文献速递骨肌技术与安全US

可解释超声多模态深度学习预测腕管综合征针刀松解疗效

Explainable ultrasound-based multimodal deep learning for outcome prediction after needle release in carpal tunnel syndrome: a multicenter study.
PubMed 文献 · Eur J Radiol · 2026-09-13

本研究回顾性收集4个中心449例腕管综合征患者,利用治疗前超声、电生理与临床资料训练多模态深度学习模型CTSNet-P,预测针刀松解术后6个月疗效,外部前瞻性169例验证。模型AUC分别为0.943和0.931,显著优于6名放射科医生平均水平,AI辅助后医生平均AUC由0.793提升至0.862。

要点

  • 超声在疗效预测中作用最大,阅片时应重视横切面、纵切面及彩色多普勒特征。
  • CTSNet-P AUC显著高于放射科医生平均水平,AI辅助可明显提升医生预测性能。
  • 预测目标是针刀松解术后6个月疗效(有效/无效),报告结论应体现个体化转归信息。

核心结论

  • 可解释多模态深度学习模型CTSNet-P对腕管综合征针刀松解术后6个月疗效的预测AUC在测试集中分别达0.943和0.931,显著高于6名放射科医生的平均水平(0.798和0.793,均p<0.001)。
  • AI辅助策略使放射科医生平均AUC从0.793提升至0.862(p<0.001),显示模型可有效增强个体化决策能力。

研究设计与样本

  • 回顾性收集4个临床中心449例CTS患者作为训练、验证和内部测试数据,另前瞻性招募169例作为外部测试集。
  • 治疗前采集超声特征(横截面积、横切面与纵切面B模式、彩色多普勒)、电生理参数和临床信息,以术后6个月患者报告疗效作为参考标准。
  • 通过消融实验确定多模态模型CTSNet-P结构,利用Shapley值展示特征贡献,Grad-CAM显示模型关注区域。

关键影像表现/征象

  • 超声特征在疗效预测过程中的作用始终最为显著,提示治疗前超声征象是判断预后的关键影像依据。
  • 热图显示CTSNet-P的注意力区域与放射科医生的关注模式趋于一致,模型关注模式具有一定可解释性。

诊断标准与关键数值

  • 内部测试与外部测试集中CTSNet-P的AUC分别为0.943和0.931。
  • CTSNet-P与6名放射科医生平均AUC比较:0.943 vs 0.798,0.931 vs 0.793,均p<0.001。
  • AI辅助后外部测试集中放射科医生平均AUC为0.862,较无辅助的0.793显著提升(p<0.001)。
  • 疗效判定标准为术后6个月患者报告结局,分为有效与无效两类。

临床应用与阅片要点

  • 日常阅片时可结合治疗前超声多切面征象、电生理参数及临床资料,综合判断针刀松解的预期转归。
  • AI辅助有助于低年资医生提升疗效预测水平,但不能替代对超声征象本身的仔细判读。
  • 模型解释工具(Shapley值、Grad-CAM)有助于理解预测依据,在报告沟通中可作为可视化参考。

局限性

  • 原文指出研究结果尚需在更大样本中进一步验证,目前结论外推需谨慎。

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: Ultrasound (US)-guided percutaneous needle release is an effective treatment for carpal tunnel syndrome (CTS) before proceeding to surgery. However, conventional methods cannot be used to effectively predict prognosis.We aimed to develop explainable multimodal deep learning (DL) models to enhance individualized decision-making.

METHODS: Pre-therapy sonographic features (cross-sectional area, B-mode in transverse and longitudinal views, and color Doppler imaging), electrophysiological parameters, and clinical information of patients with CTS (n = 449) were retrospectively collected from four clinical centers for model training, validation, and internal testing. A multimodal DL model (CTSNet-P) was established after ablation experiments to predict the 6-month therapeutic outcome (effective or ineffective). Two additional cohorts (n = 169) were prospectively recruited for external testing. Shapley values were used to display feature contributions, while Grad-CAMs were used to elucidate the model's focus. Outcome predictions from six radiologists with varying levels of expertise were compared with those obtained using CTSNet-P in the test sets. Artificial intelligence (AI)-aided strategies were then conducted in the external test set to assess the model's impact on the radiologists' predictive performance. The patient-reported outcomes at 6 months after treatment served as the reference standard.

RESULTS: The areas under the receiver operating characteristic curve (AUCs) in the test sets using CTSNet-P were 0.943 and 0.931, respectively. Higher AUCs were obtained with the model than the mean values of the six radiologists (0.943 vs. 0.798 and 0.931 vs. 0.793, respectively;all p < 0.001). The average AUC was significantly improved with assistance from CTSNet-P (0.793 vs. 0.862; p < 0.001). US consistently played the most significant role in the prediction process, and the heatmaps indicated a trend towards alignment with the attention patterns exhibited by the human radiologists.

CONCLUSION: The interpretable CTSNet-P exceeded the average level of radiologists in prognosis prediction of needle release for CTS, and significantly augmented the radiologists' performance. However, these findings necessitate further investigations in a larger cohort.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Shi, Yu, Yuan, et al. Explainable ultrasound-based multimodal deep learning for outcome prediction after needle release in carpal tunnel syndrome: a multicenter study. Eur J Radiol. 2026. PMID: 42766999. doi:10.1016/j.ejrad.2026.113251

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。