Deep learning for [F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis.

Journal: The Lancet. Digital health
Published Date:

Abstract

BACKGROUND: The rising global cancer burden has led to an increasing demand for imaging tests such as [F]fluorodeoxyglucose ([F]FDG)-PET-CT. To aid imaging specialists in dealing with high scan volumes, we aimed to train a deep learning artificial intelligence algorithm to classify [F]FDG-PET-CT scans of patients with lymphoma with or without hypermetabolic tumour sites.

Authors

  • Ida Häggström
    Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, NY 10065, United States. Electronic address: haeggsti@mskcc.org.
  • Doris Leithner
    From the Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY.
  • Jennifer Alvén
    Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden.
  • Gabriele Campanella
    Weill Cornell Medicine, New York, USA; Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, USA.
  • Murad Abusamra
    Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Honglei Zhang
    State Key Laboratory of Genetic Resources and Evolution, Kunming Institute of Zoology, Chinese Academy of Sciences, Kunming, 650223, Yunnan, China.
  • Shalini Chhabra
    Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Lucian Beer
    Department of Radiology, University of Cambridge, Cambridge CB2 0QQ, UK; Cancer Research UK Cambridge Centre, University of Cambridge, Cambridge CB2 0RE, UK; Department of Biomedical Imaging and Image-guided Therapy, Medical University Vienna, Vienna 1090, Austria. Electronic address: lb795@cam.ac.uk.
  • Alexander Haug
    Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria.
  • Gilles Salles
    Hospices Civils de Lyon, Department of Hematology, Université de Lyon, INSERM 1052, Lyon, France.
  • Markus Raderer
    Department of Medicine I, Medical University of Vienna, Vienna, Austria.
  • Philipp B Staber
    Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
  • Anton Becker
    University Hospital of Zurich, Ramistrasse 100, Zurich- 8091, Switzerland.
  • Hedvig Hricak
    Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY;
  • Thomas J Fuchs
    Weill Cornell Medicine, New York, USA; Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, USA; Department of Pathology, Memorial Sloan Kettering Cancer Center, New York, USA. Electronic address: gac2010@med.cornell.edu.
  • Heiko Schoder
    Radiology, Memorial Sloan Kettering Cancer Center, New York, New York, USA.
  • Marius E Mayerhoefer