上肢关节（腕关节、肘关节、肩关节）肌骨超声基本切面实操讲解视频，每个关节包括6个切面，分别如下：

腕关节切面1：腕背侧腔室Lister结节定位切面

腕关节切面2：尺侧腕伸肌腱短轴切面

腕关节切面3：第1和第2腔室伸肌腱切面

腕关节切面4：腕管正中神经短轴切面

腕关节切面5：手指屈肌腱长轴切面

腕关节切面6：手指屈肌腱短轴切面

肘关节切面1：伸肌总腱长轴切面

肘关节切面2：屈肌总腱长轴切面

肘关节切面3：尺侧副韧带前束长轴切面

肘关节切面4：正中神经短轴切面

肘关节切面5：桡神经短轴切面

肘关节切面6：尺神经短轴切面

肩关节切面1：肱二头肌肌腱短轴切面

肩关节切面2：肩胛下肌腱长轴切面

肩关节切面3：冈上肌腱长轴切面

肩关节切面4：冈上肌腱短轴切面

肩关节切面5：冈下肌腱长轴切面

肩关节切面6：关节后隐窝切面

下肢关节（踝关节、膝关节、髋关节）肌骨超声基本切面实操讲解视频，每个关节包括6个切面，分别如下：

踝关节切面1：踝关节前隐窝切面

踝关节切面2：内踝踝管切面

踝关节切面3：内踝胫距后韧带切面

踝关节切面4：外踝距腓前韧带切面

踝关节切面5：跟腱长轴切面

踝关节切面6：足底跖腱膜长轴切面

膝关节切面1：髌上囊和股四头肌腱长轴切面

膝关节切面2：髌腱长轴切面

膝关节切面3：内侧副韧带长轴切面

膝关节切面4：股二头肌腱长轴切面

膝关节切面5：外侧副韧带长轴切面

膝关节切面6：腘窝短轴切面、腓肠肌内侧头与半膜肌腱间滑囊

髋关节切面1：梨状肌长轴切面

髋关节切面2：臀下坐骨神经短轴切面

髋关节切面3：坐骨结节腘绳肌腱短轴切面

髋关节切面4：股骨大转子短轴切面

髋关节切面5：髋关节前隐窝长轴切面

髋关节切面6：股外侧皮神经短轴切面

This article systematically explores the key aspects of quality control in reproductive andrology ultrasound, integrating the clinical expertise of Peking University Third Hospital with the latest guidelines from the European Society of Urogenital Radiology Scrotal and Penile Imaging Working Group.Unlike routine scrotal ultrasound, which primarily evaluates tumors, inflammation, and other pathologies,reproductive andrology ultrasound focuses on diagnosing male infertility, with particular emphasis on anatomical abnormalities and disorders of spermatogenic and sperm transport pathways.This paper elaborates on standardized examination protocols, including equipment parameter settings, probe selection (primarily high-frequency linear array probes), and standardized scanning protocols for the scrotum, penis, and transrectal prostate.Requirements for image documentation using 2D, color Doppler, and spectral Doppler imaging are detailed, covering testicular volume measurement, varicocele assessment, and erectile dysfunction testing.Furthermore, the article proposes standardized image and reporting guidelines, emphasizing the enhancement of diagnostic accuracy through scientific quality control to meet clinical needs in reproductive medicine.This paper provides practical guidance for optimizing reproductive andrology ultrasound workflows and reducing missed diagnoses and misdiagnoses, and holds significant clinical reference value.

Objective

To explore the application value of deep learning algorithms in quality control of the 11 standard fetal cardiac views.

Methods

Images of fetal echocardiography were collected from seven hospitals, of which a total of 35331 images were selected from fetuses between 20 and 34 weeks of gestation.Based on the 11 standard fetal cardiac views recommended by fetal echocardiography guidelines, a novel automatic quality control method integrating transformer-based techniques was proposed to assess image quality.Using expert evaluation as the reference standard, the collected images were divided into two datasets: dataset A (24 000 images) for model training, and dataset B (11 331 images) for both deep learning-based prediction and manual quality assessment by two physicians with five years of clinical experience.Average precision (AP) was used as the primary metric to evaluate model performance.

