Compressed Sensing: From Research to Clinical Practice With Deep Neural Networks: Shortening Scan Times for Magnetic Resonance Imaging

TLDR

Compressed sensing uses sparse signal structure to reconstruct high‑resolution images from undersampled data, promising faster MRI scans and better diagnostics, but suffers from artifacts, heavy parameter tuning, and slow reconstruction times. This tutorial reviews classical compressed sensing and explains how to convert it into a deep‑learning reconstruction framework. We demonstrate the approach with open‑source Python code on public datasets and discuss practical considerations for deploying unrolled neural networks in clinical practice.

Abstract

Compressed sensing (CS) reconstruction methods leverage sparse structure in underlying signals to recover high-resolution images from highly undersampled measurements. When applied to magnetic resonance imaging (MRI), CS has the potential to dramatically shorten MRI scan times, increase diagnostic value, and improve the overall patient experience. However, CS has several shortcomings that limit its clinical translation. These include 1) artifacts arising from inaccurate sparse modeling assumptions, 2) extensive parameter tuning required for each clinical application, and 3) clinically infeasible reconstruction times. Recently, CS has been extended to incorporate deep neural networks as a way of learning complex image priors from historical exam data. Commonly referred to as unrolled neural networks, these techniques have proven to be a compelling and practical approach to address the challenges of sparse CS. In this tutorial, we review the classical CS formulation and outline steps needed to transform this formulation into a deep-learning-based reconstruction framework. Supplementary open-source code in Python is used to demonstrate this approach with open databases. Further, we discuss considerations in applying unrolled neural networks in the clinical setting.