人工智能在肩部超声扫描中实时自动引导:降低肩袖评估的操作者依赖性
这项前瞻性多中心研究开发了基于卷积神经网络的AI引导系统,用于肩部超声标准切面的实时自动分类与结构识别。系统在外部验证集上AUC为0.99、mAP为0.89,可使初级住院医师肩部超声检查时间较无AI辅助缩短34%(10.06±2.74 min vs 15.26±5.07 min,p=0.014),效率与专家监督相当。
要点
- AI系统可同时引导15个标准切面的获取并定位27个关键结构。
- 外部验证集上分类AUC为0.99,结构检测mAP为0.89。
- 初级住院医师使用AI引导后检查时间缩短34%(10.06±2.74 min vs 15.26±5.07 min,p=0.014)。
核心结论
- AI系统通过提供准确、实时的引导来标准化肩部超声图像采集,降低新手对操作者的依赖性,并为后续诊断解读建立可重复的基础。
研究设计与样本
- 前瞻性多中心研究,使用中心1的13,312个肩部超声视频中的74,909帧图像和852张标准切面图像进行模型训练与内部测试,中心2的480个视频中的8,458帧图像作为外部测试集,开发卷积神经网络。
诊断标准与关键数值
- 外部验证集上基于EfficientNetB2的AI系统分类AUC为0.99,结构检测平均精度(mAP)为0.89;系统可同时引导15个标准切面并定位27个关键结构。
临床应用与阅片要点
- 初级住院医师在AI引导下肩部超声检查时间为(10.06±2.74)min,无AI引导时为(15.26±5.07)min,AI引导使检查时间缩短34%(p=0.014),效率与专家监督相当;独立专家评估确认系统实时引导准确性高。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVES: This study aimed to develop an artificial intelligence (AI)-guided system for real-time automatic classification and structural recognition of shoulder US planes, in order to standardize the US scanning process.
MATERIALS AND METHODS: This was a prospective multicenter study. 852 standard plane images and 74,909 frame images from 13,312 shoulder US videos from Center 1 were used for model training/internal testing. 8458 frame images from 480 videos from Center 2 were collected as external test set. Convolutional neural networks were developed. Performance was evaluated using classification metrics (AUC) and structure detection metrics (average precision, AP). The clinical utility was assessed by comparing the examination duration of primary residents with and without AI guidance. AI performance in real-time shoulder US was evaluated by musculoskeletal (MSK) US expert with classification accuracy and target structure detection accuracy.
RESULTS: The EfficientNetB2-based AI system, capable of concurrently guiding the acquisition of 15 standard planes and localizing 27 key structures, demonstrated robust performance on an independent external validation set (AUC: 0.99; mAP: 0.89). For junior residents, AI guidance significantly reduced shoulder US examination time by 34% compared to unassisted scans ([10.06 ± 2.74] min vs. [15.26 ± 5.07] min; p = 0.014), achieving efficiency comparable to expert supervision. Independent expert evaluation confirmed the high real-time guidance accuracy of the system.
CONCLUSION: Our AI system standardizes shoulder US acquisition by providing accurate, real-time guidance. It reduces operator dependency for novices and establishes a reproducible foundation for subsequent diagnostic interpretation, representing a critical advancement towards standardized MSK US imaging acquisition.
引用
- He Y, Li Z, Wu H, et al. Real-time Automatic Guidance During Shoulder Ultrasound Scanning with Artificial Intelligence: Reducing Operator Dependency in Rotator Cuff Assessment. Acad Radiol. 2026. PMID: 41904092. doi:10.1016/j.acra.2026.03.012
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。