» Articles » PMID: 33514711

Deep Convolutional Neural Networks to Predict Cardiovascular Risk from Computed Tomography

Abstract

Coronary artery calcium is an accurate predictor of cardiovascular events. While it is visible on all computed tomography (CT) scans of the chest, this information is not routinely quantified as it requires expertise, time, and specialized equipment. Here, we show a robust and time-efficient deep learning system to automatically quantify coronary calcium on routine cardiac-gated and non-gated CT. As we evaluate in 20,084 individuals from distinct asymptomatic (Framingham Heart Study, NLST) and stable and acute chest pain (PROMISE, ROMICAT-II) cohorts, the automated score is a strong predictor of cardiovascular events, independent of risk factors (multivariable-adjusted hazard ratios up to 4.3), shows high correlation with manual quantification, and robust test-retest reliability. Our results demonstrate the clinical value of a deep learning system for the automated prediction of cardiovascular events. Implementation into clinical practice would address the unmet need of automating proven imaging biomarkers to guide management and improve population health.

Citing Articles

Applications of Artificial Intelligence for the Prediction and Diagnosis of Cancer Therapy-Related Cardiac Dysfunction in Oncology Patients.

Scalia I, Pathangey G, Abdelnabi M, Ibrahim O, Abdelfattah F, Pereyra Pietri M Cancers (Basel). 2025; 17(4).

PMID: 40002200 PMC: 11852369. DOI: 10.3390/cancers17040605.


OPPORTUNISTIC ASSESSMENT OF CARDIOVASCULAR RISK USING AI-DERIVED STRUCTURAL AORTIC AND CARDIAC PHENOTYPES FROM NON-CONTRAST CHEST COMPUTED TOMOGRAPHY.

Oo D, Sturniolo A, Jung M, Langenbach M, Foldyna B, Kiel D medRxiv. 2025; .

PMID: 39974056 PMC: 11839003. DOI: 10.1101/2025.01.28.25321302.


Association of Epicardial Adipose Tissue Changes on Serial Chest CT Scans with Mortality: Insights from the National Lung Screening Trial.

Langenbach I, Hadzic I, Zeleznik R, Langenbach M, Maintz D, Mayrhofer T Radiology. 2025; 314(2):e240473.

PMID: 39964263 PMC: 11868846. DOI: 10.1148/radiol.240473.


Medical multimodal multitask foundation model for lung cancer screening.

Niu C, Lyu Q, Carothers C, Kaviani P, Tan J, Yan P Nat Commun. 2025; 16(1):1523.

PMID: 39934138 PMC: 11814333. DOI: 10.1038/s41467-025-56822-w.


Opportunistic assessment of steatotic liver disease in lung cancer screening eligible individuals.

Weiss J, Bernatz S, Johnson J, Thiriveedhi V, Mak R, Fedorov A J Intern Med. 2025; 297(3):276-288.

PMID: 39868889 PMC: 11846076. DOI: 10.1111/joim.20053.


References
1.
Lu M, Onuma O, Massaro J, DAgostino Sr R, ODonnell C, Hoffmann U . Lung Cancer Screening Eligibility in the Community: Cardiovascular Risk Factors, Coronary Artery Calcification, and Cardiovascular Events. Circulation. 2016; 134(12):897-9. PMC: 5031246. DOI: 10.1161/CIRCULATIONAHA.116.023957. View

2.
Huang Y, Wu F, Wang Y, Ju Y, Mar G, Chuo C . Reliable categorisation of visual scoring of coronary artery calcification on low-dose CT for lung cancer screening: validation with the standard Agatston score. Eur Radiol. 2012; 23(5):1226-33. DOI: 10.1007/s00330-012-2726-5. View

3.
Douglas P, Hoffmann U, Lee K, Mark D, Al-Khalidi H, Anstrom K . PROspective Multicenter Imaging Study for Evaluation of chest pain: rationale and design of the PROMISE trial. Am Heart J. 2014; 167(6):796-803.e1. PMC: 4044617. DOI: 10.1016/j.ahj.2014.03.003. View

4.
Qazi S, Massaro J, Chuang M, DAgostino Sr R, Hoffmann U, ODonnell C . Increased Aortic Diameters on Multidetector Computed Tomographic Scan Are Independent Predictors of Incident Adverse Cardiovascular Events: The Framingham Heart Study. Circ Cardiovasc Imaging. 2017; 10(12). PMC: 5728667. DOI: 10.1161/CIRCIMAGING.117.006776. View

5.
Patel M, Calhoon J, Dehmer G, Grantham J, Maddox T, Maron D . Correction to: ACC/AATS/AHA/ASE/ASNC/SCAI/SCCT/STS 2017 Appropriate Use Criteria for Coronary Revascularization in Patients With Stable Ischemic Heart Disease. J Nucl Cardiol. 2018; 25(6):2191-2192. DOI: 10.1007/s12350-018-1292-x. View