Gao Hongyu, Bian Yueyan, Cheng Gen, Yu Huan, Cao Yuze, Zhang Huixue, Wang Jianjian, Li Qian, Yang Qi, Wang Lihua
Department of Neurology, The Second Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang, China.
Department of Radiology, Beijing Chaoyang Hospital, Capital Medical University, Beijing, China.
Front Med (Lausanne). 2023 Feb 22;10:1085437. doi: 10.3389/fmed.2023.1085437. eCollection 2023.
It is critical to identify the stroke onset time of patients with acute ischemic stroke (AIS) for the treatment of endovascular thrombectomy (EVT). However, it is challenging to accurately ascertain this time for patients with wake-up stroke (WUS). The current study aimed to construct a deep learning approach based on computed tomography perfusion (CTP) or perfusion weighted imaging (PWI) to identify a 6-h window for patients with AIS for the treatment of EVT.
We collected data from 377 patients with AIS, who were examined by CTP or PWI before making a treatment decision. Cerebral blood flow (CBF), time to maximum peak (Tmax), and a region of interest (ROI) mask were preprocessed from the CTP and PWI. We constructed the classifier based on a convolutional neural network (CNN), which was trained by CBF, Tmax, and ROI masks to identify patients with AIS within a 6-h window for the treatment of EVT. We compared the classification performance among a CNN, support vector machine (SVM), and random forest (RF) when trained by five different types of ROI masks. To assess the adaptability of the classifier of CNN for CTP and PWI, which were processed respectively from CTP and PWI groups.
Our results showed that the CNN classifier had a higher performance with an area under the curve (AUC) of 0.935, which was significantly higher than that of support vector machine (SVM) and random forest (RF) ( = 0.001 and = 0.001, respectively). For the CNN classifier trained by different ROI masks, the best performance was trained by CBF, Tmax, and ROI masks of Tmax > 6 s. No significant difference was detected in the classification performance of the CNN between CTP and PWI (0.902 vs. 0.928; = 0.557).
The CNN classifier trained by CBF, Tmax, and ROI masks of Tmax > 6 s had good performance in identifying patients with AIS within a 6-h window for the treatment of EVT. The current study indicates that the CNN model has potential to be used to accurately estimate the stroke onset time of patients with WUS.
确定急性缺血性卒中（AIS）患者的卒中发作时间对于血管内血栓切除术（EVT）治疗至关重要。然而，准确确定醒后卒中（WUS）患者的这一时间具有挑战性。本研究旨在构建一种基于计算机断层扫描灌注（CTP）或灌注加权成像（PWI）的深度学习方法，以确定AIS患者适合EVT治疗的6小时时间窗。
我们收集了377例AIS患者的数据，这些患者在做出治疗决策前接受了CTP或PWI检查。从CTP和PWI中预处理脑血流量（CBF）、最大峰值时间（Tmax）和感兴趣区（ROI）掩码。我们基于卷积神经网络（CNN）构建分类器，该分类器通过CBF、Tmax和ROI掩码进行训练，以识别适合EVT治疗的6小时时间窗内的AIS患者。我们比较了由五种不同类型的ROI掩码训练时，CNN、支持向量机（SVM）和随机森林（RF）之间的分类性能。评估分别从CTP组和PWI组处理得到的CTP和PWI的CNN分类器的适应性。
我们的结果表明，CNN分类器具有更高的性能，曲线下面积（AUC）为0.935，显著高于支持向量机（SVM）和随机森林（RF）（分别为 = 0.001和 = 0.001）。对于由不同ROI掩码训练的CNN分类器，最佳性能是通过CBF、Tmax以及Tmax > 6秒的ROI掩码训练得到的。CTP和PWI之间的CNN分类性能未检测到显著差异（0.902对0.928； = 0.557）。
由CBF、Tmax以及Tmax > 6秒的ROI掩码训练的CNN分类器在识别适合EVT治疗的6小时时间窗内的AIS患者方面具有良好性能。本研究表明，CNN模型有潜力用于准确估计WUS患者的卒中发作时间。
