CT kernel conversions using convolutional neural net for super-resolution with simplified squeeze-and-excitation blocks and progressive learning among smooth and sharp kernels.

Journal: Computer methods and programs in biomedicine
Published Date: Jun 20, 2020

Abstract

PURPOSE: Computed tomography (CT) volume sets reconstructed with different kernels are helping to increase diagnostic accuracy. However, several CT volumes reconstructed with different kernels are difficult to sustain, due to limited storage and maintenance issues. A CT kernel conversion method is proposed using convolutional neural networks (CNN).

Authors

  • Da-In Eun
    Department of Convergence Medicine, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, South Korea; School of Medicine, Kyunghee University, 26-6, Kyungheedae-ro, Dongdaemun-gu, Seoul, South Korea.
  • Ilsang Woo
    Department of Convergence Medicine, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, South Korea.
  • Beomhee Park
    Kakao, Seoul, South Korea.
  • Namkug Kim
    Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
  • Sang Min Lee A
    Department of Radiology, University of Ulsan College of Medicine, 88 Olympic-ro 43-gil, Songpa-gu, Seoul, South Korea.
  • Joon Beom Seo
    Department of Radiology, Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Korea.

Keywords

External Resources

Popular Topics
Recent Journals