Recurrent Variational Network: A Deep Learning Inverse Problem Solver applied to the task of Accelerated MRI Reconstruction (2021-11-18T00:00:00.000000Z)

TL;DR

This work presents a novel Deep Learning-based Inverse Problem solver applied to the task of Accelerated MRI Reconstruction, called the Recurrent Variational Network (RecurrentVarNet), by exploiting the properties of Convolutional Recurrent Neural Networks and unrolled algorithms for solving Inverse Problems.

Abstract

Magnetic Resonance Imaging can produce detailed images of the anatomy and physiology of the human body that can assist doctors in diagnosing and treating pathologies such as tumours. However, MRI suffers from very long acquisition times that make it susceptible to patient motion artifacts and limit its potential to deliver dynamic treatments. Conventional approaches such as Parallel Imaging and Compressed Sensing allow for an increase in MRI acquisition speed by reconstructing MR images from sub-sampled MRI data acquired using multiple receiver coils. Recent advancements in Deep Learning combined with Parallel Imaging and Compressed Sensing techniques have the potential to produce high-fidelity reconstructions from highly accelerated MRI data. In this work we present a novel Deep Learning-based Inverse Problem solver applied to the task of Accelerated MRI Reconstruction, called the Recurrent Variational Network (RecurrentVarNet), by exploiting the properties of Convolutional Recurrent Neural Networks and unrolled algorithms for solving Inverse Problems. The RecurrentVarNet consists of multiple recurrent blocks, each responsible for one iteration of the unrolled variational optimization scheme for solving the inverse problem of multi-coil Accelerated MRI Reconstruction. Contrary to traditional approaches, the optimization steps are performed in the observation domain (k-space) instead of the image domain. Each block of the RecurrentVarNet refines the observed k-space and comprises a data consistency term and a recurrent unit which takes as input a learned hidden state and the prediction of the previous block. Our proposed method achieves new state of the art qualitative and quantitative reconstruction results on 5-fold and 10-fold accelerated data from a public multi-coil brain dataset, outperforming previous conventional and deep learning-based approaches. Our code is publicly available at https://github.com/NKI-AI/direct.

References46 items

DIRECT: Deep Image REConstruction Toolkit

Joint Deep Model-based MR Image and Coil Sensitivity Reconstruction Network (Joint-ICNet) for Fast MRI

Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction

Multi-Coil MRI Reconstruction Challenge—Assessing Brain MRI Reconstruction Models and Their Generalizability to Varying Coil Configurations

Multi-channel MR Reconstruction (MC-MRRec) Challenge - Comparing Accelerated MR Reconstruction Models and Assessing Their Genereralizability to Datasets Collected with Different Coils

XPDNet for MRI Reconstruction: an application to the 2020 fastMRI challenge

End-to-End Variational Networks for Accelerated MRI Reconstruction

From Compressed-Sensing to Artificial Intelligence-Based Cardiac MRI Reconstruction

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstruction

LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space

Recurrent inference machines for reconstructing heterogeneous MRI data

Partial Convolution based Padding

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI

Scan‐specific robust artificial‐neural‐networks for k‐space interpolation (RAKI) reconstruction: Database‐free deep learning for fast imaging

Multi-channel Generative Adversarial Network for Parallel Magnetic Resonance Image Reconstruction in K-space

KIKI‐net: cross‐domain convolutional neural networks for reconstructing undersampled magnetic resonance images

An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement

Learned Primal-Dual Reconstruction

Recurrent Inference Machines for Solving Inverse Problems

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Learning a variational network for reconstruction of accelerated MRI data

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Multi-Scale Context Aggregation by Dilated Convolutions

ESPIRiT—an eigenvalue approach to autocalibrating parallel MRI: Where SENSE meets GRAPPA

Iterative estimation of MRI sensitivity maps and image based on sense reconstruction method (isense)

Combination of compressed sensing and parallel imaging for highly-accelerated dynamic MRI

An image-based approach to understanding the physics of MR artifacts.

Image Quality Metrics: PSNR vs. SSIM

SPIRiT: Iterative self‐consistent parallel imaging reconstruction from arbitrary k‐space

The Ill-Posed Problem and Regularization in Parallel Magnetic Resonance Imaging

Sparse MRI: The application of compressed sensing for rapid MR imaging

Parallel magnetic resonance imaging

Encoding and reconstruction in parallel MRI

Statistical and Computational Inverse Problems

Image quality assessment: from error visibility to structural similarity

SNR-optimality of sum-of-squares reconstruction for phased-array magnetic resonance imaging.

Generalized autocalibrating partially parallel acquisitions (GRAPPA)

SENSE: Sensitivity encoding for fast MRI

Simultaneous acquisition of spatial harmonics (SMASH): Fast imaging with radiofrequency coil arrays

On the use of the normalized mean square error in evaluating dispersion model performance