{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T20:59:54Z","timestamp":1793825994467,"version":"4.6.1"},"reference-count":49,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T00:00:00Z","timestamp":1726790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"publisher","award":["P2-0232"],"award-info":[{"award-number":["P2-0232"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004329","name":"Slovenian Research Agency","doi-asserted-by":"publisher","award":["J2-3059"],"award-info":[{"award-number":["J2-3059"]}],"id":[{"id":"10.13039\/501100004329","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biomedicines"],"abstract":"<jats:p>Background: Brain age prediction from brain MRI scans and the resulting brain age gap (BAG)\u2014the difference between predicted brain age and chronological age\u2014is a general biomarker for a variety of neurological, psychiatric, and other diseases or disorders. Methods: This study examined the differences in BAG values derived from T1-weighted scans using five state-of-the-art deep learning model architectures previously used in the brain age literature: 2D\/3D VGG, RelationNet, ResNet, and SFCN. The models were evaluated on healthy controls and cohorts with sleep apnea, diabetes, multiple sclerosis, Parkinson\u2019s disease, mild cognitive impairment, and Alzheimer\u2019s disease, employing rigorous statistical analysis, including repeated model training and linear mixed-effects models. Results: All five models consistently identified a statistically significant positive BAG for diabetes (ranging from 0.79 years with RelationNet to 2.13 years with SFCN), multiple sclerosis (2.67 years with 3D VGG to 4.24 years with 2D VGG), mild cognitive impairment (2.13 years with 2D VGG to 2.59 years with 3D VGG), and Alzheimer\u2019s dementia (5.54 years with ResNet to 6.48 years with SFCN). For Parkinson\u2019s disease, a statistically significant BAG increase was observed in all models except ResNet (1.30 years with 2D VGG to 2.59 years with 3D VGG). For sleep apnea, a statistically significant BAG increase was only detected with the SFCN model (1.59 years). Additionally, we observed a trend of decreasing BAG with increasing chronological age, which was more pronounced in diseased cohorts, particularly those with the largest BAG, such as multiple sclerosis (\u22120.34 to \u22120.2), mild cognitive impairment (\u22120.37 to \u22120.26), and Alzheimer\u2019s dementia (\u22120.66 to \u22120.47), compared to healthy controls (\u22120.18 to \u22120.1). Conclusions: Consistent with previous research, Alzheimer\u2019s dementia and multiple sclerosis exhibited the largest BAG across all models, with SFCN predicting the highest BAG overall. The negative BAG trend suggests a complex interplay of survival bias, disease progression, adaptation, and therapy that influences brain age prediction across the age spectrum.<\/jats:p>","DOI":"10.3390\/biomedicines12092139","type":"journal-article","created":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T07:38:57Z","timestamp":1726817937000},"page":"2139","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Analysis of Brain Age Gap across Subject Cohorts and Prediction Model Architectures"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9947-1501","authenticated-orcid":false,"given":"Lara","family":"Dular","sequence":"first","affiliation":[{"name":"University of Ljubljana, Faculty of Electrical Engineering, Tr\u017ea\u0161ka cesta 25, 1000 Ljubljana, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8300-0417","authenticated-orcid":false,"given":"\u017diga","family":"\u0160piclin","sequence":"additional","affiliation":[{"name":"University of Ljubljana, Faculty of Electrical Engineering, Tr\u017ea\u0161ka cesta 25, 1000 Ljubljana, Slovenia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"for the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"the Australian Imaging Biomarkers and Lifestyle Flagship Study of Ageing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2024,9,20]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/s10916-019-1401-7","article-title":"Age Prediction Based on Brain MRI Image: A Survey","volume":"43","author":"Sajedi","year":"2019","journal-title":"J. Med. