syngo.CT LVO Detection

syngo.CT LVO Detection is a radiological software application that analyzes CT angiography head images using artificial intelligence algorithms to identify large vessel occlusions (LVO) in the ICA, M1, and M2 segments. It provides computer-aided triage notifications to assist radiologists in prioritizing stroke cases, with output intended for informational purposes only and not for diagnostic use.

Both the subject device and predicate (syngo.CT Brain Hemorrhage) are notification-only, parallel workflow tools using AI algorithms to analyze head CT images in acute care settings. The subject device detects suspected stroke/LVO while the predicate detects hemorrhage; both flag findings for review, work with multiple scanner manufacturers, and deploy on similar platforms (syngo.via and SOMARIS systems).

IEC 62304 (medical device software life cycle), NEMA PS 3.1-3.20 (DICOM), ISO 14971 (risk management), IEC 62366-1 (usability engineering), ISO 15223-1 (symbols), and ISO 20417 (manufacturer information).

The device demonstrates substantial equivalence through identical intended use (computer-aided triage in acute care), similar technological characteristics (AI-based head CT analysis with notification output), and superior performance data (90.6% sensitivity and 88.8% specificity on 602 patient cases exceeding the predefined >80% threshold). Performance was consistent across multiple CT manufacturers, patient demographics, and stroke severity levels, demonstrating safe and effective operation equivalent to the predicate device.