Deep learning enables genetic analysis of the human thoracic aorta

Genome-wide association analyses identify variants associated with thoracic aortic diameter. A polygenic score for ascending aortic diameter was associated with a diagnosis of thoracic aortic aneurysm in independent samples. Enlargement or aneurysm of the aorta predisposes to dissection, an important cause of sudden death. We trained a deep learning model to evaluate the dimensions of the ascending and descending thoracic aorta in 4.6 million cardiac magnetic resonance images from the UK Biobank. We then conducted genome-wide association studies in 39,688 individuals, identifying 82 loci associated with ascending and 47 with descending thoracic aortic diameter, of which 14 loci overlapped. Transcriptome-wide analyses, rare-variant burden tests and human aortic single nucleus RNA sequencing prioritized genes including SVIL, which was strongly associated with descending aortic diameter. A polygenic score for ascending aortic diameter was associated with thoracic aortic aneurysm in 385,621 UK Biobank participants (hazard ratio = 1.43 per s.d., confidence interval 1.32-1.54, P = 3.3 x 10(-20)). Our results illustrate the potential for rapidly defining quantitative traits with deep learning, an approach that can be broadly applied to biomedical images.

Automated summary

Genome-wide association analyses identified variants associated with thoracic aortic diameter and polygenic score for ascending aortic diameter was correlated with a diagnosis of thoracic aortic aneurysm. Enlargement or aneurysm of the aorta predisposes to dissection, and a deep learning model along with genome-wide association studies successfully identified loci associated with ascending and descending thoracic aortic diameter, highlighting the potential for rapidly defining quantitative traits with deep learning in biomedical images.