{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:16:58Z","timestamp":1783437418382,"version":"3.54.6"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002957","name":"Technische Universit\u00e4t Dresden","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002957","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Brain Inf."],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Deep learning (DL) methods increasingly outperform classical approaches in brain MRI analysis, yet their generalizability across independent imaging cohorts remains insufficiently evaluated. Because age and sex are fundamental neurobiological factors influencing brain structure and disease risk, this study systematically compares three three-dimensional architectures\u2014Simple Fully Convolutional Network (SFCN), DenseNet121, and Swin Transformer\u2014for age and sex prediction using T1-weighted MRI from four independent cohorts: UK Biobank (UKB, n\u2009=\u200947,390), Dallas Lifespan Brain Study (DLBS, n\u2009=\u2009132), Parkinson\u2019s Progression Markers Initiative (PPMI, n\u2009=\u2009108 controls), and Information eXtraction from Images (IXI, n\u2009=\u2009319). SFCN consistently demonstrated the most robust performance. For sex classification, it achieved an AUC of 1.00 [1.00\u20131.00] in the UKB internal test set and 0.85\u20130.91 across external cohorts. For age prediction, SFCN achieved a mean absolute error (MAE) of 2.66\u00a0years (r\u2009=\u20090.89) internally and 4.98\u20135.81\u00a0years (r\u2009=\u20090.55\u20130.70) externally. Pairwise DeLong and Wilcoxon tests with Bonferroni correction confirmed significantly better performance of SFCN compared with Swin Transformer in most cohorts (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.017). No significant demographic subgroup biases were observed. Explainability analyses further showed task-specific and spatially consistent attention patterns across cohorts. These findings demonstrate that simpler convolutional architectures can generalize more reliably than more complex attention-based models in multi-cohort settings. The study highlights the importance of external validation and emphasizes potential trade-offs between model complexity, robustness, and interpretability for clinically relevant neuroimaging applications.\n                  <\/jats:p>","DOI":"10.1186\/s40708-026-00316-y","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T03:45:21Z","timestamp":1783309521000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalizable and explainable deep learning for brain MRI: a multi-cohort evaluation of 3D architectures for age and sex prediction"],"prefix":"10.1186","volume":"13","author":[{"given":"Radhika","family":"Juglan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta","family":"Ligero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zunamys I.","family":"Carrero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asier","family":"Rabasco Meneghetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Lenz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leo","family":"Misera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory Patrick","family":"Veldhuizen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Kuntke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hagen H.","family":"Kitzler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sven","family":"Nebelung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Truhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jakob Nikolas","family":"Kather","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,6]]},"reference":[{"key":"316_CR1","doi-asserted-by":"publisher","first-page":"4084","DOI":"10.1038\/s41380-023-02215-8","volume":"28","author":"L Chouliaras","year":"2023","unstructured":"Chouliaras L, O\u2019Brien JT (2023) The use of neuroimaging techniques in the early and differential diagnosis of dementia. Mol Psychiatry 28:4084\u20134097","journal-title":"Mol Psychiatry"},{"key":"316_CR2","first-page":"e27224","volume":"14","author":"EH Tedyanto","year":"2022","unstructured":"Tedyanto EH, Tini K, Pramana NAK (2022) Magnetic resonance imaging in acute ischemic stroke. Cureus 14:e27224","journal-title":"Cureus"},{"key":"316_CR3","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/nrneurol.2009.215","volume":"6","author":"GB Frisoni","year":"2010","unstructured":"Frisoni GB, Fox NC, Jack CR Jr, Scheltens P, Thompson PM (2010) The clinical use of structural MRI in Alzheimer disease. Nat Rev Neurol 6:67\u201377","journal-title":"Nat Rev