Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Musculoskeletal system(MSK)diseases have high incidences,severely affecting patients' functional status and quality of life,also being the primary causes of disability.As a supplementary technique to traditional ultrasound,ultrasound elastography(USE)has advantages such as real-time dynamic evaluation,without radiation,low cost,good repeatability and portability,being able to provide unique diagnostic information through evaluating tissue stiffness,demonstrating significant value in the diagnosis and therapeutic monitoring of MSK diseases,mainly including evaluating muscle,tendon,ligament,joint injuries,nerves and bones.However,USE also faces shortcomings and challenges such as strong operator dependence,limited evaluation of deep tissues,and lack of standardization.In the future,development of three-dimensional analysis,integration with artificial intelligence,establishment of standards and expansion of application fields are required to achieve broader clinical application of USE.The application,advantages,challenges and prospects of USE in MSK diseases were reviewed in this article.

Sj?gren syndrome(SS)is an immune disease mainly characterized by lymphocytes infiltrate in salivary and lacrimal glands,leading to glandular secretion disorders and dryness in the mouth and eyes.In recent years,clinical application of ultrasound elastography(USE)increased widespread,providing a new imaging method for diagnosis of SS.The research progresses of USE in SS were reviewed in this article.

Quality control of pediatric musculoskeletal ultrasound(MSKUS)must be integrated throughout the entire diagnostic process.Its core lies in a thorough understanding of the growth,development,and pathophysiological characteristics of the pediatric musculoskeletal system,mastery of MSKUS examination techniques,and the establishment of a systematic and comprehensive diagnostic framework.This review focuses on the core aspects of pre-examination,during examination,and post-examination to describe the quality control points and strategies for pediatric MSKUS.

Musculoskeletal system(MSK)diseases have high incidences,severely affecting patients' functional status and quality of life,also being the primary causes of disability.As a supplementary technique to traditional ultrasound,ultrasound elastography(USE)has advantages such as real-time dynamic evaluation,without radiation,low cost,good repeatability and portability,being able to provide unique diagnostic information through evaluating tissue stiffness,demonstrating significant value in the diagnosis and therapeutic monitoring of MSK diseases,mainly including evaluating muscle,tendon,ligament,joint injuries,nerves and bones.However,USE also faces shortcomings and challenges such as strong operator dependence,limited evaluation of deep tissues,and lack of standardization.In the future,development of three-dimensional analysis,integration with artificial intelligence,establishment of standards and expansion of application fields are required to achieve broader clinical application of USE.The application,advantages,challenges and prospects of USE in MSK diseases were reviewed in this article.

Sj?gren syndrome(SS)is an immune disease mainly characterized by lymphocytes infiltrate in salivary and lacrimal glands,leading to glandular secretion disorders and dryness in the mouth and eyes.In recent years,clinical application of ultrasound elastography(USE)increased widespread,providing a new imaging method for diagnosis of SS.The research progresses of USE in SS were reviewed in this article.

Quality control of pediatric musculoskeletal ultrasound(MSKUS)must be integrated throughout the entire diagnostic process.Its core lies in a thorough understanding of the growth,development,and pathophysiological characteristics of the pediatric musculoskeletal system,mastery of MSKUS examination techniques,and the establishment of a systematic and comprehensive diagnostic framework.This review focuses on the core aspects of pre-examination,during examination,and post-examination to describe the quality control points and strategies for pediatric MSKUS.

Objective:To propose a deep learning（DL）-based ultrasound imaging auxiliary tool for automatic segmentation and recognition of the brachial plexus（BP），and to enhance the accuracy and safety of clinical procedures.Methods:It was a multicenter study that collected 773 healthy subjects from Peking University Third Hospital and its branch campuses，the Third Medical Center of the Chinese PLA General Hospital，and Shanghai Eighth People's Hospital between August 2024 and February 2025. Brachial plexus（BP）images in the interscalene groove were captured used high-frequency ultrasound by senior sonographers，a dataset comprising 1 289 standardized images were constructed and the improved model（CHA-TransUNet）was trained. The test set was input into 6 different models（CHA-TransUNet，R50-Unet，TransUnet，SegFormer，SwinUnet，MISSFormer）for segmentation. Segmentation accuracy was evaluated using metrics including the Dice similarity coefficient（DSC），95% Hausdorff distance（HD95）and mean intersection over union（mIoU），and was compared with the segmentation results of 3 ultrasound physicians with varying experience levels（junior physicians and senior physicians）to validate the model's segmentation efficacy.Results:The CHA-TransUNet model established based on a dataset of 1 289 standardized images achieved segmentation results for the BP with a DSC of 90.15%，mIoU of 91.02%，and HD95 of 8.08. Its accuracy was higher than other mainstream models（DSC：90.15% vs. 87.60%，87.77%，81.35%，84.78%，84.55%），significantly better than junior physicians（DSC：90.15% vs. 68.73%， Z=-127.76， P<0.001），and approached the level of senior physician（DSC：90.15% vs. 86.15%， Z=-31.33， P=0.549）. The model demonstrated superior boundary recognition in complex anatomical structures（e.g.，C6/C7 nerve roots）compared to ultrasound physicians（junior and senior）（HD95：8.08 vs. 26.34，17.44，56.80）. Conclusions:This study proposes an analysis model for BP ultrasound images，CHA-TransUNet. This model achieves segmentation and recognition of the BP with relatively complex pathways and structures. The model exhibits high accuracy and stability，outperforming current mainstream network models and junior physicians while approaching the performance level of senior physicians. It assists junior physicians or trainees in more accurately identifying and localizing the BP.

Biliary atresia is a severe chronic liver disease in infancy that manifests as destructive inflammatory obstructive cholangiopathy.Recent evidence supports that early Kasai procedure by 30 days of life achieves the greatest likelihood of slowing or preventing the need for liver transplant in biliary atresia patients.Unfortunately,the average age at the time of Kasai procedure is around 60 days of life both in China and abroad.The primary reason for this is that there are many difficulties and challenges in early diagnosis.For example,age stratification should be considered when using GGT levels as a screening tool for biliary atresia in infant less than 30 days.What's more,imaging modality such as US shows lower accuracy in very early stage due to milder pathological change in biliary tract,which post challenges on precision medicine and improving prognosis.This article reviewed different early diagnostic methods of screening for biliary atresia,so as to provide a reference for the early diagnosis of biliary atresia,and help discuss the potential development prospect and research direction in the future.

Objective To develope and evaluate the outcomes of combining"Curriculum Ideological and Political Education"with interactive teaching in ultrasonic practice class.Methods Fifty-one sophomores in the medical en-gineering cross experimental class of Beihang University who participated in the ultrasonic course in 2022 were se-lected as research objects.They were divided into two groups:one group adopted the classic teaching mode,the an-other group adopted the"Curriculum Ideological and Political Education"interactive teaching mode.After the train-ing,a questionnaire survey and a written examination of basic knowledge were conducted.The test scores of the two groups and the feedback from questionnaires for teaching effect were compared.Results There was no significant difference in the theoretical exam achievement rate between the two groups of students.The students'learning initia-tive and understanding of doctors'profession after the application of this new training method were significantly im-proved as compared with the classic lecture group,with a statistical difference.Student feedback showed that more ideological and political elements needed to be integrated into the ultrasound medicine classroom.Conclusions It is a good teaching method to integrate the interactive teaching of"Curriculum Ideological and Political Education"with learning of ultrasonic specialized courses.