ORIGINAL RESEARCH article

Front. Neurol.

Sec. Applied Neuroimaging

Volume 16 - 2025 | doi: 10.3389/fneur.2025.1570566

AI-Driven MRI Analysis Reveals Brain Atrophy Patterns in Benign Relapsing-Remitting Multiple Sclerosis

Provisionally accepted
Marja  NiiranenMarja Niiranen1*Paula  BendelPaula Bendel2Juha  KoikkalainenJuha Koikkalainen3Jyrki  LötjönenJyrki Lötjönen3Tuomas  SelanderTuomas Selander4Eino  SoljeEino Solje1Päivi  HartikainenPäivi Hartikainen1Sakari  SimulaSakari Simula5Ritva  VanninenRitva Vanninen2Anne  PortaankorvaAnne Portaankorva6
  • 1Neurocenter, Kuopio University Hospital, Kuopio, Finland
  • 2Deparment of Clinical Radiology, Diagnostic Imaging Center, Kuopio University Hospital, Kuopio, Northern Savonia, Finland
  • 3Combinostics Oy, Tampere, Pirkanmaa, Finland
  • 4Science Service Center, Kuopio University Hospital, Kuopio, Northern Savonia, Finland
  • 5Department of Neurology, Mikkeli Central Hospital, Mikkeli, Southern Savonia, Finland
  • 6Clinical Neurosciences, University of Helsinki, Helsinki, Finland

The final, formatted version of the article will be published soon.

The existence and definition of benign multiple sclerosis (MS) remain controversial, particularly given the discrepancy between clinical presentation and underlying imaging changes.In this study, we aimed to investigate the brain atrophy patterns related to benign relapsing-remitting MS (BRRMS), particularly regarding location and extent. We analyzed global and regional grey matter (GM) and white matter (WM) volumes, WM lesion load, corpus callosum index (CCI) and corpus callosum area (CCA) in well-defined benign relapsing-remitting MS patients (BRRMS, n = 35) compared to healthy controls (HC, n = 35). Imaging data were analyzed using an AI-based volumetric analysis MRI (cNeuro®) and confirmed visually by an experienced neuroradiologist, ensuring robust validation.Results: Total brain tissue volume was significantly smaller in patients with BRRMS compared to HC (p < 0.001), but the cortical (p = 0.011) and cerebral (p = 0.002) GM volumes, as well as cingulate gyrus (p=0.032) and entorhinal area volumes (p < 0.001), were larger in BRRMS. GM volumes in the postcentral gyrus (p = 0.001), precentral gyrus (p < 0.001), the medial segment of the precentral gyrus (p < 0.001), supplementary motor cortex (p < 0.001) and thalamus (p < 0.001) were reduced in BRRMS compared to HC. Furthermore, both CCI and CCA were significantly smaller in BRRMS (p < 0.001 and p = 0.001, respectively).Conclusions: Despite the overall reduced brain volume compared to HC, distinct cortical regions, especially within the limbic system (i.e. cingulate gyrus and entorhinal area) GM may be relatively well preserved, indicating a possible compensatory volume increase. Based on this study, the corpus callosum is a crucial structure in monitoring disease progression in BRRMS.for Merck and Sanofi, paid to his institution. ES has served on the advisory board of Novartis, EISAI and Roche, served as a consultant for Novo Nordisk, and received honoraria for lectures from Lundbeck and Roche. Other authors have no conflicts of interest.

Keywords: Corpus callosum index, brain atrophy, MRI, Benign multiple sclerosis, brain volumetry

Received: 03 Feb 2025; Accepted: 21 Apr 2025.

Copyright: © 2025 Niiranen, Bendel, Koikkalainen, Lötjönen, Selander, Solje, Hartikainen, Simula, Vanninen and Portaankorva. 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: Marja Niiranen, Neurocenter, Kuopio University Hospital, Kuopio, Finland

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.