文献速递骨肌神经技术与安全US

多模态深度学习用于腕管综合征分级:一项中国多中心研究

Multimodal Deep Learning for Grading Carpal Tunnel Syndrome: A Multicenter Study in China.
PubMed 文献 · Acad Radiol · 2025-03-29

本研究基于三家医院回顾性数据(训练集680例、内部验证集173例)及另一医院前瞻性外部验证集174例,构建整合临床信息与超声多模态特征(横截面积、回声性、纵切神经形态、神经内血流)的联合深度学习模型CTSGrader进行腕管综合征分级,并以电生理结果为参考标准验证。CTSGrader在三个验证集的AUC分别为0.951、0.910、0.897,准确率分别为0.849、0.833、0.827,均高于单模态超声模型(均p<.05)。

要点

  • 联合深度学习模型CTSGrader在三个验证集AUC分别为0.951、0.910、0.897。
  • CTSGrader准确率0.849、0.833、0.827,均高于单模态超声模型(均p<.05)。
  • AI辅助后两名初级和一名高级放射科医师准确率均提高(均p<.05)。

核心结论

  • 联合深度学习模型CTSGrader优于单模态超声模型,AI辅助策略提示其有潜力支持腕管综合征严重程度分级的临床决策。

研究设计与样本

  • 回顾性数据集来自三家医院的腕管综合征患者,随机分为训练集(n=680)和内部验证集(n=173);外部验证集1为另一医院前瞻性招募(n=174);外部验证集2为三家额外医院使用不同超声系统的跨厂商测试(n=224)。参考标准为电生理结果。

关键影像表现/征象

  • 超声多模态特征包括横截面积(CSA)、回声性、纵切神经形态和神经内血流。
  • 联合深度学习模型CTSGrader整合超声特征与临床信息进行分级。

诊断标准与关键数值

  • CTSGrader在三个验证集的AUC分别为0.951、0.910、0.897。
  • CTSGrader在三个验证集的准确率分别为0.849、0.833、0.827,均高于单模态超声模型(均p<.05)。
  • CTSGrader优于两名初级和一名高级放射科医师(均p<.05),与一名高级放射科医师等效(均p>.05)。
  • AI辅助后两名初级和一名高级放射科医师准确率均提高(均p<.05)。

临床应用与阅片要点

  • 作者认为AI辅助策略有潜力支持腕管综合征严重程度分级的临床决策。

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

RATIONALE AND OBJECTIVES: Ultrasound (US)-based deep learning (DL) models for grading the severity of carpal tunnel syndrome (CTS) are scarce. We aimed to advance CTS grading by developing a joint-DL model integrating clinical information and multimodal US features.

MATERIALS AND METHODS: A retrospective dataset of CTS patients from three hospitals was randomly divided into the training (n=680) and internal validation (n=173) sets. An external validation set was prospectively recruited from another hospital (n=174). To further test the model's generalizability, cross-vendor testing was conducted at three additional hospitals utilizing different US systems in the external validation set 2 (n=224). An US-based model was developed to grade CTS severity utilizing multimodal sonographic features, including cross-sectional area [CSA], echogenicity, longitudinal nerve appearance, and intraneural vascularity. A joint-DL model (CTSGrader) was constructed integrating sonographic features and clinical information. Diagnostic performance of both models was verified based on electrophysiological results. In the validation sets, the better-performing model was compared to two junior and two senior radiologists. Additionally, the radiologists' diagnostic performance with artificial intelligence (AI) assistance was evaluated in external validation sets.

RESULTS: CTSGrader achieved areas under the curve (AUCs) of 0.951, 0.910, and 0.897 in the validation sets. The accuracies of CTSGrader were 0.849, 0.833, and 0.827, which were higher than those of US-based model (all p<.05). It outperformed two junior and one senior radiologists (all p<.05) and was equivalent to 1 senior radiologist (all p>.05). With its assistance, the accuracies of two junior and one senior radiologists were improved (all p<.05).

CONCLUSION: The joint-DL model (CTSGrader) developed in our study outperformed the single-modality model. The AI-aided strategy suggested its potential to support clinical decision-making for grading CTS severity.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Shi X, Yu T, Yuan Y, et al. Multimodal Deep Learning for Grading Carpal Tunnel Syndrome: A Multicenter Study in China. Acad Radiol. 2025. PMID: 40157849. doi:10.1016/j.acra.2025.02.043

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。