{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T15:07:35Z","timestamp":1792595255419,"version":"4.5.0"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T00:00:00Z","timestamp":1728518400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>The rate of neurodegeneration in multiple sclerosis (MS) is an important biomarker for disease progression but can be challenging to quantify. The brain age gap, which quantifies the difference between a patient's chronological and their estimated biological brain age, might be a valuable biomarker of neurodegeneration in patients with MS. Thus, the aim of this study was to investigate the value of an image-based prediction of the brain age gap using a deep learning model and compare brain age gap values between healthy individuals and patients with MS.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A multi-center dataset consisting of 5,294 T1-weighted magnetic resonance images of the brain from healthy individuals aged between 19 and 89 years was used to train a convolutional neural network (CNN) for biological brain age prediction. The trained model was then used to calculate the brain age gap in 195 patients with relapsing remitting MS (20\u201360 years). Additionally, saliency maps were generated for healthy subjects and patients with MS to identify brain regions that were deemed important for the brain age prediction task by the CNN.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Overall, the application of the CNN revealed accelerated brain aging with a larger brain age gap for patients with MS with a mean of 6.98 \u00b1 7.18 years in comparison to healthy test set subjects (0.23 \u00b1 4.64 years). The brain age gap for MS patients was weakly to moderately correlated with age at disease onset (\u03c1 = \u22120.299, <jats:italic>p<\/jats:italic> &amp;lt; 0.0001), EDSS score (\u03c1 = 0.206, <jats:italic>p<\/jats:italic> = 0.004), disease duration (\u03c1 = 0.162, <jats:italic>p<\/jats:italic> = 0.024), lesion volume (\u03c1 = 0.630, <jats:italic>p<\/jats:italic> &amp;lt; 0.0001), and brain parenchymal fraction (\u03c1 = \u22120.718, <jats:italic>p<\/jats:italic> &amp;lt; 0.0001). The saliency maps indicated significant differences in the lateral ventricle (<jats:italic>p<\/jats:italic> &amp;lt; 0.0001), insula (<jats:italic>p<\/jats:italic> &amp;lt; 0.0001), third ventricle (<jats:italic>p<\/jats:italic> &amp;lt; 0.0001), and fourth ventricle (<jats:italic>p<\/jats:italic> = 0.0001) in the right hemisphere. In the left hemisphere, the inferior lateral ventricle (<jats:italic>p<\/jats:italic> &amp;lt; 0.0001) and the third ventricle (<jats:italic>p<\/jats:italic> &amp;lt; 0.0001) showed significant differences. Furthermore, the Dice similarity coefficient showed the highest overlap of salient regions between the MS patients and the oldest healthy subjects, indicating that neurodegeneration is accelerated in this patient cohort.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>In conclusion, the results of this study show that the brain age gap is a valuable surrogate biomarker to measure disease progression in patients with multiple sclerosis.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fneur.2024.1423485","type":"journal-article","created":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T04:49:05Z","timestamp":1728535745000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Analysis and visualization of the effect of multiple sclerosis on biological brain age"],"prefix":"10.3389","volume":"15","author":[{"given":"Catharina J. A.","family":"Romme","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma A. M.","family":"Stanley","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pauline","family":"Mouches","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Wilms","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G. Bruce","family":"Pike","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luanne M.","family":"Metz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nils D.","family":"Forkert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,10,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1191\/135245899678846221","article-title":"MRI in multiple sclerosis: correlation with expanded disability status scale (EDSS)","volume":"5","author":"Barkhof","year":"1999","journal-title":"Mult Scler J"},{"key":"B2","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1093\/brain\/awm291","article-title":"Normal-appearing white matter in multiple sclerosis is in a subtle balance between inflammation and neuroprotection","volume":"131","author":"Zeis","year":"2008","journal-title":"Brain"},{"key":"B3","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1148\/radiol.2541090817","article-title":"Clinically Isolated syndrome suggestive of multiple sclerosis: voxelwise regional investigation of white and gray matter","volume":"254","author":"Raz","year":"2010","journal-title":"Radiology"},{"key":"B4","doi-asserted-by":"publisher","first-page":"545","DOI":"10.12998\/wjcc.v3.i7.545","article-title":"Treatment strategies for multiple sclerosis: when to start, when to change, when to stop?","volume":"3","author":"Gajofatto","year":"2015","journal-title":"World J Clin Cases"},{"key":"B5","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1001\/archneurol.2008.567","article-title":"Rate of brain atrophy in benign vs early