hStroke_Suite LVO is an AI-powered solution optimized for emergency neuroimaging, designed to rapidly and accurately detect large vessel occlusions (LVOs) through CT angiography, enabling faster clinical decision-making and timely intervention for stroke patients, with mobile and smartwatch integration for continuous connectivity and real-time collaboration.
hStroke_Suite LVO: Detects the presence and location of LVO in brain CT angiography scans.
Brain CT angiography, Axial plane, Slice thickness of ranging from 0.75 to 1.5 mm.
CT Segmentation.
The F1-score, sensitivity, specificity, NPV, and PPV of the model on the external test set were 96.30% (95% CI 88.46–99%), 96.30% (95% CI 87.56–99.23%), 98.86% (95% CI 96.72–99.77%), 98.86% (95% CI 96.63–99.62%), and 96.30% (95% CI 89.40–98.77%), respectively.
The nnDetection model achieved a diagnostic accuracy of 98.26% (95% CI 96.25–99.36%) in identifying LVO, correctly classifying 339 out of 345 CTA scans in the external test set. The DL-based collateral scores had a kappa of 0.80, indicating good agreement with the consensus of the radiologists.
