文献速递神经骨肌MR

从常规MRI中识别非创伤性臂丛神经病:基于深度学习网络的回顾性研究

Non-traumatic brachial plexopathy identification from routine MRIs: Retrospective studies with deep learning networks.
PubMed 文献 · Eur J Radiol · 2024-09-18

本研究回顾性纳入2002年1月至2022年12月在梅奥诊所接受臂丛MRI的患者196例,构建256个MRI序列(正常123个、异常133个),设计六种深度学习方案在三种MRI序列上区分臂丛异常。特征融合模式联合三序列策略表现最佳(AUC 92.2%,准确率89.5%),优于多通道融合模式(AUC 89.6%,准确率89.0%)和单通道容积模式(AUC 89.2%,准确率86.7%)。

要点

  • 特征融合模式联合三序列(矢状位T1、流体敏感、钆增强)的模型性能最佳,AUC 92.2%、准确率89.5%。
  • 三序列联合策略优于单序列分析,提示多序列信息整合有助于臂丛病变鉴别。
  • 异常序列中炎症性病变占33.1%、淋巴瘤占27.1%、乳腺癌占22.5%、其他占17.2%。

核心结论

  • 在矢状位T1、流体敏感和钆增强MRI序列上部署深度学习模型对臂丛神经病诊断显示出较大潜力;特征融合模式联合多MRI策略可能比单序列分析提供更满意的臂丛异常深度学习模型。

研究设计与样本

  • 回顾性研究,通过梅奥诊所电子病历或病理报告收集2002年1月至2022年12月接受臂丛MRI的患者,从初始267例候选者中选取196例,共编译256个臂丛MRI序列(正常123个、异常133个);由放射科小组在矢状位T1、流体敏感和钆增强图像上选取臂丛感兴趣区形成三维容积;设计六种深度学习方案,以五种知名深度学习网络为骨干,采用嵌套五折交叉验证进行训练和验证,并定义基于雷达图的方法评分作为最佳模型偏好的定量指标(最高2.37)。

诊断标准与关键数值

  • 最佳模型为特征融合模式联合三序列策略(AUC 92.2%,准确率89.5%),超过多通道融合模式(AUC 89.6%,准确率89.0%)、单通道容积模式(AUC 89.2%,准确率86.7%)及其余方案;以方法评分评价,VGG16骨干的特征融合模式在三序列联合策略下得分最高,为1.75。

临床应用与阅片要点

  • 作者认为,利用特征融合模式和多MRI联合策略可能比单序列分析为臂丛异常提供满意的深度学习模型。

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

PURPOSE: This study aims to seek an optimized deep learning model for differentiating non-traumatic brachial plexopathy from routine MRI scans.

MATERIALS AND METHODS: This retrospective study collected patients through the electronic medical records (EMR) or pathological reports at Mayo Clinic and underwent BP MRI from January 2002 to December 2022. Using sagittal T1, fluid-sensitive and post-gadolinium images, a radiology panel selected BP's region of interest (ROI) to form 3 dimensional volumes for this study. We designed six deep learning schemes to conduct BP abnormality differentiation across three MRI sequences. Utilizing five prestigious deep learning networks as the backbone, we trained and validated these models by nested five-fold cross-validation schemes. Furthermore, we defined a 'method score' derived from the radar charts as a quantitative indicator as the guidance of the preference of the best model.

RESULTS: This study selected 196 patients from initial 267 candidates. A total of 256 BP MRI series were compiled from them, comprising 123 normal and 133 abnormal series. The abnormal series included 4 sub-categories, et al. breast cancer (22.5 %), lymphoma (27.1 %), inflammatory conditions (33.1 %) and others (17.2 %). The best-performing model was produced by feature merging mode with triple MRI joint strategy (AUC, 92.2 %; accuracy, 89.5 %) exceeding the multiple channel merging mode (AUC, 89.6 %; accuracy, 89.0 %), solo channel volume mode (AUC, 89.2 %; accuracy, 86.7 %) and the remaining. Evaluated by method score (maximum 2.37), the feature merging mode with backbone of VGG16 yielded the highest score of 1.75 under the triple MRI joint strategy.

CONCLUSION: Deployment of deep learning models across sagittal T1, fluid-sensitive and post-gadolinium MRI sequences demonstrated great potential for brachial plexopathy diagnosis. Our findings indicate that utilizing feature merging mode and multiple MRI joint strategy may offer satisfied deep learning model for BP abnormalities than solo-sequence analysis.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Cao W, Howe BM, Ramanathan S, et al. Non-traumatic brachial plexopathy identification from routine MRIs: Retrospective studies with deep learning networks. Eur J Radiol. 2024. PMID: 39383628. doi:10.1016/j.ejrad.2024.111744

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。