Logo image
Back
Variational manifold learning from incomplete data: application to multi-slice dynamic MRI
Journal article   Open access   Peer reviewed

Variational manifold learning from incomplete data: application to multi-slice dynamic MRI

Qing Zou, Abdul Haseeb Ahmed, Prashant Nagpal, Sarv Priya, Rolf F Schulte and Mathews Jacob
IEEE transactions on medical imaging, Vol.41(12), pp.3552-3561
2022
DOI: 10.1109/TMI.2022.3189905
PMCID: PMC10210580
PMID: 35816534
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC10210580/pdf/nihms-1854919.pdfView
Open Access

Abstract

Current deep learning-based manifold learning algorithms such as the variational autoencoder (VAE) require fully sampled data to learn the probability density of real-world datasets. However, fully sampled data is often unavailable in a variety of problems, including the recovery of dynamic and high-resolution MRI. We introduce a novel variational approach to learn a manifold from undersampled data. The VAE uses a decoder fed by latent vectors, drawn from a conditional density estimated from the fully sampled images using an encoder. Since fully sampled images are not available in our setting, we approximate the conditional density of the latent vectors by a parametric model whose parameters are estimated from the undersampled measurements using back-propagation. We use the framework for the joint alignment and recovery of multi-slice free breathing and ungated cardiac MRI data from highly undersampled measurements. Experimental results demonstrate the utility of the proposed scheme in dynamic imaging alignment and reconstructions.
 Magnetic Resonance Imaging Time Series Analysis CNN Convolutional neural networks Data models Free-breathing cardiac MRI Generative model Image reconstruction Manifold approach Manifolds Three-dimensional displays Unsupervised learning Variational autoencoder Volume measurement

Details

Metrics

22 Record Views
9 Times Cited - Web of Science
Logo image