Abstract
New clinically viable approaches are needed to realise the potential of non-invasive imaging to monitor changes to the severity of cerebral small vessel disease (SVD) in patients. Field-cycling imaging (FCI) is an emerging whole-body MRI technology that provides unique access to underlying tissue features by varying the magnetic field during acquisition, at strengths up to 10,000 times lower than conventional fixed-field MRI. The low-field nature of FCI further means that it has the potential to be developed towards a variety of accessible and impactful clinical applications. The aim of this preliminary work was to investigate the feasibility of FCI to quantify SVD severity when combined with a fully automated segmentation algorithm. In reference to segmented tissue labels obtained from 3T MRI, FCI can accurately segment regions of brain matter (mean Dice coefficient of 0.89), ventricle (0.91), and SVD (0.52). The variation between SVD regions may partly be explained by differences in sensitivity of FCI to underlying pathophysiological processes involved with SVD. This preliminary work is a crucial step towards assessing the clinical feasibility of FCI for SVD clinical applications.
Original language | English |
---|---|
Title of host publication | 27th Conference on Medical Image Understanding and Analysis 2023 |
Editors | Gordon Waiter, Tryphon Lambrou, Georgios Leontidis, Nir Oren, Teresa Morris, Sharon Gordon, Jade McGowan, Cara Nicolson |
Publisher | Frontiers Media SA |
Pages | 158-162 |
Number of pages | 5 |
Volume | Frontiers Abstract Book |
ISBN (Electronic) | 9782832512319 |
DOIs | |
Publication status | Published - 19 Jul 2023 |
Event | 27th Annual Conference on Medical Image Understanding and Analysis, MIUA 2023 - Aberdeen, United Kingdom Duration: 19 Jul 2023 → 21 Jul 2023 |
Conference
Conference | 27th Annual Conference on Medical Image Understanding and Analysis, MIUA 2023 |
---|---|
Country/Territory | United Kingdom |
City | Aberdeen |
Period | 19/07/23 → 21/07/23 |
Keywords
- brain imaging
- deep learning
- cancer
- cardiac imaging
- machine learning
- computed tomography
- magnetic resonance imaging
- image interpretation
- radiology image interpretation
- image guided intervention
- opthalmology
- multi modal image analysis