Skip to main content
placeholder image

Medical Image Synthesis via Deep Learning

Journal Article


Abstract


  • Medical images have been widely used in clinics, providing visual representations of under-skin tissues in human body. By applying different imaging protocols, diverse modalities of medical images with unique characteristics of visualization can be produced. Considering the cost of scanning high-quality single modality images or homogeneous multiple modalities of images, medical image synthesis methods have been extensively explored for clinical applications. Among them, deep learning approaches, especially convolutional neural networks (CNNs) and generative adversarial networks (GANs), have rapidly become dominating for medical image synthesis in recent years. In this chapter, based on a general review of the medical image synthesis methods, we will focus on introducing typical CNNs and GANs models for medical image synthesis. Especially, we will elaborate our recent work about low-dose to high-dose PET image synthesis, and cross-modality MR image synthesis, using these models.

Authors


  •   Yu, Biting (external author)
  •   Wang, Yan (external author)
  •   Wang, Lei
  •   Shen, Dinggang (external author)
  •   Zhou, Luping

Publication Date


  • 2020

Citation


  • Yu, B., Wang, Y., Wang, L., Shen, D. & Zhou, L. (2020). Medical Image Synthesis via Deep Learning. Advances in experimental medicine and biology, 1213 23-44.

Scopus Eid


  • 2-s2.0-85079082706

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/3724

Number Of Pages


  • 21

Start Page


  • 23

End Page


  • 44

Volume


  • 1213

Place Of Publication


  • United States

Abstract


  • Medical images have been widely used in clinics, providing visual representations of under-skin tissues in human body. By applying different imaging protocols, diverse modalities of medical images with unique characteristics of visualization can be produced. Considering the cost of scanning high-quality single modality images or homogeneous multiple modalities of images, medical image synthesis methods have been extensively explored for clinical applications. Among them, deep learning approaches, especially convolutional neural networks (CNNs) and generative adversarial networks (GANs), have rapidly become dominating for medical image synthesis in recent years. In this chapter, based on a general review of the medical image synthesis methods, we will focus on introducing typical CNNs and GANs models for medical image synthesis. Especially, we will elaborate our recent work about low-dose to high-dose PET image synthesis, and cross-modality MR image synthesis, using these models.

Authors


  •   Yu, Biting (external author)
  •   Wang, Yan (external author)
  •   Wang, Lei
  •   Shen, Dinggang (external author)
  •   Zhou, Luping

Publication Date


  • 2020

Citation


  • Yu, B., Wang, Y., Wang, L., Shen, D. & Zhou, L. (2020). Medical Image Synthesis via Deep Learning. Advances in experimental medicine and biology, 1213 23-44.

Scopus Eid


  • 2-s2.0-85079082706

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/3724

Number Of Pages


  • 21

Start Page


  • 23

End Page


  • 44

Volume


  • 1213

Place Of Publication


  • United States