Background: Aortic stiffness is associated with increased risk of cardiovascular events. Deep learning on large cardiac magnetic resonance (CMR) imaging samples has enabled detailed characterization of cardiac shape and function for use in genome-wide association studies (GWAS), leading to improved understanding of genetic aetiology of cardiovascular diseases (CVDs). Aim: We present a novel CMR-based pressure-independent measure of aortic stiffness, identify genetic factors and biological determinants using GWAS analysis of CMR imaging data from the UK Biobank. Methods: A pre-trained neural network was used to segment CMR images of participants in the UK Biobank to quantify ascending aorta diameter, which together with contemporaneous systolic and diastolic blood pressure measurements were used to calculate a pressure-independent measure of aortic stiffness ( β 0 ). The measurement assumes an exponential relationship between pressure and aortic diameter. We performed a GWAS on β 0 in 45,789 participants of European ancestry, excluding individuals with a prior history of CVDs. We performed stepwise conditional joint analysis to identify conditionally independent lead variants, and then defined a locus based on a 500kb flanking region centered on the variant. For each locus, we evaluated and combined scores from four complimentary approaches: variant-to-gene, polygenic priority score, gene-based association test and nearest gene. Candidate gene with the highest aggregate score was identified as the putative effector gene. We performed a pathway enrichment analysis for putative effector gene to identify potential biological pathways involving β 0 . Results: We identified 17 independent lead variants from the GWAS (Figure A). We were able to identify putative effector genes at 16 of 17 genomic loci (Figure B, one locus was not resolved). Among the putative effectors were ELN and LTBP4, genes implicated in elastin fiber formation pathway (p=1.9E-2); ELN, HAS2 and LTBP4 associated with extracellular matrix assembly pathway (p=7.5E-3), and ULK4, ARHGAP24, ELN, HAS2, SVIL, ARHGAP22, CDH13, SMG6 , and LTBP4 linked to regulation of cellular component organization (p=2.6E-2). Conclusion: A GWAS of CMR-derived aortic stiffness identified 17 independent loci, suggesting its links with genetic influences on extracellular matrix and cellular component organization. These findings provide insights into the determinants of aortic stiffness that may inform future mechanistic studies.