Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging utilizing Deep Learning

TL;DR

This paper introduces a deep learning method using a densely connected Unet architecture to upscale low resolution 1H magnetic resonance spectroscopic images, enabling high-resolution imaging from limited data.

Contribution

The study presents a novel D-Unet model that combines T1-weighted images with low resolution spectra to produce high-resolution spectroscopic images, advancing SI techniques.

Findings

Deep learning can reconstruct high-quality spectroscopic images from low resolution data.

The D-Unet outperforms traditional methods in qualitative and quantitative assessments.

High-resolution spectra can be generated from limited acquisition data.

Abstract

Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report a novel densely connected Unet (D-Unet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.