A deep learning anthropomorphic model observer for a detection task in PET.

Journal: Medical physics
Published Date:

Abstract

BACKGROUND: Lesion detection is one of the most important clinical tasks in positron emission tomography (PET) for oncology. An anthropomorphic model observer (MO) designed to replicate human observers (HOs) in a detection task is an important tool for assessing task-based image quality. The channelized Hotelling observer (CHO) has been the most popular anthropomorphic MO. Recently, deep learning MOs (DLMOs), mostly based on convolutional neural networks (CNNs), have been investigated for various imaging modalities. However, there have been few studies on DLMOs for PET.

Authors

  • Muhan Shao
    Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA. Electronic address: muhan@jhu.edu.
  • Darrin W Byrd
    Department of Radiology, University of Washington, Seattle, Washington, USA.
  • Jhimli Mitra
    Australian e-Health Research Centre, CSIRO, Digital Productivity Flagship.
  • Fatemeh Behnia
    Department of Radiology, University of Washington, Seattle, Washington, USA.
  • Jean H Lee
    Department of Radiology, University of Washington, Seattle, Washington, USA.
  • Amir Iravani
    Centre for Molecular Imaging, Department of Cancer Imaging, Peter MacCallum Cancer Centre, 305 Grattan Street, Melbourne, Australia. amir.iravani@petermac.org.
  • Murat Sadic
    Department of Radiology, University of Washington, Seattle, Washington, USA.
  • Delphine L Chen
    Department of Molecular Imaging and Therapy, Fred Hutchinson Cancer Center, Seattle, WA, USA.
  • Scott D Wollenweber
    GE Healthcare, Waukesha, WI, USA.
  • Craig K Abbey
    Department of Psychological and Brain Sciences, University of California, Santa Barbara, Santa Barbara, CA 93106, USA.
  • Paul E Kinahan
    Department of Radiology and Bioengineering, University of Washington, Box 357987, Seattle, WA 98105, USA.
  • Sangtae Ahn
    GE Research, 1 Research Circle KWC-1310C, Niskayuna, NY 12309, USA.