AutoDPS: An unsupervised diffusion model based method for multiple degradation removal in MRI.

Journal: Computer methods and programs in biomedicine
PMID:

Abstract

BACKGROUND AND OBJECTIVE: Diffusion models have demonstrated their ability in image generation and solving inverse problems like restoration. Unlike most existing deep-learning based image restoration techniques which rely on unpaired or paired data for degradation awareness, diffusion models offer an unsupervised degradation independent alternative. This is well-suited in the context of restoring artifact-corrupted Magnetic Resonance Images (MRI), where it is impractical to exactly model the degradations apriori. In MRI, multiple corruptions arise, for instance, from patient movement compounded by undersampling artifacts from the acquisition settings.

Authors

  • Arunima Sarkar
    Department of Electrical Engineering, Indian Institute of Technology Madras (IITM), Chennai 600036, Tamil Nadu, India. Electronic address: arns2111@gmail.com.
  • Ayantika Das
  • Keerthi Ram
    Center for Computational Brain Research, Indian Institute of Technology, Chennai, Tamil Nadu, India 600036.
  • Sriprabha Ramanarayanan
  • Suresh Emmanuel Joel
    GE Healthcare, Bangalore 560067, Karnataka, India.
  • Mohanasankar Sivaprakasam
    Center for Computational Brain Research, Indian Institute of Technology, Chennai, Tamil Nadu, India 600036.