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Moskalev, A. (2019). Quantification of the Biological Age of the Brain Using Neuroimaging. Biomarkers of Human Aging, Springer International Publishing.","DOI":"10.1007\/978-3-030-24970-0"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1093\/brain\/awaa160","article-title":"MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14468 individuals worldwide","volume":"143","author":"Bashyam","year":"2020","journal-title":"Brain"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"618","DOI":"10.14336\/AD.2019.0617","article-title":"T1-weighted MRI-driven Brain Age Estimation in Alzheimer\u2019s Disease and Parkinson\u2019s Disease","volume":"11","author":"Beheshti","year":"2020","journal-title":"Aging Dis."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.neurobiolaging.2021.08.020","article-title":"Brain age and Alzheimer\u2019s-like atrophy are domain-specific predictors of cognitive impairment in Parkinson\u2019s disease","volume":"109","author":"Erus","year":"2022","journal-title":"Neurobiol. Aging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1038\/s41531-024-00673-7","article-title":"Advanced brain aging in Parkinson\u2019s disease with cognitive impairment","volume":"10","author":"Chen","year":"2024","journal-title":"NPJ Park. Dis."},{"key":"ref_7","first-page":"235","article-title":"Longitudinal changes in individual BrainAGE in healthy aging, mild cognitive impairment, and Alzheimer\u2019s disease","volume":"25","author":"Franke","year":"2012","journal-title":"GeroPsych J. Gerontopsychol. Geriatr. Psychiatry"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s43587-022-00219-7","article-title":"Deep learning-based brain age prediction in normal aging and dementia","volume":"2","author":"Lee","year":"2022","journal-title":"Nat. Aging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3400","DOI":"10.1109\/TMI.2021.3085948","article-title":"Brain Age Estimation From MRI Using Cascade Networks With Ranking Loss","volume":"40","author":"Cheng","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"H\u00f8gest\u00f8l, E.A., Kaufmann, T., Nygaard, G.O., Beyer, M.K., Sowa, P., Nordvik, J.E., Kolsk\u00e5r, K., Richard, G., Andreassen, O.A., and Harbo, H.F. (2019). Cross-Sectional and Longitudinal MRI Brain Scans Reveal Accelerated Brain Aging in Multiple Sclerosis. Front. Neurol., 10.","DOI":"10.3389\/fneur.2019.00450"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1002\/acn3.51782","article-title":"\u201cBrain age\u201d predicts disability accumulation in multiple sclerosis","volume":"10","author":"Brier","year":"2023","journal-title":"Ann. Clin. Transl. Neurol."},{"key":"ref_12","doi-asserted-by":"crossref","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":"ref_13","doi-asserted-by":"crossref","unstructured":"Franke, K., Gaser, C., Manor, B., and Novak, V. (2013). Advanced BrainAGE in older adults with type 2 diabetes mellitus. Front. Aging Neurosci., 5.","DOI":"10.3389\/fnagi.2013.00090"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.neurobiolaging.2018.10.016","article-title":"Brain age from the electroencephalogram of sleep","volume":"74","author":"Sun","year":"2019","journal-title":"Neurobiol. Aging"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kolbeinsson, A., Filippi, S., Panagakis, Y., Matthews, P.M., Elliott, P., Dehghan, A., and Tzoulaki, I. (2020). Accelerated MRI-predicted brain ageing and its associations with cardiometabolic and brain disorders. Sci. Rep., 10.","DOI":"10.1038\/s41598-020-76518-z"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.neurobiolaging.2020.03.014","article-title":"Multimodality neuroimaging brain-age in UK biobank: Relationship to biomedical, lifestyle, and cognitive factors","volume":"92","author":"Cole","year":"2020","journal-title":"Neurobiol. Aging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105921","DOI":"10.1016\/j.psyneuen.2022.105921","article-title":"Accelerated brain aging in individuals with diabetes: Association with poor glycemic control and increased all-cause mortality","volume":"145","author":"Jha","year":"2022","journal-title":"Psychoneuroendocrinology"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"781","DOI":"10.4093\/dmj.2021.0189","article-title":"Association between Type 2 Diabetes Mellitus and Brain Atrophy: A Meta-Analysis","volume":"46","author":"Zhang","year":"2022","journal-title":"Diabetes Metab. J."