Results

The transformer-based automatic quality control method achieved an AP of 0.885 in recognizing anatomical structures in fetal cardiac views, demonstrating accurate identification of key anatomical features required in standard fetal echocardiography.The deep learning model processed each image in approximately 0.028 seconds, while the two experienced physicians took an average of 3.77 seconds per image.Thus, the deep learning-based approach was 134.6 times faster than manual evaluation.

Conclusion

The application of deep learning models for quality control of fetal echocardiographic views can achieve expert-level performance while significantly reducing the time required for manual quality assessment.

【视频简介】超声医学作为临床诊疗的“可视化听诊器”，其质量控制（简称质控）体系正从传统图像评价向覆盖设备校准、操作规范、诊断标准及报告追溯的全流程管理转变。然而，基层操作差异、多模态数据整合不足以及人工审核滞后仍是主要挑战。

人工智能（artificial intelligence，AI）技术的融合为解决这些问题带来了突破。在诊断环节，AI 驱动的标准切面识别技术显著提升了图像获取的准确性和规范性，可有效辅助基层医师；多模态病灶分析系统则优化了甲状腺结节、卵巢肿瘤等疾病的鉴别能力，减少了不必要的穿刺和转诊。在质控流程方面，结构化报告智能审核提升了诊断一致性和效率；实时操作监控系统能即时纠正探头轨迹等操作偏差；多模态数据融合分析也提升了疾病诊断的特异性。此外，国家级AI 质控平台通过整合多中心数据，有效提升了产科筛查等场景的图像质量和达标率，并推动了乳腺超声等领域的基层诊断规范化；针对盆底超声、胎儿畸形筛查等单病种的质控也实现了精准化提升。

然而，AI 超声质控的广泛应用仍面临模型适应性、设备兼容性、医师角色适应、数据隐私安全及系统可解释性等挑战。应对策略包括增强模型适应性、推动标准化、建立人机协同机制以及加强安全保障。未来，AI 将与新兴技术进一步融合，构建贯穿诊疗全流程的智能质控生态。国家质控平台需在政策、标准和产学研协同中发挥核心作用，推动AI 超声质控从“能用”向“好用”演进，实现超声诊疗的高质量、同质化发展。

Objective

To compare the sonographic and clinicopathological characteristics of ovarian granulosa cell tumors （GCTs） and ovarian thecoma-fibroma group （OTFG） of tumors.

Methods

A retrospective analysis was conducted on 136 patients （42 GCTs and 94 OTFG tumors） with pathologically confirmed diagnoses between January 2015 and September 2024 from Guangdong Women and Children Hospital.Clinical manifestations， sonographic features， and laboratory indicators were compared.Receiver operating characteristic curve was plotted to analyze the sensitivity， specificity， and area under the curve （AUC） of anti-Müllerian hormone（AMH） in diagnosing GCT.Cochran Armitage trend test was used to analyze the correlation between tumor diameter， pelvic and peritoneal fluid accumulation， and carbohydrate antigen 125 （CA125）.

Results

The GCT group comprised 36 adult-type GCTs （85.71%， 36/42） and 6 juvenile-type GCTs （14.29%， 6/42）.The OTFG group included 59 fibrothecomas （62.77%， 59/94）， 32 fibromas （34.04%， 32/94）， and 3 thecomas （3.19%， 3/94）.OTFG tumors predominantly presented as solid hypoechoic masses （90.43%， 85/94） with posterior acoustic attenuation（86.17%， 81/94） and low vascularity （grades 1-2： 94.68%， 89/94）.In contrast， GCTs mainly manifested as cysticsolid （57.14%， 24/42） or heterogeneous solid masses （35.71%， 15/42） without posterior attenuation， with abundant vascularity （grades 3-4： 88.09%， 37/42）.In the OTFG group， tumor diameter showed a significant positive correlation with ascites and elevated CA125 levels （P＜0.001）； all three cases with Meigs syndrome had tumors ＞10 cm and elevated CA125.In the GCT group， tumor diameter was only associated with elevated CA125 （P＜0.05）.The incidences of clinical symptoms （83.33% vs 57.45%）， hormonal abnormalities （50.00% vs 12.20%）， and elevated AMH levels（80.00% vs 0） were significantly higher in the GCT group compared to the OTFG group （P=0.003， ＜0.001， and ＜0.001，respectively）.AMH demonstrated a sensitivity of 0.80， specificity of 1.00， and an AUC of 0.90 for diagnosing GCT（P＜0.001）.

