Loading [MathJax]/extensions/MathZoom.js
Undersampled Magnetic Resonance Image Reconstructions Based on a Combination of U-Nets and L1, L2, and TV Optimizations | IEEE Conference Publication | IEEE Xplore

Undersampled Magnetic Resonance Image Reconstructions Based on a Combination of U-Nets and L1, L2, and TV Optimizations


Abstract:

Magnetic Resonance Imaging (MRI) plays a major role in the diagnosis of several diseases. However, the acquisition of measurements in the k-space domain, which is the bas...Show More

Abstract:

Magnetic Resonance Imaging (MRI) plays a major role in the diagnosis of several diseases. However, the acquisition of measurements in the k-space domain, which is the basis for image reconstruction, takes a long time compared to other imaging modalities and is comparatively costly. In this context, undersampled MRI reconstruction is an approach for decreasing the acquisition duration and the exam's final cost. With this objective, both Compressed Sensing (CS) and Deep Learning (DL) provide techniques for generating good quality MRI images from undersampled measurements. In this paper, we combine CS and DL methods in order to investigate the potential increase in image quality over each isolated approach. We use reconstructions from from highly undersampled MRI signals using two CS approaches, the L1 and total minimizations, as inputs to a U-Net. We also use, for comparison, the reconstructions from the same undersampled signals using L2 minimization, and also test them as inputs to a U-net. The goal is to evaluate whether the the U-Net can improve the results of the CS reconstructions after learning from degraded and original image pairs. Our experimental results suggest that the combination of L1 or TV minimization with U-Nets can improve reconstruction, in terms of objective image quality, over each technique used in isolation.
Date of Conference: 21-23 June 2022
Date Added to IEEE Xplore: 20 July 2022
ISBN Information:
Print on Demand(PoD) ISSN: 1558-2809
Conference Location: Kaohsiung, Taiwan

I. Introduction

Magnetic resonance imaging (MRI) is a medical imaging technique that is used to acquire images of internal organs and tissues, thus revealing the anatomy and the physiological processes of the body. It can provide images with higher pixel contrast compared to most other medical imaging techniques, by emphasizing tissue properties related to T1 and T2 relaxation times [1]. In order to do so, MRI scanners use strong magnetic fields, magnetic field gradients, and radio waves. Contrarily to Computational Tomography (CT) techniques, it does not require the use of X-rays or other form of ionizing radiation, thus providing an important advantage for children, pregnant women, and patients who require repeated imaging procedures. MRI techniques produce medical images that have a high spatial resolution and a wide range of soft tissue contrasts, and is thusable to depict the body anatomy in great detail. Also, MRI techniques are able to generate images in more planes and can reconstruct organs and anatomical regions in 3 dimensions. In summary, MRI is one of the most important and non-invasive methods for visualizing internal biological tissues [2].

References

References is not available for this document.