Neurol"},{"key":"316_CR4","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.neuroimage.2010.12.073","volume":"55","author":"P Vemuri","year":"2011","unstructured":"Vemuri P et al (2011) Antemortem differential diagnosis of dementia pathology using structural MRI: differential-STAND. Neuroimage 55:522\u2013531","journal-title":"Neuroimage"},{"key":"316_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00415-018-8892-x","volume":"266","author":"T Yousaf","year":"2019","unstructured":"Yousaf T, Dervenoulas G, Valkimadi P-E, Politis M (2019) Neuroimaging in Lewy body dementia. J Neurol 266:1\u201326","journal-title":"J Neurol"},{"key":"316_CR6","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1212\/01.wnl.0000324924.91351.7d","volume":"71","author":"JL Whitwell","year":"2008","unstructured":"Whitwell JL et al (2008) MRI correlates of neurofibrillary tangle pathology at autopsy: a voxel-based morphometry study. Neurology 71:743\u2013749","journal-title":"Neurology"},{"key":"316_CR7","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1212\/WNL.58.5.750","volume":"58","author":"CR Jack Jr","year":"2002","unstructured":"Jack CR Jr et al (2002) Antemortem MRI findings correlate with hippocampal neuropathology in typical aging and dementia. Neurology 58:750\u2013757","journal-title":"Neurology"},{"key":"316_CR8","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1136\/jnnp-2016-314978","volume":"88","author":"L Harper","year":"2017","unstructured":"Harper L et al (2017) Patterns of atrophy in pathologically confirmed dementias: a voxelwise analysis. J Neurol Neurosurg Psychiatry 88:908\u2013916","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"316_CR9","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.neurobiolaging.2017.10.008","volume":"62","author":"DM Cash","year":"2018","unstructured":"Cash DM et al (2018) Patterns of gray matter atrophy in genetic frontotemporal dementia: results from the GENFI study. Neurobiol Aging 62:191\u2013196","journal-title":"Neurobiol Aging"},{"key":"316_CR10","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1016\/S1474-4422(06)70550-6","volume":"5","author":"BH Ridha","year":"2006","unstructured":"Ridha BH et al (2006) Tracking atrophy progression in familial Alzheimer\u2019s disease: a serial MRI study. Lancet Neurol 5:828\u2013834","journal-title":"Lancet Neurol"},{"key":"316_CR11","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/j.jalz.2013.07.003","volume":"10","author":"DLG Hill","year":"2014","unstructured":"Hill DLG et al (2014) Coalition Against Major Diseases\/European Medicines Agency biomarker qualification of hippocampal volume for enrichment of clinical trials in predementia stages of Alzheimer\u2019s disease. Alzheimers Dement 10:421\u20139.e3","journal-title":"Alzheimers Dement"},{"key":"316_CR12","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/S1474-4422(14)70324-2","volume":"14","author":"JD Rohrer","year":"2015","unstructured":"Rohrer JD et al (2015) Presymptomatic cognitive and neuroanatomical changes in genetic frontotemporal dementia in the Genetic Frontotemporal dementia Initiative (GENFI) study: a cross-sectional analysis. Lancet Neurol 14:253\u2013262","journal-title":"Lancet Neurol"},{"key":"316_CR13","doi-asserted-by":"publisher","first-page":"331","DOI":"10.3233\/JAD-200246","volume":"76","author":"N Nicastro","year":"2020","unstructured":"Nicastro N et al (2020) Cortical complexity analyses and their cognitive correlate in Alzheimer\u2019s disease and frontotemporal dementia. J Alzheimers Dis 76:331\u2013340","journal-title":"J Alzheimers Dis"},{"key":"316_CR14","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1093\/brain\/awm016","volume":"130","author":"A-T Du","year":"2007","unstructured":"Du A-T et al (2007) Different regional patterns of cortical thinning in Alzheimer\u2019s disease and frontotemporal dementia. Brain 130:1159\u20131166","journal-title":"Brain"},{"key":"316_CR15","doi-asserted-by":"publisher","first-page":"e0220739","DOI":"10.1371\/journal.pone.0220739","volume":"14","author":"M Choi","year":"2019","unstructured":"Choi M et al (2019) Comparison of neurodegenerative types using different brain MRI analysis metrics in older adults with normal cognition, mild cognitive impairment, and Alzheimer\u2019s dementia. PLoS ONE 14:e0220739","journal-title":"PLoS ONE"},{"key":"316_CR16","doi-asserted-by":"publisher","first-page":"38","DOI":"10.3389\/fnagi.2017.00038","volume":"9","author":"AM K\u00e4lin","year":"2017","unstructured":"K\u00e4lin AM et al (2017) Subcortical shape