Deep convolutional neural networks to predict cardiovascular risk from computed tomography.

Journal: Nature communications
PMID: 33514711

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.

Authors

  • Roman Zeleznik
    Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, United States of America.
  • Borek Foldyna
    From the MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68 Varosmajor St, 1122 Budapest, Hungary (M.K., J.K., B.M., P.M.H.); Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (J.K., Y.K., A.I., M.T.L., B.F., H.J.A., U.H.); Center for Cause of Death Investigation, Faculty of Medicine, Hokkaido University, Hokkaido, Japan (Y.K.); Department for Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Freiburg, Germany (C.L.S.); and Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (H.J.A.).
  • Parastou Eslami
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Jakob Weiss
    Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Harvard Medical School, Boston, MA, USA.
  • Ivanov Alexander
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Jana Taron
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Chintan Parmar
    Departments of Radiation Oncology.
  • Raza M Alvi
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Dahlia Banerji
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Mio Uno
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Yasuka Kikuchi
    From the MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68 Varosmajor St, 1122 Budapest, Hungary (M.K., J.K., B.M., P.M.H.); Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (J.K., Y.K., A.I., M.T.L., B.F., H.J.A., U.H.); Center for Cause of Death Investigation, Faculty of Medicine, Hokkaido University, Hokkaido, Japan (Y.K.); Department for Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Freiburg, Germany (C.L.S.); and Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (H.J.A.).
  • Júlia Karády
    From the MTA-SE Cardiovascular Imaging Research Group, Heart and Vascular Center, Semmelweis University, 68 Varosmajor St, 1122 Budapest, Hungary (M.K., J.K., B.M., P.M.H.); Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Mass (J.K., Y.K., A.I., M.T.L., B.F., H.J.A., U.H.); Center for Cause of Death Investigation, Faculty of Medicine, Hokkaido University, Hokkaido, Japan (Y.K.); Department for Diagnostic and Interventional Radiology, Medical Center-University of Freiburg, Freiburg, Germany (C.L.S.); and Department of Radiation Oncology, Dana-Farber Cancer Institute, Brigham and Women's Hospital, Harvard Medical School, Boston, Mass (H.J.A.).
  • Lili Zhang
    Pharmaceutics Department, Institute of Medicinal Biotechnology, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, 100050, PR China.
  • Jan-Erik Scholtz
    Cardiovascular Imaging Research Center, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
  • Thomas Mayrhofer
    Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston.
  • Asya Lyass
    Baim Institute for Clinical Research, Boston, MA; Department of Mathematics and Statistics, Boston University, Boston, MA.
  • Taylor F Mahoney
    Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA.
  • Joseph M Massaro
    Department of Biostatistics, Boston University, Boston, MA.
  • Ramachandran S Vasan
    Framingham Heart Study, Framingham, Massachusetts.
  • Pamela S Douglas
    See the Notes section for the full list of authors' affiliations.
  • Udo Hoffmann
    Department of Radiology, Massachusetts General Hospital, Boston.
  • Michael T Lu
    Cardiovascular Imaging Research Center, Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston.
  • Hugo J W L Aerts
    Department of Radiation Oncology, Brigham and Women's Hospital, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, United States.

Keywords

External Resources

Popular Topics
Recent Journals