qER-CTA (v1.0)

qER-CTA is a notification-only software tool that uses deep learning to analyze head CT angiography images for suspected large vessel occlusions (LVOs) in the brain's anterior circulation. It sends passive notifications to neurovascular specialists recommending review of flagged images, operating as a parallel workflow tool independent of standard clinical interpretation. The device analyzes the internal carotid artery and M1 segment of the middle cerebral artery in adults aged 22 and older and is not intended for diagnostic use or clinical decision-making.

qER-CTA uses image processing algorithms for LVO detection on DICOM head CTA images, similar to the predicate Viz LVO. Both employ deep learning-based classification to provide case-level outputs for worklist prioritization. The key difference is qER-CTA demonstrates higher algorithmic performance: sensitivity of 91.35% vs. predicate's 87.8%, specificity of 91.86% vs. predicate's 89.6%, and faster mean time to notification of 6.36 minutes versus 7.32 minutes.

ISO 13485:2016 (medical device quality management), IEC 62304:2006+A1:2015 (software lifecycle processes), and FDA guidance on premarket submission for device software functions (June 2023). Software verification and validation included unit testing, integration testing, regression testing, and user acceptance testing.

Both devices are Class II radiological computer-aided triage and notification software (21 CFR 892.2080, product code QAS) with identical intended use: notification-only parallel workflow tools analyzing head CTA for LVO in the anterior circulation using deep learning algorithms. The devices share the same modality, clinical target, input format, intended users (neurovascular specialists and radiologists), and operational principles. qER-CTA's superior performance metrics and faster notification time do not constitute new scientific technology—only improvements to an established algorithmic approach—making it substantially equivalent to Viz LVO (K223042).