An Optimization-Based Meta-Learning Model for MRI Reconstruction with Diverse Dataset

Wanyu Bian,Qingchao Zhang,Xiaojing Ye,Yunmei Chen

doi:10.3390/jimaging7110231

Wanyu Bian, Qingchao Zhang + Show 2 more

Open Access

https://doi.org/10.3390/jimaging7110231

Copy DOI

Abstract

This work aims at developing a generalizable Magnetic Resonance Imaging (MRI) reconstruction method in the meta-learning framework. Specifically, we develop a deep reconstruction network induced by a learnable optimization algorithm (LOA) to solve the nonconvex nonsmooth variational model of MRI image reconstruction. In this model, the nonconvex nonsmooth regularization term is parameterized as a structured deep network where the network parameters can be learned from data. We partition these network parameters into two parts: a task-invariant part for the common feature encoder component of the regularization, and a task-specific part to account for the variations in the heterogeneous training and testing data. We train the regularization parameters in a bilevel optimization framework which significantly improves the robustness of the training process and the generalization ability of the network. We conduct a series of numerical experiments using heterogeneous MRI data sets with various undersampling patterns, ratios, and acquisition settings. The experimental results show that our network yields greatly improved reconstruction quality over existing methods and can generalize well to new reconstruction problems whose undersampling patterns/trajectories are not present during training.

Highlights

Deep learning methods have demonstrated promising performance in a variety of image reconstruction problems
From the experiments implemented with radial masks, we observe that the average peak signal-to-noise ratio (PSNR) value of meta-learning improved by 1.54 dB in the T1 brain image for all four CS ratios compared with the conventional method, and for the T2 brain image, the average PSNR of meta-learning improved by 1.46 dB
In the T1 image reconstruction results, meta-learning showed an improvement of 1.6921 dB in PSNR for the 15% CS

Summary

Introduction

Deep learning methods have demonstrated promising performance in a variety of image reconstruction problems. In a multiple-task scenario, given a family of tasks, meta-learning has been proven to be a useful tool for extracting task-agnostic knowledge and improving the learning performance of new tasks from that family [11,12]. We leverage this feature of meta-learning for network training where the MRI training data are acquired by using different under-sampling patterns (e.g., Cartesian mask, Radial mask, Poisson mask), under-sampling ratios, and different settings of the scanning parameters, which result in different levels of contrast (e.g., T1-weighted, T2-weighted, proton-density (PD), and Flair)

Objectives

Results

Conclusion