Search

Background and Purpose: Accurate estimation of ischemic core on baseline imaging has treatment implications in patients with acute ischemic stroke (AIS). Machine learning (ML) algorithms have shown promising results in estimating ischemic core using routine non-contrast CT (NCCT). We used a ML-trained algorithm to quantify ischemic core volume on NCCT and compared the results to concurrent diffusion MRI as the reference standard in patients with AIS. Methods: We analyzed consecutive anterior circulation AIS patients who had baseline (pretreatment) NCCT and MRI (DWI). Ischemic lesion volume was calculated on MRI-DWI using an automated software (Olea Medical SAS, La Ciotat, France). An automatic segmentation approach using a combination of traditional 3D graphics and statistical methods, and ML classification techniques (Brainomix, Oxford, United Kingdom) was used to identify ischemic core voxels on NCCT. Total ischemic core volumes on ML-NCCT and DWI-MR were quantitatively compared by Bland-Altman plots and Pearson correlation. Results: A total of 50 patients (27 female, 23 male, mean age 72.6 years) were included. Baseline imaging was performed within 173 ± 143 minutes (mean ± SD) from symptom onset. The mean time difference between MRI and NCCT was 72 min. The baseline NIHSS was 14, 8-21 (Median, IQR). Algorithm-segmented ischemic core volume detected on NCCT was median 12.7 mL, IQR 3.5-26.0 mL. Ischemic core volume on DWI MRI was median 8.8 mL, IQR 3.2-34.0 mL. ML-NCCT core volumes significantly correlated with DWI MRI core volumes, r =0.61, p p =0.81. For the reperfusion treatment threshold of an ischemic core volume within 70 mL, while no patients would have been excluded using our algorithm, five patients would have been incorrectly dichotomized as having an ischemic volume of Conclusion: This ML-approach accurately quantifies ischemic core volume on NCCT compared to the reference standard of diffusion MRI in patients with AIS.

Background and Purpose: In acute ischemic stroke (AIS), perfusion imaging, while not directly visualizing collateral vessels, can provide important insight into collateral robustness, indexed by perfusion lesion volume and by perfusion lesion heterogeneity. Two proposed perfusion lesion heterogeneity measures indexing collateral status are the Perfusion Collateral Index (PCI) and Hypoperfusion Intensity Ratio (HIR), but their accuracy compared with direct collateral assessment on DSA has been incompletely characterized. Methods: Consecutive AIS patients with anterior circulation large vessel occlusion who underwent pre-endovascular thrombectomy MRI perfusion imaging were included. MRI measures analyzed were: 1) Perfusion Collateral Index ( PCI) - the volume of moderately hypoperfused tissue (arterial tissue delay time between 2 and 6 seconds: ATD 2-6sec ) multiplied by its corresponding relative cerebral blood volume using Olea software; 2) Hypoperfusion Intensity Ratio (HIR) ratio of moderate TMax >6 s lesion volume versus severe Tmax >10 s lesion volume with the RAPID software program. DSA collateral scores were evaluated by ASITN grading and dichotomized to inadequate (ASTIN Results: Among 48 patients meeting entry criteria, age (mean ± SD) was 70 (± 15.2), 54% were female, and NIHSS (median, IQR) was 15 (10-19). For HIR, there was no significant difference in score values in patients with adequate vs inadequate collaterals: 0.35 ± 0.20 vs 0.39 ± 0.25, p=0.68. ROC analysis using previously described cut-off of 0.4 resulted in an AUC of 0.52 and sensitivity/specificity of 71% / 33%. For PCI, score values were significantly higher in patients with adequate vs inadequate collaterals, 117 ± 61 vs. 57 ± 41, p=0.002. ROC analysis using previously described cut-off of 62 resulted in an AUC of 0.8 and sensitivity/specificity of 84% / 78%. Conclusion: Collateral status can be accurately assessed on perfusion MRI with the Perfusion Collateral Index, which outperformed the Hypoperfusion Intensity Ratio. MRI-PCI is an informative imaging biomarker of collateral status in patients with AIS.