# Learning-based Optimization of the Under-sampling Pattern in MRI

## TL;DR

This paper introduces LOUPE, a data-driven method that jointly optimizes the under-sampling pattern and reconstruction model in MRI, leading to more accurate images than traditional sampling schemes.

## Contribution

The paper presents a novel end-to-end learning approach that customizes MRI under-sampling patterns based on training data, improving reconstruction quality.

## Key findings

- Optimized sampling patterns outperform standard schemes.
- Significantly improved reconstruction accuracy on brain MRI.
- Method tailored to specific image types.

## Abstract

Acquisition of Magnetic Resonance Imaging (MRI) scans can be accelerated by under-sampling in k-space (i.e., the Fourier domain). In this paper, we consider the problem of optimizing the sub-sampling pattern in a data-driven fashion. Since the reconstruction model's performance depends on the sub-sampling pattern, we combine the two problems. For a given sparsity constraint, our method optimizes the sub-sampling pattern and reconstruction model, using an end-to-end learning strategy. Our algorithm learns from full-resolution data that are under-sampled retrospectively, yielding a sub-sampling pattern and reconstruction model that are customized to the type of images represented in the training data. The proposed method, which we call LOUPE (Learning-based Optimization of the Under-sampling PattErn), was implemented by modifying a U-Net, a widely-used convolutional neural network architecture, that we append with the forward model that encodes the under-sampling process. Our experiments with T1-weighted structural brain MRI scans show that the optimized sub-sampling pattern can yield significantly more accurate reconstructions compared to standard random uniform, variable density or equispaced under-sampling schemes. The code is made available at: https://github.com/cagladbahadir/LOUPE .