
Open access
Author
Show all
Date
2019-07Type
- Journal Article
Citations
Cited 29 times in
Web of Science
Cited 34 times in
Scopus
ETH Bibliography
yes
Altmetrics
Abstract
Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit prior information to compensate for missing k-space data. Deep learning (DL) provides a powerful framework for extracting such information from existing image datasets, through learning, and then using it for reconstruction. Leveraging this, recent methods employed DL to learn mappings from undersampled to fully sampled images using paired datasets, including undersampled and corresponding fully sampled images, integrating prior knowledge implicitly. In this article, we propose an alternative approach that learns the probability distribution of fully sampled MR images using unsupervised DL, specifically Variational Autoencoders (VAE), and use this as an explicit prior term in reconstruction, completely decoupling the encoding operation from the prior. The resulting reconstruction algorithm enjoys a powerful image prior to compensate for missing k-space data without requiring paired datasets for training nor being prone to associated sensitivities, such as deviations in undersampling patterns used in training and test time or coil settings. We evaluated the proposed method with T1 weighted images from a publicly available dataset, multicoil complex images acquired from healthy volunteers (N=8) and images with white matter lesions. The proposed algorithm, using the VAE prior, produced visually high quality reconstructions and achieved low RMSE values, outperforming most of the alternative methods on the same dataset. On multi-coil complex data, the algorithm yielded accurate magnitude and phase reconstruction results. In the experiments on images with white matter lesions, the method faithfully reconstructed the lesions. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000315674Publication status
publishedExternal links
Journal / series
IEEE Transactions on Medical ImagingVolume
Pages / Article No.
Publisher
IEEESubject
MR imaging; image reconstruction; machine learning; unsupervised learningOrganisational unit
09579 - Konukoglu, Ender / Konukoglu, Ender
02652 - Institut für Bildverarbeitung / Computer Vision Laboratory
03628 - Prüssmann, Klaas P. / Prüssmann, Klaas P.
Funding
173016 - Improving Priors towards Automated Prescreening of Brain Magnetic Resonance Images (SNF)
Related publications and datasets
Is new version of: http://hdl.handle.net/20.500.11850/236287
More
Show all metadata
Citations
Cited 29 times in
Web of Science
Cited 34 times in
Scopus
ETH Bibliography
yes
Altmetrics