changes, hippocampal atrophy and cortical thinning in future Alzheimer\u2019s disease patients. Front Aging Neurosci 9:38","journal-title":"Front Aging Neurosci"},{"key":"316_CR17","doi-asserted-by":"publisher","first-page":"1746","DOI":"10.1002\/mds.25240","volume":"27","author":"N Ibarretxe-Bilbao","year":"2012","unstructured":"Ibarretxe-Bilbao N et al (2012) Progression of cortical thinning in early Parkinson\u2019s disease: cortical thinning in early PD. Mov Disord 27:1746\u20131753","journal-title":"Mov Disord"},{"key":"316_CR18","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1097\/WCO.0000000000000571","volume":"31","author":"M Filippi","year":"2018","unstructured":"Filippi M, Agosta F (2018) MRI of non-Alzheimer\u2019s dementia: current and emerging knowledge. Curr Opin Neurol 31:405\u2013414","journal-title":"Curr Opin Neurol"},{"key":"316_CR19","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1111\/ene.14174","volume":"27","author":"MT Ferretti","year":"2020","unstructured":"Ferretti MT et al (2020) Sex and gender differences in Alzheimer\u2019s disease: current challenges and implications for clinical practice: Position paper of the Dementia and Cognitive Disorders Panel of the European Academy of Neurology: Position paper of the Dementia and Cognitive Disorders Panel of the European Academy of Neurology. Eur J Neurol 27:928\u2013943","journal-title":"Eur J Neurol"},{"key":"316_CR20","doi-asserted-by":"publisher","first-page":"54","DOI":"10.5498\/wjp.v6.i1.54","volume":"6","author":"KR Laws","year":"2016","unstructured":"Laws KR, Irvine K, Gale TM (2016) Sex differences in cognitive impairment in Alzheimer\u2019s disease. World J Psychiatry 6:54\u201365","journal-title":"World J Psychiatry"},{"key":"316_CR21","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/S1474-4422(16)00067-3","volume":"15","author":"CM Mazure","year":"2016","unstructured":"Mazure CM, Swendsen J (2016) Sex differences in Alzheimer\u2019s disease and other dementias. Lancet Neurol 15:451\u2013452","journal-title":"Lancet Neurol"},{"key":"316_CR22","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1016\/j.neuron.2024.01.024","volume":"112","author":"C Lopez-Lee","year":"2024","unstructured":"Lopez-Lee C, Torres ERS, Carling G, Gan L (2024) Mechanisms of sex differences in Alzheimer\u2019s disease. Neuron 112:1208\u20131221","journal-title":"Neuron"},{"key":"316_CR23","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1001\/jamaneurol.2014.4821","volume":"72","author":"CR Jack Jr","year":"2015","unstructured":"Jack CR Jr et al (2015) Age, sex, and APOE \u03b54 effects on memory, brain structure, and \u03b2-amyloid across the adult life span. JAMA Neurol 72:511\u2013519","journal-title":"JAMA Neurol"},{"key":"316_CR24","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1038\/s41537-023-00345-0","volume":"9","author":"S Aoyama","year":"2023","unstructured":"Aoyama S et al (2023) Sex differences in brainstem structure volumes in patients with schizophrenia. Schizophrenia (Heidelb) 9:16","journal-title":"Schizophrenia (Heidelb)"},{"key":"316_CR25","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1038\/s41386-021-01252-7","volume":"47","author":"X Hu","year":"2022","unstructured":"Hu X et al (2022) Sex-specific alterations of cortical morphometry in treatment-na\u00efve patients with major depressive disorder. Neuropsychopharmacology 47:2002\u20132009","journal-title":"Neuropsychopharmacology"},{"key":"316_CR26","doi-asserted-by":"publisher","first-page":"2799","DOI":"10.1093\/brain\/awt216","volume":"136","author":"M-C Lai","year":"2013","unstructured":"Lai M-C et al (2013) Biological sex affects the neurobiology of autism. Brain 136:2799\u20132815","journal-title":"Brain"},{"key":"316_CR27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1176\/appi.ajp.20220194","volume":"180","author":"DL Floris","year":"2023","unstructured":"Floris DL et al (2023) The link between autism and sex-related neuroanatomy, and associated cognition and gene expression. Am J Psychiatry 180:50\u201364","journal-title":"Am J Psychiatry"},{"key":"316_CR28","doi-asserted-by":"publisher","first-page":"5124","DOI":"10.1038\/s41380-020-0754-0","volume":"26","author":"LKM Han","year":"2021","unstructured":"Han LKM et al (2021) Brain aging in major depressive disorder: results from the ENIGMA major depressive disorder working group. Mol Psychiatry 26:5124\u20135139","journal-title":"Mol Psychiatry"},{"key":"316_CR29","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1038\/s41398-021-01524-2","volume":"11","author":"LKM