Activities per year
Abstract
Purpose
To allow fast and high-quality reconstruction of clinical accelerated multi-coil MR data by learning a variational network that combines the mathematical structure of variational models with deep learning.
Theory and Methods
Generalized compressed sensing reconstruction formulated as a variational model is embedded in an unrolled gradient descent scheme. All parameters of this formulation, including the prior model defined by filter kernels and activation functions as well as the data term weights, are learned during an offline training procedure. The learned model can then be applied online to previously unseen data.
Results
The variational network approach is evaluated on a clinical knee imaging protocol for different acceleration factors and sampling patterns using retrospectively and prospectively undersampled data. The variational network reconstructions outperform standard reconstruction algorithms, verified by quantitative error measures and a clinical reader study for regular sampling and acceleration factor 4.
Conclusion
Variational network reconstructions preserve the natural appearance of MR images as well as pathologies that were not included in the training data set. Due to its high computational performance, that is, reconstruction time of 193 ms on a single graphics card, and the omission of parameter tuning once the network is trained, this new approach to image reconstruction can easily be integrated into clinical workflow. Magn Reson Med 79:3055–3071, 2018. © 2017 International Society for Magnetic Resonance in Medicine.
Original language | English |
---|---|
Pages (from-to) | 3055-3071 |
Journal | Magnetic Resonance in Medicine |
Volume | 79 |
Issue number | 6 |
DOIs | |
Publication status | Published - 2018 |
Fingerprint
Dive into the research topics of 'Learning a Variational Network for Reconstruction of Accelerated MRI Data'. Together they form a unique fingerprint.-
Learning a Variational Network for Reconstruction of Accelerated MRI Data
Kerstin Hammernik (Speaker)
16 Jun 2018 → 21 Jun 2018Activity: Talk or presentation › Talk at conference or symposium › Science to science
-
Learning a Variational Network for Reconstruction of Accelerated MRI Data
Kerstin Hammernik (Speaker)
16 Jun 2018 → 21 Jun 2018Activity: Talk or presentation › Poster presentation › Science to science
Prizes
-
Young Investigator Award Finalist
Hammernik, Kerstin (Recipient), 2018
Prize: Prizes / Medals / Awards
Press/Media
-
Q&A with Kerstin Hammernik and Florian Knoll
Kerstin Hammernik
22/06/18
1 Media contribution
Press/Media: Press / Media