Deep learning-enabled analysis of medical images identifies cardiac sphericity as an early marker of cardiomyopathy and related outcomes

doi:10.1016/j.medj.2023.02.009

Med

Volume 4, Issue 4, 14 April 2023, Pages 252-262.e3

https://doi.org/10.1016/j.medj.2023.02.009 Get rights and content

Under a Creative Commons license

open access

Highlights

•
Measurement of left ventricular sphericity can be automated using deep learning
•
Sphericity predicts incident cardiomyopathy independent of traditional factors
•
Genome-wide association study of sphericity identifies loci relevant to cardiomyopathy

Context and significance

Imaging plays an important role in the diagnosis and management of heart disease. Modalities such as ultrasound and magnetic resonance imaging (MRI) allow clinicians to visualize manifestations of heart disease, including enlargement of the heart chambers or decrease in the pumping strength of the heart muscle. Here, researchers hypothesized that beyond size and function, shape may carry additional information about heart health. They use artificial intelligence to analyze >30,000 heart MRIs and show that even when the size and function are normal, the roundness (or “sphericity”) of the heart predicts risk for heart conditions. Additionally, heart roundness is impacted by genetic influences. Consideration of heart shape may help improve our ability to identify people at risk for developing heart disease.

Summary

Background

Quantification of chamber size and systolic function is a fundamental component of cardiac imaging. However, the human heart is a complex structure with significant uncharacterized phenotypic variation beyond traditional metrics of size and function. Examining variation in cardiac shape can add to our ability to understand cardiovascular risk and pathophysiology.

Methods

We measured the left ventricle (LV) sphericity index (short axis length/long axis length) using deep learning-enabled image segmentation of cardiac magnetic resonance imaging data from the UK Biobank. Subjects with abnormal LV size or systolic function were excluded. The relationship between LV sphericity and cardiomyopathy was assessed using Cox analyses, genome-wide association studies, and two-sample Mendelian randomization.

Findings

In a cohort of 38,897 subjects, we show that a one standard deviation increase in sphericity index is associated with a 47% increased incidence of cardiomyopathy (hazard ratio [HR]: 1.47, 95% confidence interval [CI]: 1.10–1.98, p = 0.01) and a 20% increased incidence of atrial fibrillation (HR: 1.20, 95% CI: 1.11–1.28, p < 0.001), independent of clinical factors and traditional magnetic resonance imaging (MRI) measurements. We identify four loci associated with sphericity at genome-wide significance, and Mendelian randomization supports non-ischemic cardiomyopathy as causal for LV sphericity.

Conclusions

Variation in LV sphericity in otherwise normal hearts predicts risk for cardiomyopathy and related outcomes and is caused by non-ischemic cardiomyopathy.

Funding

This study was supported by grants K99-HL157421 (D.O.) and KL2TR003143 (S.L.C.) from the National Institutes of Health.

Graphical abstract

CAT Scale

Translation to humans

Keywords

cardiomyopathy

atrial fibrillation

heart failure

sphericity index

artificial intelligence

deep learning

medical imaging

magnetic resonance imaging

genome-wide association study

Data and code availability

•
This paper analyzes UK Biobank data, which is available after the approval of an application at https://www.ukbiobank.ac.uk.
•
All original code has been deposited at https://github.com/vukadinovic936/UKB and is publicly available as of the date of publication. DOIs are listed in the key resources table.

Cited by (0)

⁸: Lead contact

Med

Clinical and Translational ArticleDeep learning-enabled analysis of medical images identifies cardiac sphericity as an early marker of cardiomyopathy and related outcomes