A US retrospective multicenter study evaluated two AI tools, Viz CTP (Viz.ai) and Rapid CTP (RapidAI), used to estimate core and penumbra volumes in patients with acute stroke using CT perfusion (CTP) scans. The study involved 362 participants with large vessel occlusion (LVO) and aimed to compare volume estimates and thrombectomy eligibility determined by these CTP packages across different scanners (e.g., Canon, Siemens) and scan protocols. Overall, Viz.ai reported larger core (25.9 cc) and penumbra (102.4 cc) volumes compared to RapidAI (18.2 cc and 84.6 cc). These differences were primarily driven by data from the Canon Aquilion One scanner, which accounted for the majority of the dataset. Despite these discrepancies, no significant difference in overall DEFUSE-3 thrombectomy eligibility was observed. However, a DEFUSE-3 eligibility discrepancy on one scanner at a single institution highlights the need for centers to consult with AI software vendors and scanner manufacturers to optimize CTP parameter settings for maximum accuracy, as performance can be affected by scanner models and local protocols.
Read full study
Multicenter comparison using two AI stroke CT perfusion software packages for determining thrombectomy eligibility
Journal of Stroke and Cerebrovascular Diseases, 2024
Abstract
Background: Stroke AI platforms assess infarcted core and potentially salvageable tissue (penumbra) to identify patients suitable for mechanical thrombectomy. Few studies have compared outputs of these platforms, and none have been multicenter or considered NIHSS or scanner/protocol differences. Our objective was to compare volume estimates and thrombectomy eligibility from two widely used CT perfusion (CTP) packages, Viz.ai and RAPID.AI, in a large multicenter cohort.
Methods: We analyzed CTP data of acute stroke patients with large vessel occlusion (LVO) from four institutions. Core and penumbra volumes were estimated by each software and DEFUSE-3 thrombectomy eligibility assessed. Results between software packages were compared and categorized by NIHSS score, scanner manufacturer/model, and institution.
Results: Primary analysis of 362 cases found statistically significant differences in both software's volume estimations, with subgroup analysis showing these differences were driven by results from a single scanner model, the Canon Aquilion One. Viz.ai provided larger estimates with mean differences of 8cc and 18cc for core and penumbra, respectively (p<0.001). NIHSS subgroup analysis also showed systematically larger Viz.ai volumes (p<0.001). Despite volume differences, a significant difference in thrombectomy eligibility was not found. Additional subgroup analysis showed significant differences in penumbra volume for the Phillips Ingenuity scanner, and thrombectomy eligibility for the Canon Aquilion One scanner at one center (7 % increased eligibility with Viz.ai, p=0.03).
Conclusions: Despite systematic differences in core and penumbra volume estimates between Viz.ai and RAPID.AI, DEFUSE-3 eligibility was not statistically different in primary or NIHSS subgroup analysis. A DEFUSE-3 eligibility difference, however, was seen on one scanner at one institution, suggesting scanner model and local CTP protocols can influence performance and cause discrepancies in thrombectomy eligibility. We thus recommend centers discuss optimal scanning protocols with software vendors and scanner manufacturers to maximize CTP accuracy.