REVIEW ARTICLE

Research Progress on Ultrasound Radiomics in Preoperative Prediction of Axillary Lymph Node Metastasis in Breast Cancer

Gao Yuanjing, Niu Zihan, Luo Yanwen, Zhou Mengyuan, Xiao Mengsu, Jiang Yuxin, Zhu Qingli

2026, 10 (2): 79-89. DOI:10.26599/AUDT.2026.250066

Abstract ( 28 ) HTML ( 9 ) PDF ( 527KB ) ( 35 ) 　　

Axillary lymph node (ALN) metastasis is a critical factor influencing prognosis and treatment strategies in breast cancer patients. However, traditional methods—ranging from physical examination to ultrasound—often lack the precision required for clinical decision-making. In recent years, ultrasound radiomics and deep learning have emerged as promising solutions, leveraging high-throughput quantitative features from ultrasound images to enhance detection accuracy. This review explores the development and application of radiomics and deep learning across multiple ultrasound modalities (grayscale, elastography, and contrast-enhanced ultrasound), as well as in multimodal imaging approaches that integrate ultrasound with MRI and PET/CT, underscoring the benefits of incorporating clinicopathological variables to boost predictive performance. These studies provide a vital foundation for personalized treatment and precision medicine in breast cancer management.

Use of Artificial Intelligence in Fetal Brain Ultrasound Examination: A review

Cui Yuanjie, Guo Cuixia, Li Zhen, Zhang Juan, Wu Yuting, Wu Qingqing, Sun Lijuan

2026, 10 (2): 90-97. DOI:10.26599/AUDT.2026.250061

Abstract ( 24 ) HTML ( 4 ) PDF ( 289KB ) ( 21 ) 　　

Ultrasound has become the primary modality for fetal central nervous system examination and diagnosing malformations. However, the effectiveness of fetal brain examinations remains highly operator-dependent. Deep learning, a key branch of artificial intelligence (AI), has demonstrated significant advantages in image recognition, proving particularly valuable in medical imaging. Consequently, several studies have proposed the use of deep learning models as tools for fetal brain ultrasound examinations. AI has achieved clinical applications in fetal brain ultrasonography, encompassing standard plane recognition, biometric measurements, structural identification, and malformation diagnosis. This review systematically analyzes the applications of AI in fetal brain ultrasound examination and discusses unmet clinical needs and future development.

ORIGINAL RESEARCH

RiskFactors for Bleeding in Patients Undergoing Ultrasound-guided Tube Thoracostomy: A Retrospective Study of 4073 Patients

Li Wenqing, Jing Haoyu, Zhang Huiping, Bao Rui, Yang Zhen, Luo Yukun, Zhang Mingbo

2026, 10 (2): 98-105. DOI:10.26599/AUDT.2026.250068

Abstract ( 17 ) HTML ( 2 ) PDF ( 580KB ) ( 19 ) 　　

Background US-guided tube thoracostomy (US-TT) is widely employed for pleural effusion management, however bleeding complications remain a clinical concern.
Objective To identify risk factors for bleeding during US-TT, focusing on doctor experience, coagulation status, malignancy, and anticoagulant/antiplatelet medication use.
Methods In this retrospective cohort study, we analyzed 4,073 patients undergoing US-TT between January 2019 and January 2024. Using univariate analysis and multivariate binary logistic regression, we evaluated associations between post-procedural bleeding and the following factors: coagulation parameters (PLT, INR, APTT), inflammatory markers, use of anticoagulant/antiplatelet medications, malignancy status, and doctor experience (junior vs. senior). Demographic and clinical data were extracted from electronic medical records.
Results Bleeding occurred in 24 patients (0.6%). Univariate analysis identified procedure performance by junior physicians and presence of malignancy as significant risk factors (P < 0.05). No significant associations were found with coagulation parameters, inflammatory markers, or medication use. Factors with P < 0.1 (junior doctor, malignancy, INR > 2.0, elevated leukocyte count) were included in multivariate analysis. This confirmed junior doctor status (OR, 3.333; P = 0.033) and malignancy (OR, 3.960; P = 0.016) as independent predictors of bleeding.
Conclusions US-TT carries a low overall bleeding risk (0.6%). In this study, bleeding was associated with malignancy and less experienced doctors, but not significantly with routine coagulation indices. A trend toward increased risk with INR > 2.0 warrants caution.

Quality Control Analysis of Normal Breast Imaging using a Remote Ultrasound Robot

Ma Yutong, Chen Yingying, Jiancan Renqing, Ma Xiuzhu, Zhang Yun, Dang Xiaochu, Wang Xuejuan, Zhang Zhanlei, Lv Faqin

2026, 10 (2): 106-111. DOI:10.26599/AUDT.2026.250069

Abstract ( 18 ) HTML ( 1 ) PDF ( 846KB ) ( 22 ) 　　

