文献速递神经MR

基于深度学习的时间肌MRI定量预测急性缺血性卒中不良结局

Deep learning-based temporal muscle quantification on MRI predicts adverse outcomes in acute ischemic stroke.
PubMed 文献 · Eur J Radiol · 2025-07-23

本研究纳入1020例急性缺血性卒中患者,构建深度学习流程完成时间肌MRI层面选择、分割及厚度与面积自动定量,并评估其预后价值。自动提取的时间肌厚度和面积各自独立与6个月不良结局相关(厚度HR 0.736,面积HR 0.702),端到端流程可快速自动定量并融入临床工作流。

要点

  • 时间肌厚度自动定量与6个月不良结局独立相关(HR 0.736,95%CI 0.528-0.931)。
  • 时间肌面积自动定量与6个月不良结局独立相关(HR 0.702,95%CI 0.541-0.910)。
  • T1WI时间肌分割平均DSC为0.858,层面选择±1层准确率97.94%。

核心结论

  • 时间肌厚度和面积是急性缺血性卒中患者的稳健预后标志物,端到端深度学习流程可实现快速自动定量并融入临床工作流,支持可扩展的风险分层和个性化康复规划。

研究设计与样本

  • 研究纳入1020例急性缺血性卒中患者,分为数据集1(n=295)用于ResNet50模型层面选择、数据集2(n=258)用于基于TransUNet算法的时间肌分割、数据集3(n=467)用于评估基于深度学习的时间肌厚度和面积定量的预后价值。

诊断标准与关键数值

  • 自动层面选择平均准确率72.91%,±1层准确率97.94%,平均绝对误差1.54 mm;T1WI时间肌分割平均DSC为0.858。

临床应用与阅片要点

  • 自动提取的时间肌厚度和面积可在调整年龄、性别、小野寺营养预后指数、系统性免疫炎症指数、白蛋白水平及吸烟饮酒史后独立预测6个月不良结局(厚度HR 0.736,95%CI 0.528-0.931;面积HR 0.702,95%CI 0.541-0.910)。

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: To develop a deep learning (DL) pipeline for accurate slice selection, temporal muscle (TM) segmentation, TM thickness (TMT) and area (TMA) quantification, and assessment of the prognostic role of TMT and TMA in acute ischemic stroke (AIS) patients.

METHODS: A total of 1020 AIS patients were enrolled. Participants were divided into three datasets: Dataset 1 (n = 295) for slice selection using ResNet50 model, Dataset 2 (n = 258) for TM segmentation employing TransUNet-based algorithm, and Dataset 3 (n = 467) for evaluating DL-based quantification of TMT and TMA as prognostic factors in AIS. The ability of the DL system to select slices was assessed using accuracy, ±1 slice accuracy and mean absolute error. The Dice similarity coefficient (DSC) is used to assess the performance of the DL system on TM segmentation. The association between automatic quantification of TMT and TMA and 6-month outcomes was determined.

RESULTS: Automatic slice selection achieved a mean accuracy of 72.91 %, 97.94 % ± 1 slice accuracy with a mean absolute error of 1.54 mm, while TM segmentation on T1WI achieved a mean DSC of 0.858. Automatically extracted TMT and TMA were each independently associated with 6-month poor outcomes in AIS patients after adjusting for age, sex, onodera nutritional prognosis index, systemic immune-inflammation index, albumin levels, and smoking/drinking history (TMT: hazard ratio 0.736, 95 % confidence interval 0.528-0.931; TMA: hazard ratio 0.702, 95 % confidence interval 0.541-0.910).

CONCLUSION: TMT and TMA are robust prognostic markers in AIS patients, and our end-to-end DL pipeline enables rapid, automated quantification that integrates seamlessly into clinical workflows, supporting scalable risk stratification and personalized rehabilitation planning.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Huang R, Chen J, Wang H, et al. Deep learning-based temporal muscle quantification on MRI predicts adverse outcomes in acute ischemic stroke. Eur J Radiol. 2025. PMID: 40716184. doi:10.1016/j.ejrad.2025.112332

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。