Abstract P544: Automated Artificial Intelligence Based Detection and Location Specification of Large Vessel Occlusion on CT Angiography in Stroke

Introduction: Fast and accurate detection of large vessel occlusions (LVOs) is crucial in selection of patients for endovascular treatment. We assessed the diagnostic performance and speed of an Artifical Intelligence algorithm for automated LVO detection with a novel feature that specifies the exact level of occlusion. Methods: All Computed Tomography Angiography (CTA) imaging data were analyzed by an automated algorithm for anterior circulation LVOs (internal carotid artery (ICA), M1 or M2 segments of the middle cerebral artery) (StrokeViewer, Nico.lab). Ground truth was established by consensus of two independent neuroradiologist readings. Diagnostic performance was assessed by calculating sensitivity, specificity, negative predictive value (NPV), and positive predictive value (PPV). Performance of the LVO localization feature was assessed by calculating interrater agreement (Cohen’s Kappa) between the algorithm and the expert panel. Results: CTAs from 297 patients referred or directly admitted to a comprehensive stroke center in the United States (mean age 67 years, SD 15; 145 males) were analyzed. One-hundred and fifty-six patients had an anterior circulation LVO. Location of the occlusions was ICA (n=43 [28%]), M1 (n=79 [51%]) and M2 (n=34 [22%]). Sensitivity and specificity for LVO detection were respectively 92% (95% CI, 86.2%-95.5%) and 85% (95% CI, 78.1%-90.5%). NPV and PPV were 90% and 87% respectively. Interrater agreement between the algorithm and the expert observers for LVO location was 0.92 (95% CI, 0.86-0.98). Median upload-to-notification time for all cases was 3 minutes, 34 seconds (minimal 2:28 minutes; maximal 5:03 minutes). Conclusions: Anterior circulation LVOs can be rapidly and accurately detected by an automated LVO detection algorithm with reliable localization of the involved vessel segment. Therefore, the algorithm presented in this study is a suitable screening tool to support diagnosis of LVOs.