Deep-learning features based on F18 fluorodeoxyglucose positron emission tomography/computed tomography (F-FDG PET/CT) to predict preoperative colorectal cancer lymph node metastasis.

Journal: Clinical radiology
PMID:

Abstract

AIM: The objective of this study was to create and authenticate a prognostic model for lymph node metastasis (LNM) in colorectal cancer (CRC) that integrates clinical, radiomics, and deep transfer learning features.

Authors

  • H Wang
    Department of Mechanical Engineering, Columbia University, 500 West 120th Street, New York, NY 10027, USA.
  • J Zhang
    Department of Mechanical Engineering, Columbia University, 500 West 120th Street, New York, NY 10027, USA.
  • Y Li
  • D Wang
    Department of Otolaryngology-Head and Neck Surgery, Institute of Otolaryngology, Chinese PLA General Hospital, Beijing, China.
  • T Zhang
    a School of Mathematics and Statistics, Xidian University , Xi'an , PR China.
  • F Yang
    Department of Radiation Oncology, University of Washington Medical Center, Seattle, Washington 98195.
  • Y Zhang
    University Technology Sydney, 15 Broadway, Ultimo, NSW Australia.
  • L Yang
    Departments of Neurology (L.Y.).
  • P Li
    Criminal Investigation Detachment, Zibo Public Security Bureau, Zibo 255000, Shandong Province, China.