MoDL-MUSSELS: Model-Based Deep Learning for Multishot Sensitivity-Encoded Diffusion MRI

Abstract

We introduce a model-based deep learning architecture termed MoDL-MUSSELS for the correction of phase errors in multishot diffusion-weighted echo-planar MR images. The proposed algorithm is a generalization of the existing MUSSELS algorithm with similar performance but significantly reduced computational complexity. In this work, we show that an iterative re-weighted least-squares implementation of MUSSELS alternates between a multichannel filter bank and the enforcement of data consistency. The multichannel filter bank projects the data to the signal subspace, thus exploiting the annihilation relations between shots. Due to the high computational complexity of the self-learned filter bank, we propose replacing it with a convolutional neural network (CNN) whose parameters are learned from exemplary data. The proposed CNN is a hybrid model involving a multichannel CNN in the k-space and another CNN in the image space. The k-space CNN exploits the annihilation relations between the shot images, while the image domain network is used to project the data to an image manifold. The experiments show that the proposed scheme can yield reconstructions that are comparable to state-of-the-art methods while offering several orders of magnitude reduction in run-time. ) are with the department of electrical and computer engineering,

Accelerated Acquisition of High-resolution Diffusion-weighted Imaging of the Brain with a Multi-shot Echo-planar Sequence: Deep-learning-based Denoising

“…19 Although the algorithm is time-consuming, its high computational cost can be mitigated using CNNs. 20 The incorporation of it into our approach could enable the removal of both noise and aliasing. Diffusion-weighted imaging currently conforms a routine protocol for brain MRI given its high contrast resolution.…”

RUN‐UP: Accelerated multishot diffusion‐weighted MRI reconstruction using an unrolled network with U‐Net as priors

“…Our method uses a different architecture compared with previous method MoDL‐MUSSELS, 31 and it enables further acceleration of the reconstruction using only one single gradient update and a deeper network (U‐Net) in each iteration. Moreover, our proposed method offers denoising capabilities similar to averaging multiple repetitions using results from a joint reconstruction 17 as the target.…”

Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling

“…In this study, this translated to considerable reduction of reconstruction noise compared to SPIRiT. In contrast to the recent machine learning-based MRI techniques [25][26][27][28][29][30][31][32][33][34][35][36][37][38], which require large training datasets, sRAKI is trained on scan/subject-specific ACS data. This data was also retrospectively undersampled at rates 2, 3, 4, and 5, and fully-sampled images are shown in the first column as reference.…”

“…Several strategies have been used to accelerate coronary MRI acquisitions such as parallel imaging [12,13], compressed sensing [14][15][16], and their combinations [17][18][19][20][21][22][23]. Recently, deep learning-based techniques [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] have also gained attention as a means to accelerate MRI acquisition. Numerous studies have designed neural network architectures that either establish an end-to-end nonlinear mapping from under-sampled k-space/distorted image to full kspace/undistorted image [25,27,28,31,[33][34][35]37] or decompose an iterative optimization problem into (recurrent) deep learning blocks that learn a data-specific regularization [26,29,30,32,38].…”

“…Recently, deep learning-based techniques [24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] have also gained attention as a means to accelerate MRI acquisition. Numerous studies have designed neural network architectures that either establish an end-to-end nonlinear mapping from under-sampled k-space/distorted image to full kspace/undistorted image [25,27,28,31,[33][34][35]37] or decompose an iterative optimization problem into (recurrent) deep learning blocks that learn a data-specific regularization [26,29,30,32,38]. A number of these studies also show support for parallel imaging with multicoil data [24,26,29,31,36].…”