adler-j / learned_gradient_tomography

Solving ill-posed inverse problems using iterative deep neural networks

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Solving ill-posed inverse problems using iterative deep neural networks

This repository will contain the code for the article "Solving ill-posed inverse problems using iterative deep neural networks" published on arXiv.

Contents

The code contains the following

  • Training using ellipse phantoms
  • Evaluation on ellipse phantoms
  • Training using anthropomorphic data. (Data not included for legal/privacy reasons)
  • Evaluation on example head slice
  • Reference reconstructions of the above using ODL.

Dependencies

The code is currently based on an experimental version of ODL, so that specific branch needs to be used for the code to work.

Contact

Jonas Adler, PhD student
KTH, Royal Institute of Technology
Elekta Instrument AB
jonasadl@kth.se

Ozan Öktem, Associate Professor
KTH, Royal Institute of Technology
ozan@kth.se

Funding

Development is financially supported by the Swedish Foundation for Strategic Research as part of the project "Low complexity image reconstruction in medical imaging" and "3D reconstruction with simulated forward models".

Development has also been financed by Elekta.

About

Solving ill-posed inverse problems using iterative deep neural networks


Languages

Language:Python 100.0%