文献速递脑血管病

机器学习基于CT血管成像自动测定急性缺血核心

Machine Learning-Enabled Automated Determination of Acute Ischemic Core From Computed Tomography Angiography.
PubMed 文献 · Stroke · 2019-09-24

本研究开发并验证了一种基于卷积神经网络(DeepSymNet)的自动化方法,利用CT血管成像(CTA)源图像评估大血管闭塞(LVO)和缺血核心体积,以CT灌注(CTP)-RAPID为参考标准。在297例患者中,模型检测LVO的AUC为0.88,确定缺血核心(≤30 mL和≤50 mL)的AUC分别为0.88和0.90,且在早期和晚期时间窗内表现一致。

要点

  • DeepSymNet可从CTA源图像自动检测LVO,AUC 0.88。
  • 模型确定缺血核心(≤30 mL和≤50 mL)的AUC分别为0.88和0.90。
  • 在0-6小时和6-24小时时间窗内,缺血核心≤50 mL的AUC分别为0.90和0.91。

核心结论

  • 基于CTA的机器学习模型可自动化评估LVO和缺血核心,性能与CTP-RAPID相当。

研究设计与样本

  • 回顾性队列研究,纳入297例急性缺血性卒中或卒中 mimics 患者,均接受CTA和CTP-RAPID检查。
  • 开发卷积神经网络DeepSymNet,以CTP-RAPID定义为参考,采用10折交叉验证和AUC评估性能。

主要发现

  • 224例(75%)为急性缺血性卒中,其中179例(60%)存在LVO。
  • 平均CTP-RAPID缺血核心体积为23±42 mL。
  • LVO位置包括颈内动脉(13%)、M1(44%)和M2(21%)。
  • DeepSymNet检测LVO的AUC为0.88。
  • 确定缺血核心(≤30 mL和≤50 mL)的AUC分别为0.88和0.90;在早期(0-6小时)和晚期(6-24小时)时间窗内,缺血核心≤50 mL的AUC分别为0.90和0.91。

临床怎么用

  • 对于缺乏高级影像检查条件的机构,可尝试使用CTA源图像结合机器学习自动化评估LVO和缺血核心,辅助血管内治疗决策。

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)。

原文

Background and Purpose- The availability of and expertise to interpret advanced neuroimaging recommended in the guideline-based endovascular stroke therapy (EST) evaluation are limited. Here, we develop and validate an automated machine learning-based method that evaluates for large vessel occlusion (LVO) and ischemic core volume in patients using a widely available modality, computed tomography angiogram (CTA). Methods- From our prospectively maintained stroke registry and electronic medical record, we identified patients with acute ischemic stroke and stroke mimics with contemporaneous CTA and computed tomography perfusion (CTP) with RAPID (IschemaView) post-processing as a part of the emergent stroke workup. A novel convolutional neural network named DeepSymNet was created and trained to identify LVO as well as infarct core from CTA source images, against CTP-RAPID definitions. Model performance was measured using 10-fold cross validation and receiver-operative curve area under the curve (AUC) statistics. Results- Among the 297 included patients, 224 (75%) had acute ischemic stroke of which 179 (60%) had LVO. Mean CTP-RAPID ischemic core volume was 23±42 mL. LVO locations included internal carotid artery (13%), M1 (44%), and M2 (21%). The DeepSymNet algorithm autonomously learned to identify the intracerebral vasculature on CTA and detected LVO with AUC 0.88. The method was also able to determine infarct core as defined by CTP-RAPID from the CTA source images with AUC 0.88 and 0.90 (ischemic core ≤30 mL and ≤50 mL). These findings were maintained in patients presenting in early (0-6 hours) and late (6-24 hours) time windows (AUCs 0.90 and 0.91, ischemic core ≤50 mL). DeepSymNet probabilities from CTA images corresponded with CTP-RAPID ischemic core volumes as a continuous variable with r=0.7 (Pearson correlation, P<0.001). Conclusions- These results demonstrate that the information needed to perform the neuroimaging evaluation for endovascular therapy with comparable accuracy to advanced imaging modalities may be present in CTA, and the ability of machine learning to automate the analysis.

来源:Stroke,查看原文。版权归原作者所有。

引用

  1. Sheth SA, Lopez-Rivera V, Barman A, et al. Machine Learning-Enabled Automated Determination of Acute Ischemic Core From Computed Tomography Angiography. Stroke. 2019. PMID: 31547796. doi:10.1161/STROKEAHA.119.026189

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。