Skip to content

An official repository for 'A 3D Conditional Diffusion Model for Image Quality Transfer - An Application to Low-Field MRI' presented at NeurIPS DGM4H 2023

Notifications You must be signed in to change notification settings

edshkim98/DiffusionIQT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DiffusionIQT (NeurIPS DGM4H 2023)

Introducing DiffusionIQT, a 3D conditional diffusion model for image quality transfer!
Note that our code is modified from Imagen.

Image quality transfer (IQT) is a ML framework to enhance low-quality medical data, originally proposed by Alexander et al. 2013.
Inspired from a recent development of diffusion models, we propose a 3D conditional diffusion model for image quality transfer.
To the best of our knowledge, this is the first work to apply a diffusion model for 3D medical image enhancement, especially using patch-based method.
Our work has been published to NeurIPS DGM4H 2023.

Code still under developement, please wait :)

To cite my paper:

@inproceedings{kim20233d,
  title={A 3D Conditional Diffusion Model for Image Quality Transfer-An Application to Low-Field MRI},
  author={Kim, Seunghoi and Alexander, Daniel C and Eldaly, Ahmed Karam and Figini, Matteo and Tregidgo, Henry FJ},
  booktitle={Deep Generative Models for Health Workshop NeurIPS 2023}
}

Releases

No releases published

Packages

No packages published