The final, formatted version of the article will be published soon.
ORIGINAL RESEARCH article
Front. Neurosci.
Sec. Brain Imaging Methods
Volume 18 - 2024 |
doi: 10.3389/fnins.2024.1473132
Perceptual super-resolution in multiple sclerosis MRI
Provisionally accepted- 1 University of Antwerp, Antwerp, Belgium
- 2 µNEURO Research Centre of Excellence, University of Antwerp, Antwerp, Antwerp, Belgium
- 3 Computer Imaging and Medical Applications Laboratory, National University of Colombia, Bogota, Colombia
- 4 Biomedical Research Institute, University of Hasselt, Hasselt, Limburg, Belgium
- 5 Data Science Institute, University of Hasselt, Hasselt, Limburg, Belgium
- 6 The D-Lab, Department of Precision Medicine, GROW-Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, Netherlands
- 7 imec Vision Lab, Faculty of Sciences, University of Antwerp, Antwerp, Antwerp, Belgium
- 8 Department of Diagnostic Imaging, National University Hospital, Bogota, Colombia
- 9 Revalidatie & Multiple Sclerosis (MS), Pelt, Belgium
- 10 Department of Radiology and Nuclear Imaging, GROW-Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, Netherlands
Magnetic resonance imaging (MRI) is crucial for diagnosing and monitoring of multiple sclerosis (MS) as it is used to assess lesions in the brain and spinal cord. However, in real-world clinical settings, MRI scans are often acquired with thick slices, limiting their utility for automated quantitative analyses. This work presents a single-image super-resolution (SR) reconstruction framework that leverages SR convolutional neural networks (CNN) to enhance the through-plane resolution of structural MRI in people with MS (PwMS). Our strategy involves the supervised finetuning of CNN architectures, guided by a content loss function that promotes perceptual quality, as well as reconstruction accuracy, to recover high-level image features. Extensive evaluation with MRI data of PwMS shows that our SR strategy leads to more accurate MRI reconstructions than competing methods. Furthermore, it improves lesion segmentation on low-resolution MRI, approaching the performance achievable with high-resolution images. Results demonstrate the potential of our SR framework to facilitate the use of low-resolution retrospective MRI from real-world clinical settings to investigate quantitative image-based biomarkers of MS.
Keywords: super resolution, MRI, Multiple Sclerosis, lesion segmentation, CNN, Fine-tuning
Received: 30 Jul 2024; Accepted: 06 Sep 2024.
Copyright: © 2024 Giraldo, Khan, PINEDA, Liang, Lozano, Van Wijmeersch, Woodruff, Lambin, Romero, Peeters and Sijbers. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Diana L. Giraldo, University of Antwerp, Antwerp, Belgium
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.