Heart failure & cardiomyopathies

Deep Learning-Derived Cardiac Chamber Volumes and Mass From PET/Computed Tomography (CT) Attenuation Scans: Associations With Myocardial Flow Reserve and Heart Failure

Circ Cardiovasc ImagingPublished multivariable analysis

Authors' conclusion

Deep learning-derived chamber volumes and left ventricular mass from CT attenuation correction were predictive of heart failure hospitalization and reduced myocardial flow reserve in patients undergoing cardiac PET perfusion imaging. This anatomic data can be routinely reported along with other PET/CT parameters to improve risk prediction.

Study context

Population
Patients with cardiac PET/CTpatients with cardiac PET/CT from 6 sites
Participants
18,079 patients
Comparison
Deep learning-derived CT chamber volumes and left ventricular mass in association with heart failure hospitalization and reduced myocardial flow reserve
Outcome
Heart failure hospitalization
Follow-up
Median 4.3 years
Methodological details6 sites
  • 6 sites

Main finding

As reported in the abstract

Patients who experienced heart failure hospitalization

1721

9.5%

Patients with 3 or 4 abnormal chamber volumes vs patients with normal volumes: likelihood of heart failure hospitalization

7×

Further findings

OutcomeHR (95% CI)
Heart failure hospitalization, per chamber measureLeft atrial volume · adjusted · In adjusted analyses1.25 (1.19–1.30)
Heart failure hospitalization, per chamber measureRight atrial volume · adjusted · In adjusted analyses1.29 (1.23–1.35)
Heart failure hospitalization, per chamber measureRight ventricular volume · adjusted · In adjusted analyses1.25 (1.20–1.31)
Heart failure hospitalization, per chamber measureLeft ventricular volume · adjusted · In adjusted analyses1.27 (1.23–1.35)
Heart failure hospitalization, per chamber measureLeft ventricular mass · adjusted · In adjusted analyses1.25 (1.18–1.32)

Reduced myocardial flow reserve

Odds ratio (95% CI)
Left atrial volumeMultivariable · In multivariable analyses1.14 (1.0–1.19)
Ventricular massIn multivariable analyses1.12 (1.6–1.17)
  • Reduced myocardial flow reserve: multivariable; CI as printed (lower bound 1.6 exceeds estimate)

Original publication

Deep Learning-Derived Cardiac Chamber Volumes and Mass From PET/CT Attenuation Scans: Associations With Myocardial Flow Reserve and Heart Failure. Circ Cardiovasc Imaging. Published 13 May 2025. doi:10.1161/circimaging.124.018188

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.