Automated detection of hyperdense artery sign on non-contrast CT for rapid identification of large vessel occlusion: a multicenter validation study

Purpose: Computed tomography angiography (CTA) is the gold standard for detecting large vessel occlusion, but its acquisition and reconstruction delay time-critical workflow. The hyperdense artery sign (HAS) on non-contrast CT (NCCT) offers an immediate, albeit subtle, marker. We developed a fully automated deep-learning model for HAS detection and evaluated its utility as an adjunctive pre-CTA alert to support earlier workflow readiness while confirmatory vascular imaging is pending. Furthermore, we assessed the radiological validity of the model's detections to ensure they correspond to genuine thrombi rather than artifacts. Methods: = 10 specialists and residents) to evaluate whether AI-detected regions were radiologically perceivable by human readers. Results: < 0.01). Conclusion: The proposed model enables rapid HAS detection on NCCT and demonstrated complementary performance across two validation settings: high reliability of positive alerts in a workflow-enriched CSC triage cohort and preserved sensitivity/specificity in a broader consecutive cohort. These findings support its role as an adjunctive pre-CTA alert for earlier workflow readiness in high-probability settings, not as a stand-alone rule-out tool. The observer study further supports the radiological validity of the AI-highlighted regions.