View in EDS

A Physics-informed Conditional Wasserstein Autoencoder to Quantify Uncertainties in Accelerated 2D Dynamic Radial MRI

Saved in:
Bibliographic Details
Title: A Physics-informed Conditional Wasserstein Autoencoder to Quantify Uncertainties in Accelerated 2D Dynamic Radial MRI
Authors: Sherine Brahma, Tobias Schaeffter, Christoph Kolbitsch, Andreas Kofler
Source: ISMRM Annual Meeting.
Publisher Information: ISMRM, 2024.
Publication Year: 2024
Description: Uncertainty quantification (UQ) can provide important information about deep learning algorithms and help interpret the obtained results. UQ for multi-coil dynamic MRI is challenging due to the large scale of the problem and scarce training data. We approach these issues by learning distributions in a lower dimensional latent space using a conditional Wasserstein autoencoder while utilizing the MR data acquisition model and by exploiting spatio-temporal correlations of the cine MR images. Our results indicate excellent image quality accompanied with uncertainty maps that correlate well with estimation errors.
Document Type: Article
ISSN: 1545-4428
DOI: 10.58530/2023/4799
Accession Number: edsair.doi...........a9b62ff7cb9a5b47a08b61dba2445a98
Database: OpenAIRE
Description
Abstract:Uncertainty quantification (UQ) can provide important information about deep learning algorithms and help interpret the obtained results. UQ for multi-coil dynamic MRI is challenging due to the large scale of the problem and scarce training data. We approach these issues by learning distributions in a lower dimensional latent space using a conditional Wasserstein autoencoder while utilizing the MR data acquisition model and by exploiting spatio-temporal correlations of the cine MR images. Our results indicate excellent image quality accompanied with uncertainty maps that correlate well with estimation errors.
ISSN:15454428
DOI:10.58530/2023/4799