Investigation of Low-Dose CT Image Denoising Using Unpaired Deep Learning Methods

Zeheng Li, Shiwei Zhou, Junzhou Huang, Lifeng Yu, Mingwu Jin

Research output: Contribution to journalArticlepeer-review


Low-dose computed tomography (LDCT) is desired due to prevalence and ionizing radiation of CT, but suffers elevated noise. To improve LDCT image quality, an image-domain denoising method based on cycle-consistent generative adversarial network (CycleGAN) is developed and compared with two other variants, IdentityGAN and GAN-CIRCLE. Different from supervised deep learning methods, these unpaired methods can effectively learn image translation from the low-dose domain to the full-dose (FD) domain without the need of aligning FDCT and LDCT images. The results on real and synthetic patient CT data show that these methods can achieve peak signal-To-noise ratio (PSNR) and structural similarity index (SSIM) comparable to, if not better than, the other state-of-The-Art denoising methods. Among CycleGAN, IdentityGAN, and GAN-CIRCLE, the later achieves the best denoising performance with the shortest computation time. Subsequently, GAN-CIRCLE is used to demonstrate that the increasing number of training patches and of training patients can improve denoising performance. Finally, two nonoverlapping experiments, i.e., no counterparts of FDCT and LDCT images in the training data, further demonstrate the effectiveness of unpaired learning methods. This work paves the way for applying unpaired deep learning methods to enhance LDCT images without requiring aligned FD and low-dose images from the same patient.

Original languageEnglish (US)
Article number9134929
Pages (from-to)224-234
Number of pages11
JournalIEEE Transactions on Radiation and Plasma Medical Sciences
Issue number2
StatePublished - Mar 2021


  • Cycle consistency
  • deep-learning-based denoising
  • generative adversarial network~(GAN)
  • low-dose computed tomography (LDCT)
  • unpaired learning

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging
  • Instrumentation


Dive into the research topics of 'Investigation of Low-Dose CT Image Denoising Using Unpaired Deep Learning Methods'. Together they form a unique fingerprint.

Cite this