, and myometrial plexus enlargement. Penalized logistic regression with bootstrap-nested cross-validation identified independent predictors of venography-confirmed PCS. Coefficients were converted into a point-score to classify patients into rule-out, indeterminate, and rule-in bands. Diagnostic performance, calibration, and decision-curve analyses were used to evaluate discrimination and clinical utility across probability thresholds.

Results: Venography confirmed PCS in 26 of 40 participants (65%). A 6-mm diameter threshold provided optimal diagnostic balance (sensitivity 92.3%, specificity 64.3%). The penalized model retained diameter, reflux ≥1.0 second, low velocity ≤3 cm/second, Valsalva-evoked caudal flow, myometrial plexus enlargement, and bilaterality, achieving an optimism-corrected AUC of 0.861. The derived score stratified patients into rule-out, indeterminate, and rule-in groups with high predictive accuracy (positive predictive value 93.3%, negative predictive value 91.7%). Decision-curve analysis showed higher net benefit than treat-all or treat-none strategies.

Conclusion: Standardized duplex ultrasound integrating morphologic and hemodynamic parameters accurately identified venographic PCS and enabled selective triage. The validated score supports ultrasound as an effective, noninvasive first-line tool to optimize venography and guide patient-centered management.