Abstract

Multiple Sclerosis (MS) is an autoimmune demyelinating disease characterised by changes in iron and myelin content. These biomarkers are detectable by Quantitative Susceptibility Mapping (QSM), an advanced Magnetic Resonance Imaging technique detecting magnetic properties. When analysed with radiomic techniques that exploit its intrinsic quantitative nature, QSM may furnish biomarkers to facilitate early diagnosis of MS and timely assessment of progression. In this work, we explore the robustness of QSM radiomic features by varying the number of grey levels (GLs) and echo times (TEs), in a sample of healthy controls and patients with MS. We analysed the white matter in total and within six clinically relevant tracts, including the cortico-spinal tract and the optic radiation. After optimising the number of GLs (n = 64), at least 65% of features were robust for each Volume of Interest (VOI), with no difference (p > .05) between left and right hemispheres. Different outcomes in feature robustness among the VOIs depend on their characteristics, such as volume and variance of susceptibility values. This study validated the processing pipeline for robustness analysis and established the reliability of QSM-based radiomics features against GLs and TEs. Our results provide important insights for future radiomics studies using QSM in clinical applications.

Details

Title
Assessing robustness of quantitative susceptibility-based MRI radiomic features in patients with multiple sclerosis
Author
Fiscone, Cristiana 1 ; Rundo, Leonardo 2 ; Lugaresi, Alessandra 3 ; Manners, David Neil 4 ; Allinson, Kieren 5 ; Baldin, Elisa 6 ; Vornetti, Gianfranco 7 ; Lodi, Raffaele 7 ; Tonon, Caterina 7 ; Testa, Claudia 8 ; Castelli, Mauro 9 ; Zaccagna, Fulvio 10 

 University of Bologna, Department of Biomedical and Neuromotor Sciences, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758) 
 University of Salerno, Department of Information and Electrical Engineering and Applied Mathematics, Fisciano, Italy (GRID:grid.11780.3f) (ISNI:0000 0004 1937 0335) 
 University of Bologna, Department of Biomedical and Neuromotor Sciences, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758); IRCCS Istituto delle Scienze Neurologiche di Bologna, UOSI Riabilitazione Sclerosi Multipla, Bologna, Italy (GRID:grid.492077.f) 
 University of Bologna, Department for Life Quality Sciences, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758); IRCCS Istituto delle Scienze Neurologiche di Bologna, Functional and Molecular Neuroimaging Unit, Bologna, Italy (GRID:grid.492077.f) 
 Cambridge University Hospitals NHS Foundation Trust, Department of Histopathology, Cambridge, United Kingdom (GRID:grid.24029.3d) (ISNI:0000 0004 0383 8386) 
 IRCCS Istituto delle Scienze Neurologiche di Bologna, Epidemiology and Statistics Unit, Bologna, Italy (GRID:grid.492077.f) 
 University of Bologna, Department of Biomedical and Neuromotor Sciences, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758); IRCCS Istituto delle Scienze Neurologiche di Bologna, Functional and Molecular Neuroimaging Unit, Bologna, Italy (GRID:grid.492077.f) 
 University of Bologna, Department of Physics and Astronomy, Bologna, Italy (GRID:grid.6292.f) (ISNI:0000 0004 1757 1758) 
 Universidade NOVA de Lisboa, NOVA Information Management School (NOVA IMS), Lisbon, Portugal (GRID:grid.10772.33) (ISNI:0000 0001 2151 1713) 
10  Cambridge University Hospitals NHS Foundation Trust, Department of Imaging, Cambridge, United Kingdom (GRID:grid.24029.3d) (ISNI:0000 0004 0383 8386); University of Cambridge, Department of Radiology, Cambridge, United Kingdom (GRID:grid.5335.0) (ISNI:0000 0001 2188 5934); University of Oxford, Investigative Medicine Division, Radcliffe Department of Medicine, Oxford, United Kingdom (GRID:grid.4991.5) (ISNI:0000 0004 1936 8948) 
Pages
16239
Publication year
2023
Publication date
2023
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
2869406399
Copyright
© The Author(s) 2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.