Stroke is a major disease of the 21st century. Worldwide, it affects about 15 million people each year [1,2]. It is a leading cause of long-term disability and the second leading cause of death [3]. In the past 20 years, there has been a significant increase in the absolute number of stroke cases, with an increase of 70.0% in incidence, 102.0% in prevalence, and 43.0% in the number of deaths [4,5].

Stroke is classified in two types: hemorrhagic stroke which is caused by a leak of brain blood vessels creating an intracranial hemorrhage (ICH) and ischemic stroke (IS) which consists of an occlusion of a brain blood vessel that creates a lack of blood flow [6]. Overall, approximately 20% of strokes are hemorrhagic and 80% ischemic [2].  

In the treatment of stroke "time is brain" because every minute of an untreated stroke has serious consequences on patient outcome [2]. When a stroke code is activated, a NCCT is performed to check for ICH, followed by a CTA for vessel occlusion; if confirmed, then the Alberta Stroke Program Early CT Score (ASPECTS) is calculated on NCCT by analyzing the 10 regions of the middle cerebral artery and internal carotid artery territory. An ASPECTS of 6 or higher is usually associated with patient eligibility for mechanical thrombectomy [7]. Hence, a high quality of imaging-based analyses during the stroke workflow is crucial for the adequate management of patients. 

This study aims to evaluate the performance of an FDA-cleared and/or CE-marked artificial intelligence (AI)-based application designed to identify cases with ICH and/or large vessel occlusion (LVO) and compute the ASPECT Score, in order to support clinicians in the stroke imaging workflow.