Single-pass Object-adaptive Data Undersampling and Reconstruction for MRI

TL;DR

This paper introduces a neural network-based method for object-specific MRI data undersampling, enabling faster acquisition with high-quality image reconstruction through adaptive sampling patterns learned from limited data.

Contribution

It presents a novel convolutional neural network that predicts object-specific undersampling patterns for MRI, improving acceleration and image quality over existing methods.

Findings

Achieves fourfold and eightfold acceleration with superior image quality.

Outperforms existing undersampling schemes in reconstruction performance.

Demonstrates effectiveness on the fastMRI knee dataset.

Abstract

There is much recent interest in techniques to accelerate the data acquisition process in MRI by acquiring limited measurements. Often sophisticated reconstruction algorithms are deployed to maintain high image quality in such settings. In this work, we propose a data-driven sampler using a convolutional neural network, MNet, to provide object-specific sampling patterns adaptive to each scanned object. The network observes very limited low-frequency k-space data for each object and rapidly predicts the desired undersampling pattern in one go that achieves high image reconstruction quality. We propose an accompanying alternating-type training framework with a mask-backward procedure that efficiently generates training labels for the sampler network and jointly trains an image reconstruction network. Experimental results on the fastMRI knee dataset demonstrate the ability of the proposed learned undersampling network to generate object-specific masks at fourfold and eightfold acceleration that achieve superior image reconstruction performance than several existing schemes. The source code for the proposed joint sampling and reconstruction learning framework is available at https://github.com/zhishenhuang/mri.