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

Abstract

BackgroundHyperdense artery sign (HAS) on non-contrast CT (NCCT) can indicate a large vessel occlusion (LVO) in patients with acute ischemic stroke. HAS detection belongs to routine reporting in patients with acute stroke and can help to identify patients in whom LVO is not initially suspected. We sought to evaluate automated HAS detection by commercial software and compared its performance to that of trained physicians against a reference standard.MethodsNon-contrast CT 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 the reference standard.ResultsAmong 154 patients, 84 (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 readers 1 and 2, respectively. The automated estimation of the thrombus length was in moderate agreement with the CTA-based reference standard [intraclass correlation coefficient (ICC) 0.73].ConclusionAutomated 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.

Predictive value of clot imaging in acute ischemic stroke: A systematic review of artificial intelligence and conventional studies

“…A recent large AI study, using a historical database of 24214 patients for training and 1453 patients for validation, established a machine learning algorithm and a software (MethinksLVO) [18] capable of rapidly and reliably predicting LVO from NCCT scans with slice thickness 3-to-5 mm. Weyland et al [23] tested a readily available software, Brainomix © (Oxford, UK). Shinohara et al developed [19] and tested [20] an interactive deep learning-assisted identification of HMCAS, on NCCT.…”

“…A growing number of articles are evaluating AI techniques that analyze the neuroimaging signs of the clot (or thrombus) occluding the arteries in ischemic stroke [13] [14] [15] [16] [17] [18] [19] [20] [21] [22] [23]. No systematic reviews were conducted so far to examine the progress made in developing AI methods that are using clot imaging derived parameters.…”

Automated Intracranial Clot Detection: A Promising Tool for Vascular Occlusion Detection in Non-Enhanced CT

“…Lower clot burden, smaller thrombus length, and more distal thrombus location are predictors of a better clinical and radiologic outcome [ 8 , 9 , 10 ]. Hyperdense clots are erythrocyte-rich and respond better to mechanical thrombectomy [ 11 , 12 , 13 ]. In contrast, isodense clots are rich in fibrin with increased elasticity and stiffness [ 14 , 15 ] and are associated with unsuccessful reperfusion by mechanical thrombectomy [ 16 ].…”

Automated Prediction of Proximal Middle Cerebral Artery Occlusions in Noncontrast Brain Computed Tomography

“…A few studies have reported that several features on noncontrast computed tomography (NCCT) are indicators of LVO, such as hyperdense arterial signs, 3 , 4 sulcal effacement, 5 and loss of gray-white matter differentiation. 6 While NCCT scans are highly accessible and offer fast acquisition, achieving an accurate diagnosis of LVO from these scans requires expertise in stroke, which is difficult to find in developing countries or hospitals in excessive demand.…”

“…Previous studies exploring automatic LVO detection using artificial intelligence encountered limitations such as a lack of robust external validation and interpretability in clinical usage. 3 , 4 , 6 To date, there have been a limited number of attempts aimed at extracting handcrafted features that hold clinical relevance to LVO, particularly about ischemic density changes and the presence of clots.…”