A novel strategy to develop deep learning for image super-resolution using original ultra-high-resolution computed tomography images of lung as training dataset.

Journal: Japanese journal of radiology
Published Date: Jul 28, 2021

Abstract

PURPOSE: To improve the image quality of inflated fixed cadaveric human lungs by utilizing ultra-high-resolution computed tomography (U-HRCT) as a training dataset for super-resolution processing using deep learning (SR-DL).

Authors

  • Hitoshi Kitahara
    Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-Cho, Otsu, Shiga, 520-2192, Japan. hitoshik@belle.shiga-med.ac.jp.
  • Yukihiro Nagatani
    Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-Cho, Otsu, Shiga, 520-2192, Japan.
  • Hideji Otani
    Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-Cho, Otsu, Shiga, 520-2192, Japan.
  • Ryohei Nakayama
  • Yukako Kida
    Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-Cho, Otsu, Shiga, 520-2192, Japan.
  • Akinaga Sonoda
    Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-Cho, Otsu, Shiga, 520-2192, Japan.
  • Yoshiyuki Watanabe
    Department of Future Diagnostic Radiology, Osaka University Graduate School of Medicine.

Keywords

External Resources

Popular Topics
Recent Journals