Conclusion

OTFG tumors and GCTs exhibit distinct sonographic， clinical， and laboratory characteristics.Ultrasonography combined with AMH testing provides a reliable preoperative diagnostic framework for ovarian sex cord-stromal tumors.

Objective

To explore the application value of the plan-do-check-act (PDCA ) cycle in enhancing the quality of peripheral vascular ultrasound reports (including textual and imaging components)generated by resident physicians in the ultrasound department.

Methods

The PDCA cycle was implemented from January to July 2023.Peripheral vascular ultrasound reports produced by resident physicians were randomly sampled monthly from the Ultrasound Medical Imaging Information System of the Third Central Hospital of Tianjin.These reports were evaluated for textual clarity, image quality, and diagnostic accuracy.We set an improvement target of 95% or more for category A image and text reports and established a continuous quality improvement team to analyze deficiencies and develop corrective measures for substandard reports.After the implementation of the improvement measures from August to December 2023, the image and text scores were rescored.A chi-square test was used to compare the differences in image and text report scores and deficiency items before and after implementation.The improvement results were assessed through ongoing training implementation,discussion within the department, and feedback from resident physicians.

Results

Prior to PDCA implementation,category A images accounted for 66.3% (130/196) of reports, and category A reports constituted 44.9% (88/196).After PDCA intervention, category A images significantly increased to 95.8% (92/96), and category A reports improved to 78.1% (75/96).The enhancements in both image and report quality were statistically significant(χ²=30.797, P＜0.01; χ²=28.849, P＜0.01).After implementing the PDCA cycle, image and report deficiencies were significantly reduced (45 vs 102; 59 vs 164), and the ability of instrument adjustment, disease diagnosis and description, and standardized image storage were improved.

Conclusion

The PDCA cycle effectively improves the quality of peripheral vascular ultrasound reports.

Objective

To explore the role of promotion of standardized thyroid ultrasound examination and C-TIRADS classification in improving the diagnostic concordance rate of thyroid ultrasound examinations in secondary and primary healthcare institutions in Haidian District, Beijing.

Methods

From July 2023 to June 2024, the Ultrasound Medical Quality Control and Improvement Center of Haidian District, Beijing conducted a one-year program of training and promotion of standardized thyroid ultrasound examination and C-TIRADS classification among secondary and primary healthcare institutions in Haidian District, Beijing.Both at baseline and after training, an online questionnaire survey was used to investigate the usage of C-TIRADS classification and the diagnostic concordance rate of thyroid ultrasound examinations in the involved institutions.The t-test was employed to compare the differences in diagnostic concordance rates between secondary and primary hospitals, as well as before and after training.

Results

A total of 59 valid questionnaires were finally included.At baseline, the usage rate of C-TIRADS classification was 30.5% (18/59); after training, it increased to 66.1% (39/59).At baseline, the overall diagnostic concordance rate of thyroid ultrasound examinations was 80.6%±11.7%.The diagnostic concordance rate in secondary hospitals was significantly higher than that in primary hospitals [(88.8%±9.4%) vs (78.8%±11.5%),t=3.064, P=0.007].After training, the overall diagnostic concordance rate of thyroid ultrasound examinations was 83.5%±7.6%.The diagnostic concordance rate in secondary hospitals remained significantly higher than that in primary hospitals [(88.9%±6.5%) vs (82.2%±7.4%), t=2.987, P=0.009], and the concordance rate in primary hospitals significantly increased compared with the baseline level (t=-2.453, P=0.018).

Conclusion

The Ultrasound Medical Quality Control and Improvement Center of Haidian District, Beijing has successfully increased the usage rate of C-TIRADS classification for thyroid nodules in secondary and primary hospitals in Haidian District, Beijing, significantly improving the diagnostic concordance rate of thyroid nodule ultrasound in primary hospitals.These efforts are beneficial for the establishment of a tiered diagnosis and treatment pattern.