The effects of physics-based data augmentation on the generalizability of deep neural networks: Demonstration on nodule false-positive reduction.

Journal: Medical physics
Published Date: Aug 27, 2019

Abstract

PURPOSE: An important challenge for deep learning models is generalizing to new datasets that may be acquired with acquisition protocols different from the training set. It is not always feasible to expand training data to the range encountered in clinical practice. We introduce a new technique, physics-based data augmentation (PBDA), that can emulate new computed tomography (CT) data acquisition protocols. We demonstrate two forms of PBDA, emulating increases in slice thickness and reductions of dose, on the specific problem of false-positive reduction in the automatic detection of lung nodules.

Authors

  • Akinyinka O Omigbodun
    Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Suite 650, 924 Westwood Boulevard, Los Angeles, CA, 90024, USA.
  • Frederic Noo
    Department of Radiology and Imaging Sciences, The University of Utah, Salt Lake City, UT, 84108, USA.
  • Michael McNitt-Gray
    Departments of Biomedical Physics and Radiology, University of California, Los Angeles, CA, 90095, USA.
  • William Hsu
    Medical & Imaging Informatics, Department of Radiological Sciences, David Geffen School of Medicine at UCLA, Los Angeles, CA 90024, USA.
  • Scott S Hsieh
    Department of Radiological Sciences, David Geffen School of Medicine, University of California Los Angeles, Suite 650, 924 Westwood Boulevard, Los Angeles, CA, 90024, USA.

Keywords

External Resources

Popular Topics
Recent Journals