Deep Learning of Time-Signal Intensity Curves from Dynamic Susceptibility Contrast Imaging Enables Tissue Labeling and Prediction of Survival in Glioblastoma.

Journal: AJNR. American journal of neuroradiology
Published Date:

Abstract

BACKGROUND AND PURPOSE: An autoencoder can learn representative time-signal intensity patterns to provide tissue heterogeneity measures using dynamic susceptibility contrast MR imaging. The aim of this study was to investigate whether such an autoencoder-based pattern analysis could provide interpretable tissue labeling and prognostic value in isocitrate dehydrogenase () wild-type glioblastoma.

Authors

  • J Yun
    From the Departments of Convergence Medicine (J.Y., N.K.).
  • S Yun
    Department of Radiology (S.Y.), Busan Paik Hospital, Inje University College of Medicine, Busan, Korea.
  • J E Park
    Department of Radiology and Research Institute of Radiology (J.E.P., H.S.K.), Asan Medical Center, University of Ulsan College of Medicine.
  • E-N Cheong
    Medical Science and Asan Medical Institute of Convergence Science and Technology (E.-N.C.), University of Ulsan College of Medicine, Seoul, Korea.
  • S Y Park
    Colorectal Cancer Center, Kyungpook National University Chilgok Hospital, School of Medicine, Kyungpook National University , 807 Hogukro, Buk-gu, Daegu, 41404, South Korea.
  • N Kim
    From the Departments of Convergence Medicine (J.Y., N.K.).
  • H S Kim
    Department of Pharmacology, Pharmacogenomic Research Center for Membrane Transporters, Brain Korea 21 PLUS Project for Medical Sciences; Division of Medical Oncology, Department of Internal Medicine, Yonsei Cancer Center, Yonsei University College of Medicine, Seoul.