Search

IntroductionIt 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.MethodsWe 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.ResultsOur 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) (p = 0.001 and p = 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; p = 0.557).DiscussionThe 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.

Perfusion imaging generates multimaps of ischemic tissues and is a proven decision-making tool in patients with acute ischemic stroke. However, the reliability of perfusion post-processing outcomes has been debated, given disparate results of various software applications, especially for patients with small ischemic core volume. This study was undertaken to compare ischemic volume estimates determined by imSTROKE (a software with new imaging protocol) and RAPID computer applications, respectively. A total of 611 patients qualified for study, each having met inclusion and exclusion criteria of the Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands (MR CLEAN trial). Subjects were examined by computed tomography perfusion (CTP) imaging (n = 349) or perfusion-weighted (PWI) and diffusion-weighted (DWI) imaging (n = 262). Ischemic volumes estimated by imSTROKE and RAPID applications were then compared. We used Bland-Altman analysis and intraclass correlation coefficients (ICCs) to ascertain agreement between applications. Accuracies of estimated core infarct and penumbra volumes were tested at specific thresholds (core: 25 mL, 50 mL, and 70 mL; penumbra: 45 mL, 90 mL, and 125 mL). Median core infarct volumes by imSTROKE and RAPID were 29.18 mL and 29.53 mL, respectively (ICC = 0.9880, 95% confidence interval [CI]: 0.9860–0.9898). Median penumbra volumes by imSTROKE and RAPID were 68.20 mL and 68.55 mL, respectively (ICC = 0.9885, 95% CI: 0.9865–0.9902). In estimating core infarct and penumbra volumes, imSTROKE and RAPID applications showed high-level agreement. For patients with small ischemic core volume, compared with RAPID, imSTROKE may have better sensitivity.

Automated cerebrovascular segmentation of time-of-flight magnetic resonance angiography (TOF-MRA) images is an important technique, which can be used to diagnose abnormalities in the cerebrovascular system, such as vascular stenosis and malformation. Automated cerebrovascular segmentation can direct show the shape, direction and distribution of blood vessels. Although deep neural network (DNN)-based cerebrovascular segmentation methods have shown to yield outstanding performance, they are limited by their dependence on huge training dataset. In this paper, we propose an unsupervised cerebrovascular segmentation method of TOF-MRA images based on DNN and hidden Markov random field (HMRF) model. Our DNN-based cerebrovascular segmentation model is trained by the labeling of HMRF rather than manual annotations. The proposed method was trained and tested using 100 TOF-MRA images. The results were evaluated using the dice similarity coefficient (DSC), which reached a value of 0.79. The trained model achieved better performance than that of the traditional HMRF-based cerebrovascular segmentation method in binary pixel-classification. This paper combines the advantages of both DNN and HMRF to train the model with a not so large amount of the annotations in deep learning, which leads to a more effective cerebrovascular segmentation method.