Deep learning model to quantify left atrium volume on routine non-contrast chest CT and predict adverse outcomes

Low-dose computed tomography (LDCT) are performed routinely for lung cancer screening. However, a large amount of nonpulmonary data from these scans remains unassessed. We aimed to validate a deep learning model to automatically segment and measure left atrial (LA) volumes from routine NCCT and eval...

Full description

Saved in:
Bibliographic Details
Published in:Journal of cardiovascular computed tomography 2022-05, Vol.16 (3), p.245-253
Main Authors: Aquino, Gilberto J., Chamberlin, Jordan, Mercer, Megan, Kocher, Madison, Kabakus, Ismail, Akkaya, Selcuk, Fiegel, Matthew, Brady, Sean, Leaphart, Nathan, Dippre, Andrew, Giovagnoli, Vincent, Yacoub, Basel, Jacob, Athira, Gulsun, Mehmet Akif, Sahbaee, Pooyan, Sharma, Puneet, Waltz, Jeffrey, Schoepf, U. Joseph, Baruah, Dhiraj, Emrich, Tilman, Zimmerman, Stefan, Field, Michael E., Agha, Ali M., Burt, Jeremy R.
Format: Article
Language:English
Subjects:
Artificial intelligence
Atrial fibrillation
Deep learning
Heart failure
Left atrium volume
Low-dose computed tomography
Lung cancer screening
Major adverse cardiac and cerebrovascular events
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Low-dose computed tomography (LDCT) are performed routinely for lung cancer screening. However, a large amount of nonpulmonary data from these scans remains unassessed. We aimed to validate a deep learning model to automatically segment and measure left atrial (LA) volumes from routine NCCT and evaluate prediction of cardiovascular outcomes. We retrospectively evaluated 273 patients (median age 69 years, 55.5% male) who underwent LDCT for lung cancer screening. LA volumes were quantified by three expert cardiothoracic radiologists and a prototype AI algorithm. LA volumes were then indexed to the body surface area (BSA). Expert and AI LA volume index (LAVi) were compared and used to predict cardiovascular outcomes within five years. Logistic regression with appropriate univariate statistics were used for modelling outcomes. There was excellent correlation between AI and expert results with an LAV intraclass correlation of 0.950 (0.936–0.960). Bland-Altman plot demonstrated the AI underestimated LAVi by a mean 5.86 ​mL/m2. AI-LAVi was associated with new-onset atrial fibrillation (AUC 0.86; OR 1.12, 95% CI 1.08–1.18, p ​
ISSN:1934-5925
1876-861X
DOI:10.1016/j.jcct.2021.12.005