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wang, D.Q., Wang, L., Wei, M.M., Xia, X.S., Tian, X.L., Cui, X.H., and Li, X. (2020). Relationship Between Type 2 Diabetes and White Matter Hyperintensity: A Systematic Review. Front. Endocrinol., 11.","DOI":"10.3389\/fendo.2020.595962"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"zsaa204","DOI":"10.1093\/sleep\/zsaa204","article-title":"Associations between sleep apnea and advanced brain aging in a large-scale population study","volume":"44","author":"Weihs","year":"2021","journal-title":"Sleep"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s00429-020-02184-6","article-title":"When your brain looks older than expected: Combined lifestyle risk and BrainAGE","volume":"226","author":"Bittner","year":"2021","journal-title":"Brain Struct. Funct."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"120469","DOI":"10.1016\/j.neuroimage.2023.120469","article-title":"BASE: Brain Age Standardized Evaluation","volume":"285","author":"Dular","year":"2024","journal-title":"NeuroImage"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1002\/hbm.25368","article-title":"Brain age prediction: A comparison between machine learning models using region- and voxel-based morphometric data","volume":"42","author":"Baecker","year":"2021","journal-title":"Hum. Brain Mapp."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1432","DOI":"10.1109\/JBHI.2021.3083187","article-title":"Predicting Brain Age Using Machine Learning Algorithms: A Comprehensive Evaluation","volume":"26","author":"Beheshti","year":"2022","journal-title":"IEEE J. Biomed. Health Infor."},{"key":"ref_25","doi-asserted-by":"crossref","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":"ref_26","doi-asserted-by":"crossref","first-page":"119947","DOI":"10.1016\/j.neuroimage.2023.119947","article-title":"Brain-age prediction: A systematic comparison of machine learning workflows","volume":"270","author":"More","year":"2023","journal-title":"NeuroImage"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Shafto, M.A., Tyler, L.K., Dixon, M., Taylor, J.R., Rowe, J.B., Cusack, R., Calder, A.J., Marslen-Wilson, W.D., Duncan, J., and Dalgleish, T. (2014). The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) study protocol: A cross-sectional, lifespan, multidisciplinary examination of healthy cognitive ageing. BMC Neurol., 14.","DOI":"10.1186\/s12883-014-0204-1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.neuroimage.2015.09.018","article-title":"The Cambridge Centre for Ageing and Neuroscience (Cam-CAN) data repository: Structural and functional MRI, MEG, and cognitive data from a cross-sectional adult lifespan sample","volume":"144","author":"Taylor","year":"2017","journal-title":"NeuroImage"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1016\/j.neuroimage.2017.08.021","article-title":"An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement","volume":"170","author":"Souza","year":"2018","journal-title":"NeuroImage"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1162\/jocn.2009.21407","article-title":"Open Access Series of Imaging Studies: Longitudinal MRI Data in Nondemented and Demented Older Adults","volume":"22","author":"Marcus","year":"2010","journal-title":"J. Cogn. Neurosci."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1038\/nn.4393","article-title":"Multimodal population brain imaging in the UK Biobank prospective epidemiological study","volume":"19","author":"Miller","year":"2016","journal-title":"Nat. Neurosci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"125","DOI":"10.31887\/DCNS.2007.9.2\/mpucak","article-title":"Neuropsychiatric manifestations of depression in multiple sclerosis: Neuroinflammatory, neuroendocrine, and neurotrophic mechanisms in the pathogenesis of immune-mediated depression","volume":"9","author":"Pucak","year":"2007","journal-title":"Dialogues Clin. Neurosci."},{"key":"ref_33","first-page":"e27750","article-title":"Depression in Parkinson\u2019s Disease: A Narrative Review","volume":"14","author":"Chikatimalla","year":"2022","journal-title":"Cureus"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1017\/S1041610209009405","article-title":"The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging: Methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of Alzheimer\u2019s disease","volume":"21","author":"Ellis","year":"2009","journal-title":"Int. Psychogeriatr."