multiple sclerosis","volume":"66","author":"Gauthier","year":"2009","journal-title":"Arch Neurol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.3174\/ajnr.A2972","article-title":"Brain volume and diffusion markers as predictors of disability and short-term disease evolution in multiple sclerosis","volume":"33","author":"S\u00e4mann","year":"2012","journal-title":"Am J Neuroradiol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.3174\/ajnr.A3107","article-title":"Reliability of longitudinal brain volume loss measurements between 2 sites in patients with multiple sclerosis: comparison of 7 quantification techniques","volume":"33","author":"Durand-Dubief","year":"2012","journal-title":"Am J Neuroradiol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1212\/01.wnl.0000201238.93586.d9","article-title":"Gray and white matter brain atrophy and neuropsychological impairment in multiple sclerosis","volume":"66","author":"Sanfilipo","year":"2006","journal-title":"Neurology"},{"key":"B9","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10072-010-0370-x","article-title":"Cognition in multiple sclerosis: relevance of lesions, brain atrophy and proton MR spectroscopy","volume":"31","author":"Giorgio","year":"2010","journal-title":"Neurol Sci"},{"key":"B10","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1046\/j.1468-1331.2001.00147.x","article-title":"T1 lesion load and cerebral atrophy as a marker for clinical progression in patients with multiple sclerosis. A prospective 18 months follow-up study","volume":"8","author":"Sailer","year":"2001","journal-title":"Eur J Neurol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1038\/nrneurol.2015.157","article-title":"Rovira \u00c0, Miller D, Yousry TA, Sormani MP, de Stefano N, et al. MAGNIMS consensus guidelines on the use of MRI in multiple sclerosis\u2013establishing disease prognosis and monitoring patients","volume":"11","author":"Wattjes","year":"2015","journal-title":"Nat Rev Neurol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e4564","DOI":"10.1002\/nbm.4564","article-title":"MRI of healthy brain aging: a review","volume":"34","author":"MacDonald","year":"2021","journal-title":"NMR Biomed"},{"key":"B13","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1016\/j.tins.2017.10.001","article-title":"Predicting age using neuroimaging: innovative brain ageing biomarkers","volume":"40","author":"Cole","year":"2017","journal-title":"Trends Neurosci"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4117373","article-title":"A comparison of brain age estimation and brain parenchymal fraction as imaging markers in multiple sclerosis","author":"H\u00f8gest\u00f8l","year":"2022","journal-title":"SSRN Electron J."},{"key":"B15","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1038\/s41593-019-0471-7","article-title":"Common brain disorders are associated with heritable patterns of apparent aging of the brain","volume":"22","author":"Kaufmann","year":"2019","journal-title":"Nat Neurosci"},{"key":"B16","doi-asserted-by":"publisher","first-page":"3039","DOI":"10.1111\/ene.15473","article-title":"Brain age as a surrogate marker for cognitive performance in multiple sclerosis","volume":"29","author":"Denissen","year":"2022","journal-title":"Eur J Neurol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1002\/ana.25746","article-title":"Longitudinal assessment of multiple sclerosis with the brain-age paradigm","volume":"88","author":"Cole","year":"2020","journal-title":"Ann Neurol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1002\/acn3.51782","article-title":"\u201cBrain age\u201d predicts disability accumulation in multiple sclerosis","volume":"10","author":"Brier MR Li","year":"2023","journal-title":"Ann Clin Transl Neurol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"107679","DOI":"10.1016\/j.isci.2023.107679","article-title":"Similar neural pathways link psychological stress and brain-age in health and multiple sclerosis","volume":"26","author":"Schulz","year":"2023","journal-title":"iScience"},{"key":"B20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1136\/jnnp-2022-329680","article-title":"Brain age gap in neuromyelitis optica spectrum disorders and multiple sclerosis","volume":"94","author":"Wei","year":"2023","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"B21","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1002\/ana.22366","article-title":"Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria","volume":"69","author":"Polman","year":"2011","journal-title":"Ann Neurol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1212\/WNL.0000000000000560","article-title":"Defining the clinical course of multiple sclerosis: the 2013 revisions","volume":"83","author":"Lublin","year":"2014","journal-title":"Neurology"},{"key":"B23","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1093\/ije\/dyp394","article-title":"Cohort profile: the study of health in pomerania","volume":"40","author":"Vlzke","year":"2010","journal-title":"Int J Epidemiol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1101\/177279","article-title":"Structural and functional MRI from a cross-sectional Southwest University Adult lifespan Dataset (SALD)","author":"Wei","year":"2018","journal-title":"bioRxiv"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1101\/2019.12.13.19014902","article-title":"OASIS-3: longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer disease","author":"LaMontagne","year":"2019","journal-title":"medRxiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1109\/TMI.2022.3161947","article-title":"Invertible modeling of bidirectional relationships in neuroimaging with normalizing flows: application to brain aging","volume":"41","author":"Wilms","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"key":"B28","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1038\/s41597-020-0557-9","article-title":"CerebrA registration and manual label correction of mindboggle-101 atlas for MNI-ICBM152 template","volume":"7","author":"Manera","year":"2020","journal-title":"Sci Data"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2554","DOI":"10.1002\/hbm.25805","article-title":"Multimodal biological brain age prediction using magnetic resonance imaging and angiography with the identification of predictive regions","volume":"43","author":"Mouches","year":"2022","journal-title":"Hum Brain Mapp"},{"key":"B30","doi-asserted-by":"publisher","first-page":"101871","DOI":"10.1016\/j.media.2020.101871","article-title":"Accurate brain age prediction with lightweight deep neural networks","volume":"68","author":"Peng","year":"2021","journal-title":"Med Image Anal"},{"key":"B31","first-page":"807","article-title":"Rectified linear units improve restricted boltzmann machines","author":"Nair","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning (ICML-10)."},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03825","article-title":"SmoothGrad: removing noise by adding noise","author":"Smilkov","year":"2017","journal-title":"arXiv"},{"key":"B33","doi-asserted-by":"publisher","first-page":"061102","DOI":"10.1117\/1.JMI.9.6.061102","article-title":"Fairness-related performance and explainability effects in deep learning models for brain image analysis","volume":"9","author":"Stanley","year":"2022","journal-title":"J Med Imaging"},{"key":"B34","doi-asserted-by":"publisher","first-page":"117471","DOI":"10.1016\/j.neuroimage.2020.117471","article-title":"A contrast-adaptive method for simultaneous whole-brain and lesion segmentation in multiple sclerosis","volume":"225","author":"Cerri","year":"2021","journal-title":"Neuroimage"},{"key":"B35","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1146\/annurev.ps.46.020195.003021","article-title":"Multiple hypothesis testing","volume":"46","author":"Shaffer","year":"1995","journal-title":"Annu Rev Psychol"},{"key":"B36","doi-asserted-by":"publisher","first-page":"584888","DOI":"10.1101\/584888","article-title":"Accelerated brain ageing and disability in multiple sclerosis","author":"Cole","year":"2019","journal-title":"bioRxiv"},{"key":"B37","doi-asserted-by":"publisher","first-page":"989","DOI":"10.1001\/archneur.60.7.989","article-title":"Longitudinal study of brain volume changes in normal aging using serial registered magnetic resonance imaging","volume":"60","author":"Scahill","year":"2003","journal-title":"Arch Neurol"},{"key":"B38","first-page":"341","article-title":"Regional brain atrophy evolves differently in patients with multiple sclerosis according to clinical phenotype","volume":"26","author":"Pagani","year":"2005","journal-title":"Am J Neuroradiol"},{"key":"B39","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1212\/WNL.53.1.139","article-title":"A longitudinal study of brain atrophy in relapsing multiple sclerosis","volume":"53","author":"Simon","year":"1999","journal-title":"Neurology"},{"key":"B40","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1002\/hbm.24750","article-title":"Automated brain extraction of multisequence MRI using artificial neural networks","volume":"40","author":"Isensee","year":"2019","journal-title":"Hum Brain Mapp"},{"key":"B41","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1002\/hbm.20906","article-title":"The SRI24 multichannel atlas of normal adult human brain structure","volume":"31","author":"Rohlfing","year":"2010","journal-title":"Hum Brain Mapp"},{"key":"B42","doi-asserted-by":"publisher","first-page":"2047","DOI":"10.1109\/JBHI.2024.3352513","article-title":"Identifying biases in a multicenter MRI database for Parkinson's disease classification: is the disease classifier a secret site classifier?","volume":"28","author":"Souza","year":"2024","journal-title":"IEEE J Biomed Health Inf"},{"key":"B43","doi-asserted-by":"publisher","first-page":"941864","DOI":"10.3389\/fnagi.2022.941864","article-title":"An exploratory causal analysis of the relationships between the brain age gap and cardiovascular risk factors","volume":"14","author":"Mouches","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"B44","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1139\/gen-2020-0131","article-title":"Machine learning for precision medicine","volume":"64","author":"MacEachern","year":"2021","journal-title":"Genome"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1423485\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T04:49:09Z","timestamp":1728535749000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2024.1423485\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,10]]},"references-count":44,"alternative-id":["10.3389\/fneur.2024.1423485"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2024.1423485","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,10]]},"article-number":"1423485"}}