Deep learning only by normal brain PET identify unheralded brain anomalies.

Journal: EBioMedicine
Published Date:

Abstract

BACKGROUND: Recent deep learning models have shown remarkable accuracy for the diagnostic classification. However, they have limitations in clinical application due to the gap between the training cohorts and real-world data. We aimed to develop a model trained only by normal brain PET data with an unsupervised manner to identify an abnormality in various disorders as imaging data of the clinical routine.

Authors

  • Hongyoon Choi
    Cheonan Public Health Center, 234-1 Buldang-Dong, Seobuk-Gu, Cheonan, Republic of Korea.
  • Seunggyun Ha
    Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
  • Hyejin Kang
    Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
  • Hyekyoung Lee
    Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.
  • Dong Soo Lee
    Department of Nuclear Medicine, Seoul National University College of Medicine, Seoul, Republic of Korea.