Logo image
Joint Optimization of Sampling Patterns and Deep Priors for Improved Parallel MRI
Conference proceeding

Joint Optimization of Sampling Patterns and Deep Priors for Improved Parallel MRI

Hemant K Aggarwal and Mathews Jacob
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.8901-8905
05/2020
DOI: 10.1109/ICASSP40776.2020.9053297
url
https://arxiv.org/pdf/1911.02945View
Open Access

Abstract

Multichannel imaging techniques are widely used in MRI to reduce the scan time. These schemes typically perform undersampled acquisition and utilize compressed-sensing based regularized reconstruction algorithms. Model-based deep learning (MoDL) frameworks are now emerging as powerful alternatives to compressed sensing, with significantly improved image quality. In this work, we investigate the impact of sampling patterns on the quality of the image recovered using the MoDL algorithm. We introduce a scheme to jointly optimize the sampling pattern and the reconstruction network parameters in MoDL for parallel MRI. The improved decoupling of the network parameters from the sampling patterns offered by the MoDL scheme translates to improved optimization and thus improved performance. Preliminary experimental results demonstrate that the proposed joint opti-mization framework significantly improves the image quality.
Image quality Deep learning Magnetic resonance imaging Signal processing algorithms parallel MRI sampling Speech processing Image reconstruction Optimization

Details

Metrics

18 Record Views
Logo image