Ultra-Low Field MRI: A New Frontier in Brain Injury Research

A group of patients with acquired brain injury will undergo MRI scans on two scanning systems (30 minutes per scanning system), including the low-field portable MRI and a high-field MRI scanner.

This proof-of-concept study will offer valuable insights into structural changes in the brain, potentially aiding in the diagnosis and management of patients with brain injuries in remote areas.

About

MRI methods are of broad and current interest in brain injury research. However, MRI scans are not as widely used as they could be in the clinical practice within this cohort.

Low-field MRI may provide a solution for several reasons. Firstly, it provides a cost-effective option making it more accessible for healthcare facilities. Secondly, low-field MRI provides a more compact and portable system in comparison to current clinical MRI scanners. Thirdly, lower magnetic field strengths can be safer for certain patients (reducing the risk of adverse effects), and it does not require restricted access or specifically designed shielded rooms. Despite lower resolution compared to high-field MRI, low field MRI scans combined with novel machine learning techniques may improve the image quality of the low field MRI data.

In the present study, we will employ a paired dataset comprising structural MRI sequences from the low field (64mT) and high-field (3T) MRI scanning systems. We aim to improve the low-field MR images through a novel (artificial intelligence, AI) deep learning approach to generate a synthetic 3T images and examine the ability of these images to maintain diagnostic integrity and the medical information without the introduction of image artefacts. Moreover, we will compare the brain morphometry measurements between the synthetic 3T MRI images and the native 3T MRI images. Our findings will help to fully understand the applicability of low-field MRI for clinical diagnostics, especially in settings where high-field MRI scanners are less accessible.