Han","year":"2021","unstructured":"Han LKM et al (2021) Contributing factors to advanced brain aging in depression and anxiety disorders. Transl Psychiatry 11:402","journal-title":"Transl Psychiatry"},{"key":"316_CR30","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1038\/s41386-021-00967-x","volume":"46","author":"K Dunlop","year":"2021","unstructured":"Dunlop K, Victoria LW, Downar J, Gunning FM, Liston C (2021) Accelerated brain aging predicts impulsivity and symptom severity in depression. Neuropsychopharmacology 46:911\u2013919","journal-title":"Neuropsychopharmacology"},{"key":"316_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00117-022-01051-1","volume":"62","author":"K-H Nenning","year":"2022","unstructured":"Nenning K-H, Langs G (2022) Machine learning in neuroimaging: from research to clinical practice. Radiologie (Heidelb) 62:1\u201310","journal-title":"Radiologie (Heidelb)"},{"key":"316_CR32","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.neuroimage.2016.11.005","volume":"148","author":"F Liem","year":"2017","unstructured":"Liem F et al (2017) Predicting brain-age from multimodal imaging data captures cognitive impairment. Neuroimage 148:179\u2013188","journal-title":"Neuroimage"},{"key":"316_CR33","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/j.neuroimage.2010.01.005","volume":"50","author":"K Franke","year":"2010","unstructured":"Franke K, Ziegler G, Kl\u00f6ppel S, Gaser C, Alzheimer\u2019s Disease Neuroimaging Initiative (2010) Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters. Neuroimage 50:883\u2013892","journal-title":"Neuroimage"},{"key":"316_CR34","doi-asserted-by":"publisher","first-page":"2959","DOI":"10.1093\/cercor\/bhy109","volume":"28","author":"SJ Ritchie","year":"2018","unstructured":"Ritchie SJ et al (2018) Sex differences in the adult human brain: evidence from 5216 UK biobank participants. Cereb Cortex 28:2959\u20132975","journal-title":"Cereb Cortex"},{"key":"316_CR35","doi-asserted-by":"publisher","first-page":"e26768","DOI":"10.1002\/hbm.26768","volume":"45","author":"Y Yu","year":"2024","unstructured":"Yu Y et al (2024) Brain-age prediction: systematic evaluation of site effects, and sample age range and size. Hum Brain Mapp 45:e26768","journal-title":"Hum Brain Mapp"},{"key":"316_CR36","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41467-020-20655-6","volume":"12","author":"A Abrol","year":"2021","unstructured":"Abrol A et al (2021) Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning. Nat Commun 12:353","journal-title":"Nat Commun"},{"key":"316_CR37","doi-asserted-by":"publisher","first-page":"101871","DOI":"10.1016\/j.media.2020.101871","volume":"68","author":"H Peng","year":"2021","unstructured":"Peng H, Gong W, Beckmann CF, Vedaldi A, Smith SM (2021) Accurate brain age prediction with lightweight deep neural networks. Med Image Anal 68:101871","journal-title":"Med Image Anal"},{"key":"316_CR38","doi-asserted-by":"publisher","first-page":"5097","DOI":"10.3390\/s20185097","volume":"20","author":"SP Singh","year":"2020","unstructured":"Singh SP et al (2020) 3D deep learning on medical images: a review. Sensors (Basel) 20:5097","journal-title":"Sensors (Basel)"},{"key":"316_CR39","doi-asserted-by":"publisher","first-page":"101694","DOI":"10.1016\/j.media.2020.101694","volume":"63","author":"J Wen","year":"2020","unstructured":"Wen J et al (2020) Convolutional neural networks for classification of Alzheimer\u2019s disease: overview and reproducible evaluation. Med Image Anal 63:101694","journal-title":"Med Image Anal"},{"key":"316_CR40","doi-asserted-by":"publisher","first-page":"5409","DOI":"10.1038\/s41467-019-13163-9","volume":"10","author":"BA Jonsson","year":"2019","unstructured":"Jonsson BA et al (2019) Brain age prediction using deep learning uncovers associated sequence variants. Nat Commun 10:5409","journal-title":"Nat Commun"},{"key":"316_CR41","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.neurobiolaging.2020.02.009","volume":"91","author":"X Feng","year":"2020","unstructured":"Feng X et al (2020) Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging. Neurobiol Aging 91:15\u201325","journal-title":"Neurobiol Aging"},{"key":"316_CR42","doi-asserted-by":"publisher","first-page":"25051","DOI":"10.1007\/s11042-020-09121-z","volume":"79","author":"N Pardakhti","year":"2020","unstructured":"Pardakhti N, Sajedi H (2020) Brain age estimation based on 3D MRI images using 3D convolutional neural network. Multimed Tools Appl 79:25051\u201325065","journal-title":"Multimed Tools Appl"},{"key":"316_CR43","unstructured":"Kayalibay B, Jensen G, van der Smagt P (2017) CNN-based segmentation of medical imaging data. arXiv [cs.CV] (2017)."