Machine Learning Multiorgan Analysis of Coronary CT Angiography Body Composition, Myocardial Infarction, and
Alan Ranieri Guimaraes1, Steven E Williams1,2, Mark T Macmillan1,3
1British Heart Foundation Centre for Research Excellence, Institute for Neuroscience and Cardiovascular Research, University of Edinburgh, Chancellor's Building, 49 Little France Crescent, Edinburgh, United Kingdom.
Insights
Machine learning analysis of coronary CT angiography reveals body composition impacts 10-year outcomes. Lower skeletal muscle attenuation is linked to increased mortality and myocardial infarction risk.
Area of Science:
- Radiology
- Cardiovascular Imaging
- Artificial Intelligence in Medicine
Background:
- Coronary CT angiography (CCTA) offers prognostic insights beyond coronary findings.
- Machine learning (ML) can derive detailed body composition from CCTA images.
- Understanding multiorgan composition's role in cardiovascular outcomes is crucial.
Purpose of the Study:
- To assess associations between ML-derived multiorgan body composition and 10-year outcomes.
- To investigate the prognostic value of body composition in the SCOT-HEART trial.
- To identify specific body composition metrics related to mortality and myocardial infarction (MI).
Main Methods:
- Retrospective analysis of 1722 patients from the SCOT-HEART trial using wide field-of-view CCTA images.
- Application of the TotalSegmentator model for automated organ segmentation and calculation of volume and mean attenuation.
- Construction of multivariable Cox proportional hazards models adjusted for age, sex, and scan length to predict all-cause mortality and MI.
Main Results:
- Higher lung attenuation, lower liver attenuation, and greater torso fat volume were associated with coronary artery disease.
- Increased skeletal muscle attenuation correlated with reduced all-cause mortality (HR, 0.61).
- Lower skeletal muscle attenuation was independently associated with increased risk of mortality (HR, 1.85) and MI (HR, 1.58) after adjustment for coronary calcium score.
Conclusions:
- ML-driven multiorgan body composition analysis from CCTA provides significant prognostic information.
- Skeletal muscle attenuation emerged as a particularly strong predictor of adverse cardiovascular outcomes.
- CCTA-derived body composition can enhance risk stratification beyond traditional coronary findings.
Abstract:
Background Coronary CT angiography provides prognostic information in addition to coronary findings. Purpose To evaluate associations between machine learning-derived multiorgan body composition and 10-year outcomes in the SCOT-HEART (Scottish Computed Tomography of the Heart) trial. Materials and Methods Wide field-of-view images of 1722 patients (recruited between November 2010 and September 2014) were retrospectively processed using the TotalSegmentator model. The volume and mean attenuation of segmented organs were calculated. Multivariable Cox proportional hazards models were constructed for all-cause mortality and myocardial infarction (MI), adjusted for age, sex, and scan length. Odds ratios or hazard ratios (HRs) and 95% CIs were calculated per 10-unit increase in attenuation or volume. Results Mortality and MI occurred in 133 (7.72%) and 106 (6.16%) of the 1722 patients, respectively (age, 57.5 years ± 9.5 [SD]; 55.7% male). Coronary artery disease was associated with greater lung attenuation (odds ratio, 1.04 [95% CI: 1.03, 1.06]; P < .001), lower liver attenuation (odds ratio, 0.87 [95% CI: 0.8, 0.95]; P = .034), and greater torso fat volume (odds ratio, 1.01 [95% CI: 1.01, 1.02]; P < .001) after multivariable adjustment. Increased skeletal muscle attenuation was associated with lower all-cause mortality (HR, 0.61 [95% CI: 0.47, 0.79]; P < .001) after multivariable adjustment. MI was associated with increased myocardial volume (HR, 1.09 [95% CI: 1.01, 1.16]; P = .018) and decreased rib (HR, 0.98 [95% CI: 0.96, 1.0]; P = .043) and skeletal muscle (HR, 0.69 [95% CI: 0.54, 0.87]; P = .002) attenuation after multivariable adjustment. However, when further adjusted for coronary calcium score, only skeletal muscle attenuation was associated with MI (HR, 0.72 [95% CI: 0.57, 0.91]; P = .007). Patients with skeletal muscle attenuation below the median had a higher risk of mortality (HR, 1.85 [95% CI: 1.30, 2.64]; P < .001) or experience MI (HR, 1.58 [95% CI: 1.07, 2.33]; P = .022). Conclusion Multiorgan body composition analysis using coronary CT angiography provided additional prognostic information, among which skeletal muscle attenuation was particularly important. ClinicalTrials.gov identifier: NCT01149590 © RSNA, 2026 Supplemental material is available for this article.
Related Concept Videos
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:28Imaging Studies for Cardiovascular System V: CT
01:30Acute Coronary Syndrome III: Diagnostic Studies