18 Automated vendor-independent detection and quantification of aortic stenosis from a 3-chamber bSSFP cine view

Introduction Cardiac magnetic resonance imaging (CMR) evaluates aortic stenosis (AS) and concurrent myocardial abnormalities. Initial diagnosis of aortic valve (AV) disease can occur during CMR scanning, but universal multiparametric AS assessment is inefficient. An automated strategy for identifying AS patients from the 3-chamber view (part of all protocols) is therefore valuable. We observed that in patients with AS, there was reduced blood signal intensity in the ascending aorta compared to the cardiac chambers. We investigated the diagnostic potential of quantifying this signal reduction as a radiomic marker for AS severity. We introduce an AI-based solution to enhance this metric's precision and reproducibility. Materials and Methods This was a multi-centre, retrospective cohort study with 249 patients. Signal intensity was quantified within a 1cm2 region of interest (ROI) in the ascending aorta (Ao), left ventricle (LV), and left atrium (LA) (figure 1). Normalised Ao:LV ratio was calculated and compared against echocardiographic gold standards of AS severity: e.g., dimensionless index (DI) and AV maximum velocity, utilising Pearson correlation coefficients. Automated analysis was conducted using a point-tracking algorithm. Results The cohort (n = 249, median age 67 IQR 58–77, 63% male) was stratified into no AS (n=87), mild AS (n=52), moderate AS (n=53) or severe AS (n=57) based on gold-standard echocardiography. The Ao:LV signal ratio strongly correlated with echocardiography parameters (figure 2A-B). A ratio of Discussion The Ao:LV ratio is a novel, automatable radiomic marker with good correlation to echocardiographic parameters for AS severity assessment. Derived from routine 3CH bSSFP cines, it provides clinical information and could optimise clinical workflow by eliminating the need for unnecessary imaging sequences. Its multi-vendor compatibility allows generalizability across various scanning technologies. The algorithmic framework is designed for machine learning adaptation, offering the potential for real-time analysis. Conclusion The Ao:LV ratio is a robust, simple tool for the initial diagnosis and severity assessment of AS available in a standard clinical protocol. This study demonstrates feasibility of automated Ao:LV computation which could enhance efficiency by targeting the appropriate use of patient-specific AV sequences. Acknowledgements KV is funded by the UK research and Innovation UKRI Centre for Doctoral Training in AI for Healthcare grant number EP/S023283/1. JH is funded by the British Heart Foundation FS/ICRF/22/26039. GDC is supported by the National Institute of Health Research (NIHR) Imperial Biomedical Research Centre (BRC).