Conference proceeding
Accelerated dynamic MRI using sparse dictionary learning
Proceedings of SPIE - The International Society for Optical Engineering, Vol.8858, pp.885822-885822-8
09/26/2013
DOI: 10.1117/12.2024867
Abstract
We propose a novel sparse dictionary learning frame work to recover dynamic images from under-sampled measurements. Unlike the recent low rank schemes, the proposed scheme models the dynamic signal as a sparse linear combination of temporal basis functions chosen from a large dictionary. Both the basis functions and the sparse coefficients are estimated from the undersampled data. We show that this representation is much more compact compared to the low rank models. We also develop an efficient majorize-minimize algorithm to estimate the sparse model coefficients and the dictionary directly from the measured data. We compare the proposed scheme against low rank models and compressed sensing, and demonstrate improved reconstructions in the context of myocardial perfusion imaging in the presence of motion.
Details
- Title: Subtitle
- Accelerated dynamic MRI using sparse dictionary learning
- Creators
- Sajan Goud Lingala - The Univ. of Iowa (United States)Mathews Jacob - The Univ. of Iowa (United States)
- Contributors
- Dimitri Van De Ville (Editor) - Ecole Polytechnique Fédérale de Lausanne (Switzerland)Vivek K Goyal (Editor) - Massachusetts Institute of Technology (United States)Manos Papadakis (Editor) - Univ. of Houston (United States)
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of SPIE - The International Society for Optical Engineering, Vol.8858, pp.885822-885822-8
- Publisher
- SPIE
- DOI
- 10.1117/12.2024867
- ISSN
- 0277-786X
- eISSN
- 1996-756X
- Language
- English
- Date published
- 09/26/2013
- Academic Unit
- Electrical and Computer Engineering; Radiation Oncology; Roy J. Carver Department of Biomedical Engineering; Radiology; Iowa Neuroscience Institute
- Record Identifier
- 9984070225002771
Metrics
50 Record Views