Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review

Multiple sclerosis (MS) is an autoimmune disease of the brain and spinal cord with both inflammatory and neurodegenerative features. Although advances in imaging techniques, particularly magnetic resonance imaging (MRI), have improved the process of diagnosis, its cause is unknown, a cure remains el...

Full description

Saved in:
Bibliographic Details
Main Authors: Adam C. Szekely-Kohn, Marco Castellani, Daniel M. Espino, Luca Baronti, Zubair Ahmed, William G. K. Manifold, Michael Douglas
Format: Article
Language:English
Published: The Royal Society 2025-01-01
Series:Royal Society Open Science
Subjects:
Online Access:https://royalsocietypublishing.org/doi/10.1098/rsos.241052
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849313300750270464
author Adam C. Szekely-Kohn
Marco Castellani
Daniel M. Espino
Luca Baronti
Zubair Ahmed
William G. K. Manifold
Michael Douglas
author_facet Adam C. Szekely-Kohn
Marco Castellani
Daniel M. Espino
Luca Baronti
Zubair Ahmed
William G. K. Manifold
Michael Douglas
author_sort Adam C. Szekely-Kohn
collection DOAJ
description Multiple sclerosis (MS) is an autoimmune disease of the brain and spinal cord with both inflammatory and neurodegenerative features. Although advances in imaging techniques, particularly magnetic resonance imaging (MRI), have improved the process of diagnosis, its cause is unknown, a cure remains elusive and the evidence base to guide treatment is lacking. Computational techniques like machine learning (ML) have started to be used to understand MS. Published MS MRI-based computational studies can be divided into five categories: automated diagnosis; differentiation between lesion types and/or MS stages; differential diagnosis; monitoring and predicting disease progression; and synthetic MRI dataset generation. Collectively, these approaches show promise in assisting with MS diagnosis, monitoring of disease activity and prediction of future progression, all potentially contributing to disease management. Analysis quality using ML is highly dependent on the dataset size and variability used for training. Wider public access would mean larger datasets for experimentation, resulting in higher-quality analysis, permitting for more conclusive research. This narrative review provides an outline of the fundamentals of MS pathology and pathogenesis, diagnostic techniques and data types in computational analysis, as well as collating literature pertaining to the application of computational techniques to MRI towards developing a better understanding of MS.
format Article
id doaj-art-826b72e2c4634a159b0aec650dad70f8
institution Kabale University
issn 2054-5703
language English
publishDate 2025-01-01
publisher The Royal Society
record_format Article
series Royal Society Open Science
spelling doaj-art-826b72e2c4634a159b0aec650dad70f82025-08-20T03:52:48ZengThe Royal SocietyRoyal Society Open Science2054-57032025-01-0112110.1098/rsos.241052Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative reviewAdam C. Szekely-Kohn0Marco Castellani1Daniel M. Espino2Luca Baronti3Zubair Ahmed4William G. K. Manifold5Michael Douglas6School of Engineering, University of Birmingham, Edgbaston, Birmingham B15 2TT, UKSchool of Engineering, University of Birmingham, Edgbaston, Birmingham B15 2TT, UKSchool of Engineering, University of Birmingham, Edgbaston, Birmingham B15 2TT, UKSchool of Computer Science, University of Birmingham, Edgbaston, Birmingham B15 2TT, UKUniversity Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham B15 2GW, UKThe Royal London Hospital, Barts Health NHS Trust, Whitechapel Road, London E1 1FR, UKUniversity Hospitals Birmingham NHS Foundation Trust, Edgbaston, Birmingham B15 2GW, UKMultiple sclerosis (MS) is an autoimmune disease of the brain and spinal cord with both inflammatory and neurodegenerative features. Although advances in imaging techniques, particularly magnetic resonance imaging (MRI), have improved the process of diagnosis, its cause is unknown, a cure remains elusive and the evidence base to guide treatment is lacking. Computational techniques like machine learning (ML) have started to be used to understand MS. Published MS MRI-based computational studies can be divided into five categories: automated diagnosis; differentiation between lesion types and/or MS stages; differential diagnosis; monitoring and predicting disease progression; and synthetic MRI dataset generation. Collectively, these approaches show promise in assisting with MS diagnosis, monitoring of disease activity and prediction of future progression, all potentially contributing to disease management. Analysis quality using ML is highly dependent on the dataset size and variability used for training. Wider public access would mean larger datasets for experimentation, resulting in higher-quality analysis, permitting for more conclusive research. This narrative review provides an outline of the fundamentals of MS pathology and pathogenesis, diagnostic techniques and data types in computational analysis, as well as collating literature pertaining to the application of computational techniques to MRI towards developing a better understanding of MS.https://royalsocietypublishing.org/doi/10.1098/rsos.241052artificial intelligencecomputational methodsmachine learningmagnetic resonance imaging (MRI)multiple sclerosis (MS)
spellingShingle Adam C. Szekely-Kohn
Marco Castellani
Daniel M. Espino
Luca Baronti
Zubair Ahmed
William G. K. Manifold
Michael Douglas
Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
Royal Society Open Science
artificial intelligence
computational methods
machine learning
magnetic resonance imaging (MRI)
multiple sclerosis (MS)
title Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
title_full Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
title_fullStr Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
title_full_unstemmed Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
title_short Machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis: a narrative review
title_sort machine learning for refining interpretation of magnetic resonance imaging scans in the management of multiple sclerosis a narrative review
topic artificial intelligence
computational methods
machine learning
magnetic resonance imaging (MRI)
multiple sclerosis (MS)
url https://royalsocietypublishing.org/doi/10.1098/rsos.241052
work_keys_str_mv AT adamcszekelykohn machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT marcocastellani machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT danielmespino machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT lucabaronti machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT zubairahmed machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT williamgkmanifold machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview
AT michaeldouglas machinelearningforrefininginterpretationofmagneticresonanceimagingscansinthemanagementofmultiplesclerosisanarrativereview