Logo image
Multi-Shot Sensitivity-Encoded Diffusion MRI Using Model-Based Deep Learning (Modl-Mussels)
Conference proceeding   Open access

Multi-Shot Sensitivity-Encoded Diffusion MRI Using Model-Based Deep Learning (Modl-Mussels)

Hemant K Aggarwal, Merry P Mani and Mathews Jacob
2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Vol.2019, pp.1541-1544
04/2019
DOI: 10.1109/ISBI.2019.8759514
PMID: 33584974
url
https://www.ncbi.nlm.nih.gov/pmc/articles/7879460View
Open Access

Abstract

We propose a model-based deep learning architecture for the correction of phase errors in multishot diffusion-weighted echo-planar MRI images. This work is a generalization of MUSSELS, which is a structured low-rank algorithm. We show that an iterative reweighted least-squares implementation of MUSSELS resembles the model-based deep learning (MoDL) framework. We propose to replace the self-learned linear filter bank in MUSSELS with a convolutional neural network, whose parameters are learned from exemplary data. The proposed algorithm reduces the computational complexity of MUSSELS by several orders of magnitude, while providing comparable image quality.
Deep learning Convolutional Neural Network Convolution Magnetic resonance imaging Noise reduction K-space Deep learning Echo Planar Imaging Image reconstruction Testing

Details

Logo image