Real-world evaluation of Brainomix 360 software

Background and Purpose: Brainomix 360 Stroke is an artificial intelligence-based decision support tool that aids the interpretation of CT imaging in the context of acute stroke. The aim of this study was to prospectively evaluate the performance of Brainomix 360 Stroke in an unselected cohort of patients with suspected acute ischemic stroke.

Methods: The study cohort included all patients admitted to the University College London Hospital Hyperacute Stroke Unit between October 2021 and April 2022. For e-ASPECTS and e-CTA, the ground truth was determined by a neuroradiologist with access to all clinical and imaging data. For e-CTP, the core infarct and ischemic penumbra values were compared with those derived from syngo.via.

Results: A total of 1,163 studies were performed in 551 patients; 1,130 (97.2%) were successfully processed in an average of 4 minutes. For acute MCA territory ischemia, e-ASPECTS had an accuracy of 77.0%. Identification of acute hemorrhage was highly accurate (97.8%). The accuracy of e-CTA for large vessel occlusions was 91.5%, and e-CTP volumes strongly correlated with syngo.via (ρ = 0.804–0.979).

Conclusion: Brainomix 360 Stroke software provides rapid and reliable analysis of CT imaging in the acute stroke setting. However, it should be used as an adjunct to expert interpretation rather than a standalone decision-making tool.