Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Learning-Based Solutions for Inverse Problems

Variational Diffusion Models for MRI Blind Inverse Problems

Julio Oscanoa · Cagan Alkan · Daniel Abraham · Aizada Nurdinova · Daniel Ennis · Shreyas Vasanawala · Morteza Mardani · John Pauly

Keywords: [ Blind Inverse Problem ] [ diffusion models ] [ image reconstruction ] [ MRI ]


Abstract:

Diffusion models have demonstrated state-of-the-art results in solving inverse problems in various domains including medical imaging. However, existing works generally consider the cases where the forward operator is fully known. Therefore blind inverse problems with unknown forward operator parameters require modifications on existing methods. In this work, we present an extension of the recently developed regularization by denoising diffusion process (RED-diff) algorithm to the blind inverse problems. We test our method in fieldmap-corrected MR image reconstruction and show that the blind RED-diff framework can successfully approximate the unknown forward model parameters and produce fieldmap corrected reconstructions accurately.

Chat is not available.