| 61. |
- Wouters, Anke, et al.
(författare)
-
Prediction of Stroke Onset is Improved by Relative Fluid-Attenuated Inversion Recovery and Perfusion Imaging Compared to the Visual Diffusion-Weighted Imaging/Fluid-Attenuated Inversion Recovery Mismatch
- 2016
-
Ingår i: Stroke: a journal of cerebral circulation. - 0039-2499. ; 47:10, s. 2559-2564
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Purpose - Acute stroke patients with unknown time of symptom onset are ineligible for thrombolysis. The diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR) mismatch is a reasonable predictor of stroke within 4.5 hours of symptom onset, and its clinical usefulness in selecting patients for thrombolysis is currently being investigated. The accuracy of the visual mismatch rating is moderate, and we hypothesized that the predictive value of stroke onset within 4.5 hours could be improved by including various clinical and imaging parameters. Methods - In this study, 141 patients in whom magnetic resonance imaging was obtained within 9 hours after symptom onset were included. Relative FLAIR signal intensity was calculated in the region of nonreperfused core. Mean T max was calculated in the total region with T max >6 s. Mean relative FLAIR, mean T max, lesion volume with T max >6 s, age, site of arterial stenosis, core volume, and location of infarct were analyzed by logistic regression to predict stroke onset time before or after 4.5 hours. Results - Receiver-operating characteristic curve analysis revealed an area under the curve of 0.68 (95% confidence interval 0.59-0.78) for the visual diffusion-weighted imaging/FLAIR mismatch, thereby correctly classifying 69% of patients with an onset time before or after 4.5 hours. Age, relative FLAIR, and T max increased the accuracy significantly (P<0.01) to an area under the curve of 0.82 (95% confidence interval 0.74-0.89). This new predictive model correctly categorized 77% of patients according to stroke onset before versus after 4.5 hours. Conclusions - In patients with unknown stroke onset, the accuracy of predicting time from symptom onset within 4.5 hours is improved by obtaining relative FLAIR and perfusion imaging.
|
|
| 62. |
- Wu, Ona, et al.
(författare)
-
Big Data Approaches to Phenotyping Acute Ischemic Stroke Using Automated Lesion Segmentation of Multi-Center Magnetic Resonance Imaging Data
- 2019
-
Ingår i: Stroke. - 1524-4628. ; 50:7, s. 1734-1741
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Purpose- We evaluated deep learning algorithms' segmentation of acute ischemic lesions on heterogeneous multi-center clinical diffusion-weighted magnetic resonance imaging (MRI) data sets and explored the potential role of this tool for phenotyping acute ischemic stroke. Methods- Ischemic stroke data sets from the MRI-GENIE (MRI-Genetics Interface Exploration) repository consisting of 12 international genetic research centers were retrospectively analyzed using an automated deep learning segmentation algorithm consisting of an ensemble of 3-dimensional convolutional neural networks. Three ensembles were trained using data from the following: (1) 267 patients from an independent single-center cohort, (2) 267 patients from MRI-GENIE, and (3) mixture of (1) and (2). The algorithms' performances were compared against manual outlines from a separate 383 patient subset from MRI-GENIE. Univariable and multivariable logistic regression with respect to demographics, stroke subtypes, and vascular risk factors were performed to identify phenotypes associated with large acute diffusion-weighted MRI volumes and greater stroke severity in 2770 MRI-GENIE patients. Stroke topography was investigated. Results- The ensemble consisting of a mixture of MRI-GENIE and single-center convolutional neural networks performed best. Subset analysis comparing automated and manual lesion volumes in 383 patients found excellent correlation (ρ=0.92; P<0.0001). Median (interquartile range) diffusion-weighted MRI lesion volumes from 2770 patients were 3.7 cm3 (0.9-16.6 cm3). Patients with small artery occlusion stroke subtype had smaller lesion volumes ( P<0.0001) and different topography compared with other stroke subtypes. Conclusions- Automated accurate clinical diffusion-weighted MRI lesion segmentation using deep learning algorithms trained with multi-center and diverse data is feasible. Both lesion volume and topography can provide insight into stroke subtypes with sufficient sample size from big heterogeneous multi-center clinical imaging phenotype data sets.
|
|
