Automation of a Rule-based Workflow to Estimate Age from Brain MR Imaging of Infants and Children Up to 2 Years Old Using Stacked Deep Learning.

Journal: Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine
Published Date: Dec 10, 2021

Abstract

PURPOSE: Myelination-related MR signal changes in white matter are helpful for assessing normal development in infants and children. A rule-based myelination evaluation workflow regarding signal changes on T1-weighted images (T1WIs) and T2-weighted images (T2WIs) has been widely used in radiology. This study aimed to simulate a rule-based workflow using a stacked deep learning model and evaluate age estimation accuracy.

Authors

  • Akihiko Wada
  • Yuya Saito
  • Shohei Fujita
    Department of Radiology, Juntendo University School of Medicine.
  • Ryusuke Irie
    Department of Radiology, Juntendo University School of Medicine.
  • Toshiaki Akashi
  • Katsuhiro Sano
    Department of Radiology, Juntendo University School of Medicine.
  • Shinpei Kato
    Department of Radiology, Juntendo University School of Medicine.
  • Yutaka Ikenouchi
    Department of Radiology, Juntendo University School of Medicine.
  • Akifumi Hagiwara
    Department of Radiology, Juntendo University School of Medicine.
  • Kanako Sato
    Department of Radiology, Juntendo University School of Medicine.
  • Nobuo Tomizawa
    Department of Radiology, Juntendo University School of Medicine.
  • Yayoi Hayakawa
    Department of Radiology, Juntendo University School of Medicine.
  • Junko Kikuta
    Department of Radiology, Juntendo University School of Medicine.
  • Koji Kamagata
  • Michimasa Suzuki
    Department of Radiology, Juntendo University School of Medicine.
  • Masaaki Hori
  • Atsushi Nakanishi
    Department of Radiology, Juntendo University School of Medicine.
  • Shigeki Aoki

Keywords

External Resources

Popular Topics
Recent Journals