Process (computing)

Undersampling

Image quality

Operating system

Set (abstract data type)

Iterative reconstruction

Computer science

Filter (signal processing)

Code (set theory)

Pattern recognition (psychology)

Image (mathematics)

Sampling (signal processing)

Object (grammar)

Artificial intelligence

Programming language

Compressed sensing

Convolutional neural network

Computer vision

IEEE Transactions on Computational Imaging

There is recent interest in techniques to accelerate the data acquisition process in MRI by acquiring limited measurements. Sophisticated reconstruction algorithms are often deployed to maintain high image quality in such settings. In this work, we propose a data-driven sampler using a convolutional neural network, <monospace xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MNet</monospace> , to provide object-specific sampling patterns adaptive to each scanned object. The network observes limited low-frequency <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$k$</tex-math></inline-formula> -space data for each object and predicts the desired undersampling pattern in one go that achieves high image reconstruction quality. We propose an accompanying alternating-type training framework 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 capability 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.

Single-Pass Object-Adaptive Data Undersampling and Reconstruction for MRI