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Dular, L., Pernu\u0161, F., and \u0160piclin, \u017d. (2024). Extensive T1-weighted MRI preprocessing improves generalizability of deep brain age prediction models. Comput. Biol. Med., 173.","DOI":"10.1016\/j.compbiomed.2024.108320"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1002\/jmri.22003","article-title":"Adaptive non-local means denoising of MR images with spatially varying noise levels","volume":"31","author":"Collins","year":"2010","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"024003","DOI":"10.1117\/1.JMI.1.2.024003","article-title":"Global image registration using a symmetric block-matching approach","volume":"1","author":"Modat","year":"2014","journal-title":"J. Med. Imaging"},{"key":"ref_38","doi-asserted-by":"crossref","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":"ref_39","doi-asserted-by":"crossref","unstructured":"Huang, T., Chen, H., Fujimoto, R., Ito, K., Wu, K., Sato, K., Taki, Y., Fukuda, H., and Aoki, T. (2017, January 18\u201321). Age estimation from brain MRI images using deep learning. Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, Australia.","DOI":"10.1109\/ISBI.2017.7950650"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neuroimage.2017.07.059","article-title":"Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker","volume":"163","author":"Cole","year":"2017","journal-title":"NeuroImage"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2304","DOI":"10.1109\/TMI.2022.3161739","article-title":"Deep Relation Learning for Regression and Its Application to Brain Age Estimation","volume":"41","author":"He","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1007\/s00429-023-02686-z","article-title":"MRI-based brain age prediction model for children under 3 years old using deep residual network","volume":"228","author":"Hu","year":"2023","journal-title":"Brain Struct. Funct."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Dartora, C., Marseglia, A., M\u00e5rtensson, G., Rukh, G., Dang, J., Muehlboeck, J.S., Wahlund, L.O., Moreno, R., Barroso, J., and Ferreira, D. (2024). A deep learning model for brain age prediction using minimally preprocessed T1w images as input. Front. Aging Neurosci., 15.","DOI":"10.3389\/fnagi.2023.1303036"},{"key":"ref_44","doi-asserted-by":"crossref","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":"ref_45","doi-asserted-by":"crossref","first-page":"4092","DOI":"10.1002\/hbm.25533","article-title":"Pitfalls in brain age analyses","volume":"42","author":"Butler","year":"2021","journal-title":"Hum. Brain Mapp."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"3113","DOI":"10.1002\/hbm.25837","article-title":"Mind the gap: Performance metric evaluation in brain-age prediction","volume":"43","author":"Rokicki","year":"2022","journal-title":"Hum. Brain Mapp."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5235","DOI":"10.1038\/s41380-022-01728-y","article-title":"Independent replication of advanced brain age in mild cognitive impairment and dementia: Detection of future cognitive dysfunction","volume":"27","author":"Karim","year":"2022","journal-title":"Mol. Psychiatry"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"e616","DOI":"10.1212\/NXI.0000000000000616","article-title":"Contribution of normal aging to brain atrophy in MS","volume":"6","author":"Azevedo","year":"2019","journal-title":"Neurol. Neuroimmunol. Neuroinflamm."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1001\/jamaneurol.2017.2180","article-title":"Association of Sleep-Disordered Breathing with Cognitive Function and Risk of Cognitive Impairment: A Systematic Review and Meta-analysis","volume":"74","author":"Leng","year":"2017","journal-title":"JAMA Neurol."}],"container-title":["Biomedicines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9059\/12\/9\/2139\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:00:51Z","timestamp":1760112051000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9059\/12\/9\/2139"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,20]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,9]]}},"alternative-id":["biomedicines12092139"],"URL":"https:\/\/doi.org\/10.3390\/biomedicines12092139","relation":{},"ISSN":["2227-9059"],"issn-type":[{"value":"2227-9059","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,20]]}}}