AUTHOR=Weyland Charlotte Sabine , Papanagiotou Panagiotis , Schmitt Niclas , Joly Olivier , Bellot Pau , Mokli Yahia , Ringleb Peter Arthur , Kastrup A. , Möhlenbruch Markus A. , Bendszus Martin , Nagel Simon , Herweh Christian 

TITLE=Hyperdense Artery Sign in Patients With Acute Ischemic Stroke–Automated Detection With Artificial Intelligence-Driven Software

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.807145

DOI=10.3389/fneur.2022.807145

ISSN=1664-2295

ABSTRACT=Background and Purpose
Hyperdense artery sign (HAS) on non-contrast computed tomography (NCCT) can indicate a large vessel occlusion (LVO) in patients with acute ischemic stroke. HAS detection belongs to routine reporting in stroke patients and could help to identify patients in whom LVO is not suspected initially. We sought to evaluate automated HAS detection of an artificial intelligence driven software and compared its performance to that of trained physicians.
Methods
NCCT scans from 154 patients with and without LVO proven by CT angiography (CTA) were independently rated for HAS by two blinded neuroradiologists and an AI-driven algorithm (Brainomix®). Sensitivity and specificity were analyzed for the clinicians and the software. As a secondary analysis, the clot length was automatically calculated by the software and compared with the length manually outlined on CTA images as reference standard. 
Results
84/154 patients (54.5%) had CTA-proven LVO. HAS on the correct side was detected with a sensitivity and specificity of 0.77 (CI: 0.66-0.85) and 0.87 (0.77-0.94), 0.8 (0.69-0.88) and 0.97 (0.89-0.99) and 0.93 (0.84-0.97) and 0.71(0.59-0.81) by the software and reader 1 and 2, respectively. The automated estimation of the thrombus length was in moderate agreement with the CTA-based reference standard (ICC 0.73). 

Conclusions
Automated detection of HAS and estimation of thrombus length on NCCT by the tested software is feasible with a sensitivity and specificity comparable to that of trained neuroradiologists.