Towards radiologist-level cancer risk assessment in CT lung screening using deep learning.

Journal: Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Published Date:

Abstract

PURPOSE: Lung cancer is the leading cause of cancer mortality in the US, responsible for more deaths than breast, prostate, colon and pancreas cancer combined and large population studies have indicated that low-dose computed tomography (CT) screening of the chest can significantly reduce this death rate. Recently, the usefulness of Deep Learning (DL) models for lung cancer risk assessment has been demonstrated. However, in many cases model performances are evaluated on small/medium size test sets, thus not providing strong model generalization and stability guarantees which are necessary for clinical adoption. In this work, our goal is to contribute towards clinical adoption by investigating a deep learning framework on larger and heterogeneous datasets while also comparing to state-of-the-art models.

Authors

  • Stojan Trajanovski
    Philips Research, Eindhoven, 5656 AE, The Netherlands.
  • Dimitrios Mavroeidis
    Philips Research, Eindhoven, 5656 AE, The Netherlands.
  • Christine Leon Swisher
    Human Longevity, Inc., San Diego, CA, 92121, USA.
  • Binyam Gebrekidan Gebre
    Philips Research, Eindhoven, 5656 AE, The Netherlands.
  • Bastiaan S Veeling
    Machine Learning lab, University of Amsterdam, 1090 GH Amsterdam and, Philips Research, Eindhoven, 5656 AE, The Netherlands.
  • Rafael Wiemker
    Philips Research France, 92150 Suresnes, France.
  • Tobias Klinder
    Philips Research, Hamburg, 22335, Germany.
  • Amir Tahmasebi
  • Shawn M Regis
    Lahey Hospital & Medical Center, Burlington, MA, 01805, USA.
  • Christoph Wald
    Chairman, Department of Radiology at Lahey Hospital & Medical Center, Professor of Radiology, Tufts University Medical School; Chair of the ACR Informatics Commission.
  • Brady J McKee
    Lahey Hospital & Medical Center, Burlington, MA, 01805, USA.
  • Sebastian Flacke
    Lahey Hospital & Medical Center, Burlington, MA, 01805, USA.
  • Heber MacMahon
    Department of Radiology, University of Chicago, Chicago, IL, 60637, USA.
  • Homer Pien
    Philips Research North America, Cambridge, MA, 02141, USA.