Objective To explore the quality control value of 5G remote ultrasound robot in normal breast imaging.
Methods Fifty female volunteers from Xizang were selected to undergo routine breast examinations using 5G remote ultrasound robot (robot group) and on-site ultrasound (control group). Longitudinal and transverse continuous scanning methods were used to collect and save images respectively. The two groups of images were scored for breast imaging quality by five senior attending physicians or above using a blind method according to the Likert scale grading standard. The paired t-test was used to analyze the differences in breast imaging quality scores obtained by five physicians between the two examination methods and the age differences between the two groups of volunteers. The Kappa test was used to analyze the consistency of the image scoring results between the two groups. The χ² test was used to analyze the ethnic differences between the two groups of volunteers.
Results There is no significant age difference between the two groups of volunteers (t = −0.850, P = 0.101, P > 0.05). There is no significant difference in the ethnic proportions between the two groups of volunteers (P = 1.00, P > 0.05). There was no statistically significant difference in the scores of the five physicians between the two groups of images (P > 0.05), Doctor A (t = −1.647, P = 0.101), Doctor B (t = −0.943, P = 0.347), Doctor C (t = 0.582, P = 0.561), Doctor D (t = 0.040, P = 0.958), Doctor E (t = 0.144, P = 0.886). The consistency of the scoring results of the five doctors on the two groups of images was good (Kappa = 0.789, 0.753, 0.807, 0.778, 0.823, P < 0.001).
Conclusion The remote ultrasound robot has good consistency with the on-site ultrasound imaging quality. The remote ultrasound robot can be used for breast cancer screening in special environments such as high altitude and cold weather.

Evaluating the Diagnostic Performance of Sound Touch Elastography, Visco-elastography, and Sound Attenuation in Chronic Liver Diseases Detection

Mo Sijie, Ding Zhimin, Huang Zhibin, Wang Mengyun, Xu Jinfeng, Zhang Hongan, Dong Fajin

2026, 10 (2): 112-122. DOI:10.26599/AUDT.2026.250108

Abstract ( 24 ) HTML ( 1 ) PDF ( 2459KB ) ( 15 ) 　　

Objectives This study aims to explore the diagnostic effectiveness of sound touch elastography (STE), visco-elastography, and ultrasound attenuation analysis (USAT) in some chronic liver diseases (CLDs).
Materials and Methods From February 1st to September 30th, 2023, participants underwent multiple examinations on the same day, including sound touch elastography (STE), visco-elastography, ultrasound attenuation analysis (USAT), FibroScan-VCTE, and FibroScan-CAP. Statistical analysis utilized t-tests and rank sum tests to compare differences between the hepatic fibrosis and non-hepatic fibrosis groups, the hepatocellular injury state and non-hepatocellular injury state groups, and the fatty liver and non-fatty liver groups. The ROC curve of sound touch elastography, visco-elastography, and ultrasound attenuation analysis was calculated to obtain cut-off values, area under the curve, and corresponding sensitivity and specificity values.
Results This study comprised 310 patients, with age, height, alanine aminotransferase, ultrasound attenuation analysis, and FibroScan-CAP identified as significant variables for liver fibrosis, hepatocellular injury state, and non-alcoholic fatty liver disease. The determined cut-off values for sound touch elastography, visco-elastography, and ultrasound attenuation analysis were 8.09 (7.30-9.17), 1.62 (1.49-1.74), and 0.68 (0.59-0.68), respectively. Based on these cut-off values, preliminary diagnoses can be made for seven different types of chronic liver diseases.
Conclusion The combination of sound touch elastography, visco-elastography, and ultrasound attenuation analysis demonstrates strong reliability for early screening and diagnosis of chronic liver diseases, encompassing liver fibrosis, non-alcoholic fatty liver, and hepatocellular injury state.

CASE REPORT

Water-Air Sequential Infusion Assisted Ultrasound-Guided Percutaneous Gastrostomy in a Patient with Complete Esophageal Obstruction

Mu Zhengqing, Feng Ru, Yang Muyang, Zhou Qin, Xu Changsong, Xie Rui

2026, 10 (2): 123-126. DOI:10.26599/AUDT.2026.250117

Abstract ( 20 ) HTML ( 3 ) PDF ( 3300KB ) ( 14 ) 　　

Objective To evaluate the feasibility and safety of water–air sequential infusion assisted Ultrasound-Guided Percutaneous Gastrostomy (UGPG) in a patient with complete esophageal obstruction.
Methods A 72-year-old male patient with esophageal squamous cell carcinoma presented with complete esophageal obstruction and severe malnutrition. Endoscopic and fluoroscopic gastrostomy were not feasible, and the patient was unable to tolerate general anesthesia. A purely ultrasound-guided percutaneous gastrostomy was performed. The procedure consisted of initial infusion of a small volume of normal saline into the gastric antrum to facilitate identification of the gastric lumen and placement of a pigtail drainage catheter, followed by continuous air insufflation through the catheter to achieve adequate gastric distension and close apposition of the anterior gastric wall to the abdominal wall. Under real-time ultrasound guidance, gastric wall fixation and gastrostomy tube placement were successfully completed.
Results The procedure was completed smoothly with satisfactory gastric distension and a clear, safe puncture pathway. The gastrostomy tube was accurately positioned, and no perioperative complications, including bleeding, infection, or peritonitis, were observed. Enteral nutrition was initiated 24 hours after the procedure and was well tolerated.
Conclusion Water–air sequential infusion–assisted UGPG is a feasible and safe alternative for gastrostomy in patients with complete esophageal obstruction who are unsuitable for endoscopic or fluoroscopic approaches. This radiation-free, minimally invasive technique avoids the need for general anesthesia and may represent a valuable option for high-risk or critically ill patients. Further studies with larger sample sizes are warranted to validate its clinical utility.