Evaluating artificial intelligence software for delineating hemorrhage extent on CT brain imaging in stroke: AI delineation of ICH on CT.

Vacek, Adam; Mair, Grant; White, Philip; Bath, Philip M.; Muir, Keith W.; Al-Shahi Salman, Rustam; Martin, Chloe; Dye, David; Chappell, Francesca M.; von Kummer, Rüdiger; Macleod, Malcolm; Sprigg, Nikola; Wardlaw, Joanna M.

Abstract

Background: : The extent and distribution of intracranial hemorrhage (ICH) directly affects clinical management. Artificial intelligence (AI) software can detect and may delineate ICH extent on brain CT. We evaluated e-ASPECTS software (Brainomix Ltd.) performance for ICH delineation. Methods: : We qualitatively assessed software delineation of ICH on CT using patients from six stroke trials. We assessed hemorrhage delineation in five compartments: lobar, deep, posterior fossa, intraventricular, extra-axial. We categorized delineation as excellent, good, moderate, or poor. We assessed quality of software delineation with number of affected compartments in univariate analysis (Kruskall-Wallis test) and ICH location using logistic regression (dependent variable: dichotomous delineation categories ‘excellent-good’ versus ‘moderate-poor’), and report odds ratios (OR) and 95 % confidence intervals (95 %CI). Results: : From 651 patients with ICH (median age 75 years, 53 % male), we included 628 with assessable CTs. Software delineation of ICH extent was ‘excellent’ in 189/628 (30 %), ‘good’ in 255/628 (41 %), ‘moderate’ in 127/628 (20 %), and ‘poor’ in 57/628 cases (9 %). The quality of software delineation of ICH was better when fewer compartments were affected (Z = 3.61-6.27; p = 0.0063). Software delineation of ICH extent was more likely to be ‘excellent-good’ quality when lobar alone (OR = 1.56, 95 %CI = 0.97-2.53) but ‘moderate-poor’ with any intraventricular (OR = 0.56, 95 %CI = 0.39-0.81, p = 0.002) or any extra-axial (OR = 0.41, 95 %CI = 0.27-0.62, p<0.001) extension. Conclusions: : Delineation of ICH extent on stroke CT scans by AI software was excellent or good in 71 % of cases but was more likely to over- or under-estimate extent when ICH was either more extensive, intraventricular, or extra-axial.

• Journal Article Type: Article
• Acceptance Date: Nov 21, 2023
• Online Publication Date: Nov 25, 2023
• Publication Date: Jan 1, 2024
• Deposit Date: Nov 23, 2023
• Publicly Available Date: Nov 26, 2024
• Journal: Journal of Stroke and Cerebrovascular Diseases
• Print ISSN: 1052-3057
• Electronic ISSN: 1532-8511
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 33
• Issue: 1
• Article Number: 107512
• DOI: https://doi.org/10.1016/j.jstrokecerebrovasdis.2023.107512
• Keywords: Artificial intelligence; CT; Stroke; Hemorrhage
• Public URL: https://nottingham-repository.worktribe.com/output/27596314
• Publisher URL: https://www.strokejournal.org/article/S1052-3057(23)00533-5/fulltext
• Additional Information: This article is maintained by: Elsevier; Article Title: Evaluating artificial intelligence software for delineating hemorrhage extent on CT brain imaging in stroke; Journal Title: Journal of Stroke and Cerebrovascular Diseases; CrossRef DOI link to publisher maintained version: https://doi.org/10.1016/j.jstrokecerebrovasdis.2023.107512; Content Type: article; Copyright: © 2023 The Authors. Published by Elsevier Inc.