文献速递神经外周血管CT

基于深度学习的多时相CTA侧支循环评分在MCA区域急性缺血性卒中患者中的应用

Deep Learning-Based Collateral Scoring on Multiphase CTA in Patients with Acute Ischemic Stroke in the MCA Region.
PubMed 文献 · AJNR Am J Neuroradiol · 2026-01-05

本回顾性研究纳入420例症状发作14小时内的急性缺血性卒中患者的多时相CTA图像,开发基于深度学习的侧支循环分类方法,以简化Menon法人工评分为参考标准。模型在3分类侧支评分中准确率87.6%、AUC 93.7%,2分类中良好vs非良好准确率94.0%、AUC 97.1%,与放射科医师评分一致性高。

要点

  • 深度学习模型对mCTA侧支循环3分类(良好、中等、差)准确率87.6%、AUC 93.7%。
  • 良好vs非良好2分类准确率94.0%、AUC 97.1%,与人工评分一致性ICC 0.882。
  • 多时相CTA在侧支评估中表现优于单时相或2时相CTA。

核心结论

  • 所提出的深度学习框架在评估急性缺血性卒中患者mCTA侧支循环时表现出高准确率,与放射科医师评分一致性高,可能作为辅助临床决策、减少变异性和改善诊断流程的工具。

研究设计与样本

  • 回顾性研究,纳入420例症状发作14小时内的急性缺血性卒中患者的多时相CTA图像,以简化Menon法人工评估为参考标准,采用5折交叉验证评估模型性能。

诊断标准与关键数值

  • 3分类侧支评分(良好、中等、差):准确率87.6%、F1分数85.7%、精确率83.8%、敏感度89.3%、特异度92.9%、AUC 93.7%、ICC 0.832、κ 0.781。良好vs非良好2分类:准确率94.0%、F1分数94.4%、精确率95.9%、敏感度93.0%、特异度94.1%、AUC 97.1%、ICC 0.882、κ 0.881。差vs非差2分类:准确率97.1%、F1分数98.5%、精确率98.0%、敏感度99.0%、特异度84.8%、AUC 95.6%、ICC 0.740、κ 0.738。

临床应用与阅片要点

  • 作者认为该方法可能作为辅助临床决策的工具,减少变异性并改善诊断流程;多时相CTA在侧支评估中表现优于单时相或2时相CTA。

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

BACKGROUND AND PURPOSE: Collateral circulation is a critical determinant of clinical outcomes in patients with acute ischemic stroke (AIS) and plays a key role in patient selection for endovascular therapy. This study aimed to develop an automated method for assessing and quantifying collateral circulation on multiphase CTA (mCTA), aiming to reduce observer variability and improve diagnostic efficiency.

MATERIALS AND METHODS: This retrospective study included mCTA images from 420 patients with AIS within 14 hours of stroke symptom onset. A deep learning-based classification method with a tailored preprocessing module was developed to assess collateral circulation status. Manual evaluations using the simplified Menon method served as the ground truth. Model performance was assessed through 5-fold cross-validation using metrics including accuracy, F1 score, precision, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC).

RESULTS: The median age of the 420 patients was 73 years (interquartile range [IQR], 64-80 years; 222 men), and the median time from symptom onset to mCTA acquisition was 123 minutes (IQR, 79-245.5 minutes). The proposed framework achieved an accuracy of 87.6% for 3-class collateral scores (good, intermediate, poor), with the F1 score (85.7%), precision (83.8%), sensitivity (89.3%), specificity (92.9%), AUC (93.7%), intraclass coordination coefficient (ICC) (0.832), and κ (0.781). For 2-class collateral scores, we obtained 94.0% accuracy for good-versus-nongood scores (F1 score [94.4%], precision [95.9%], sensitivity [93.0%], specificity [94.1%], AUC [97.1%], ICC [0.882]), κ [0.881]), and 97.1% for poor-versus-nonpoor scores ([F1 score [98.5%], precision [98.0%], sensitivity [99.0%], specificity [84.8%], AUC [95.6%], ICC [0.740], κ [0.738]). Additional analyses demonstrated that multiphase CTA showed improved performance over single- or 2-phase CTA in the collateral assessment.

CONCLUSIONS: The proposed deep learning (DL) framework demonstrated high accuracy and consistency with radiologist-assigned scores for evaluating collateral circulation with mCTA in patients with AIS. This method may offer a useful tool to aid in clinical decision-making, reducing variability and improving diagnostic workflow.

来源:AJNR Am J Neuroradiol,查看原文。版权归原作者所有。

引用

  1. Liu H, Zhang J, Chen S, et al. Deep Learning-Based Collateral Scoring on Multiphase CTA in Patients with Acute Ischemic Stroke in the MCA Region. AJNR Am J Neuroradiol. 2026. PMID: 40623825. doi:10.3174/ajnr.A8911

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。