Research Article| Volume 16, ISSUE 3, P245-253, May 2022

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

Published:December 16, 2021DOI:



      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 ​< ​0.001), HF hospitalization (AUC 0.90; OR 1.07, 95% CI 1.04–1.13, p ​< ​0.001), and MACCE (AUC 0.68; OR 1.04, 95% CI 1.01–1.07, p ​= ​0.01).


      This novel deep learning algorithm for automated measurement of LA volume on lung cancer screening scans had excellent agreement with manual quantification. AI-LAVi is significantly associated with increased risk of new-onset atrial fibrillation, HF hospitalization, and major adverse cardiac and cerebrovascular events within 5 years.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      Full access to the journal is a member benefit for SCCT Members, Login via the SCCT website to access all journal content.


      Subscribe to Journal of Cardiovascular Computed Tomography
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Chamberlin J.
        • Kocher M.R.
        • Waltz J.
        • et al.
        Automated detection of lung nodules and coronary artery calcium using artificial intelligence on low-dose CT scans for lung cancer screening: accuracy and prognostic value.
        BMC Med. 2021; 19: 55
        • Bruns S.
        • Wolterink J.M.
        • Takx R.A.P.
        • et al.
        Deep learning from dual-energy information for whole-heart segmentation in dual-energy and single-energy non-contrast-enhanced cardiac CT.
        Med Phys. 2020; 47: 5048-5060
        • Bos D.
        • Leening M.J.G.
        Leveraging the coronary calcium scan beyond the coronary calcium score.
        Eur Radiol. 2018; 28: 3082-3087
        • Shahzad R.
        • Bos D.
        • Budde R.P.
        • et al.
        Automatic segmentation and quantification of the cardiac structures from non-contrast-enhanced cardiac CT scans.
        Phys Med Biol. 2017; 62: 3798-3813
        • Fredgart M.H.
        • Carter-Storch R.
        • Moller J.E.
        • et al.
        Measurement of left atrial volume by 2D and 3D non-contrast computed tomography compared with cardiac magnetic resonance imaging.
        J Cardiovasc Comput Tomogr. 2018; 12: 316-319
        • Cardona A.
        • Trovato V.
        • Nagaraja H.N.
        • Raman S.V.
        • Harfi T.T.
        Left atrial volume quantification using coronary calcium score scan: feasibility, reliability and reproducibility analysis of a standardized approach.
        Int J Cardiol Heart Vasc. 2019; 23: 100351
        • Baskaran L.
        • Al'Aref S.J.
        • Maliakal G.
        • et al.
        Automatic segmentation of multiple cardiovascular structures from cardiac computed tomography angiography images using deep learning.
        PLoS One. 2020; 15e0232573
        • Du X.
        • Yin S.
        • Tang R.
        • et al.
        Segmentation and visualization of left atrium through a unified deep learning framework.
        Int J Comput Assist Radiol Surg. 2020; 15: 589-600
        • Wolf F.
        • Ourednicek P.
        • Loewe C.
        • et al.
        Evaluation of left atrial function by multidetector computed tomography before left atrial radiofrequency-catheter ablation: comparison of a manual and automated 3D volume segmentation method.
        Eur J Radiol. 2010; 75: e141-e146
        • Kay F.U.
        • Abbara S.
        • Joshi P.H.
        • Garg S.
        • Khera A.
        • Peshock R.M.
        Identification of high-risk left ventricular hypertrophy on calcium scoring cardiac computed tomography scans: validation in the DHS.
        Circ Cardiovasc Imaging. 2020; 13e009678
        • Hoit B.D.
        Left atrial size and function: role in prognosis.
        J Am Coll Cardiol. 2014; 63: 493-505
        • Mahabadi A.A.
        • Geisel M.H.
        • Lehmann N.
        • et al.
        Association of computed tomography-derived left atrial size with major cardiovascular events in the general population: the Heinz Nixdorf Recall Study.
        Int J Cardiol. 2014; 174: 318-323
        • Mahabadi A.A.
        • Lehmann N.
        • Mohlenkamp S.
        • et al.
        Noncoronary measures enhance the predictive value of cardiac CT above traditional risk factors and CAC score in the general population.
        JACC Cardiovasc Imaging. 2016; 9: 1177-1185
        • Koh A.S.
        • Murthy V.L.
        • Sitek A.
        • et al.
        Left atrial enlargement increases the risk of major adverse cardiac events independent of coronary vasodilator capacity.
        Eur J Nucl Med Mol Imag. 2015; 42: 1551-1561
        • Kohl S.A.A.
        • Romera-Paredes B.
        • Meyer C.
        • et al.
        A Probabilistic U-Net for Segmentation of Ambiguous Images Proceedings of the 32nd International Conference on Neural Information Processing Systems.
        • Lang R.M.
        • Badano L.P.
        • Mor-Avi V.
        • et al.
        Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging.
        Eur Heart J Cardiovasc Imaging. 2015; 16: 233-270
        • Olsen F.J.
        • Bertelsen L.
        • de Knegt M.C.
        • et al.
        Multimodality cardiac imaging for the assessment of left atrial function and the association with atrial Arrhythmias.
        Circ Cardiovasc Imaging. 2016; 9
        • Commandeur F.
        • Goeller M.
        • Betancur J.
        • et al.
        Deep learning for quantification of epicardial and thoracic adipose tissue from non-contrast CT.
        IEEE Trans Med Imag. 2018; 37: 1835-1846
        • Isgum I.
        • Rutten A.
        • Prokop M.
        • et al.
        Automated aortic calcium scoring on low-dose chest computed tomography.
        Med Phys. 2010; 37: 714-723