},{"key":"316_CR44","doi-asserted-by":"publisher","first-page":"9835","DOI":"10.1038\/s41598-024-60340-y","volume":"14","author":"J Chen","year":"2024","unstructured":"Chen J, Bayanagari VL, Chung S, Wang Y, Lui YW (2024) Deep learning with diffusion MRI as in vivo microscope reveals sex-related differences in human white matter microstructure. Sci Rep 14:9835","journal-title":"Sci Rep"},{"key":"316_CR45","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.neuroimage.2017.07.059","volume":"163","author":"JH Cole","year":"2017","unstructured":"Cole JH et al (2017) Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker. Neuroimage 163:115\u2013124","journal-title":"Neuroimage"},{"key":"316_CR46","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s10278-017-9983-4","volume":"30","author":"Z Akkus","year":"2017","unstructured":"Akkus Z, Galimzianova A, Hoogi A, Rubin DL, Erickson BJ (2017) Deep learning for brain MRI segmentation: state of the art and future directions. J Digit Imaging 30:449\u2013459","journal-title":"J Digit Imaging"},{"key":"316_CR47","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.neuroimage.2017.02.035","volume":"170","author":"C Wachinger","year":"2018","unstructured":"Wachinger C, Reuter M, Klein T (2018) DeepNAT: deep convolutional neural network for segmenting neuroanatomy. Neuroimage 170:434\u2013445","journal-title":"Neuroimage"},{"key":"316_CR48","doi-asserted-by":"crossref","unstructured":"Liu Z et al (2021) Swin transformer: hierarchical vision transformer using shifted windows. In: 2021 IEEE\/CVF international conference on computer vision (ICCV) 9992\u201310002. IEEE","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"316_CR49","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s12938-023-01157-0","volume":"22","author":"CC Atabansi","year":"2023","unstructured":"Atabansi CC et al (2023) A survey of Transformer applications for histopathological image analysis: new developments and future directions. Biomed Eng Online 22:96","journal-title":"Biomed Eng Online"},{"key":"316_CR50","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.ccell.2023.08.002","volume":"41","author":"SJ Wagner","year":"2023","unstructured":"Wagner SJ et al (2023) Transformer-based biomarker prediction from colorectal cancer histology: a large-scale multicentric study. Cancer Cell 41:1650-1661.e4","journal-title":"Cancer Cell"},{"key":"316_CR51","unstructured":"MRI volume-based robust brain age estimation using weight-shared spatial attention in 3D CNNs. https:\/\/arxiv.org\/html\/2407.06686v1"},{"key":"316_CR52","doi-asserted-by":"publisher","first-page":"117293","DOI":"10.1016\/j.neuroimage.2020.117293","volume":"223","author":"E Adeli","year":"2020","unstructured":"Adeli E et al (2020) Deep learning identifies morphological determinants of sex differences in the pre-adolescent brain. Neuroimage 223:117293","journal-title":"Neuroimage"},{"key":"316_CR53","doi-asserted-by":"publisher","first-page":"2304","DOI":"10.1109\/TMI.2022.3161739","volume":"41","author":"S He","year":"2022","unstructured":"He S, Feng Y, Grant PE, Ou Y (2022) Deep relation learning for regression and its application to brain age estimation. IEEE Trans Med Imaging 41:2304\u20132317","journal-title":"IEEE Trans Med Imaging"},{"key":"316_CR54","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1038\/nn.4393","volume":"19","author":"KL Miller","year":"2016","unstructured":"Miller KL et al (2016) Multimodal population brain imaging in the UK Biobank prospective epidemiological study. Nat Neurosci 19:1523\u20131536","journal-title":"Nat Neurosci"},{"key":"316_CR55","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.neuroimage.2017.10.034","volume":"166","author":"F Alfaro-Almagro","year":"2018","unstructured":"Alfaro-Almagro F et al (2018) Image processing and Quality Control for the first 10,000 brain imaging datasets from UK Biobank. Neuroimage 166:400\u2013424","journal-title":"Neuroimage"},{"key":"316_CR56","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1007\/s11548-021-02420-2","volume":"16","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda F et al (2021) A self-supervised learning strategy for postoperative brain cavity segmentation simulating resections. Int J Comput Assist Radiol Surg 16:1653\u20131661","journal-title":"Int J Comput Assist Radiol Surg"},{"key":"316_CR57","doi-asserted-by":"crossref","unstructured":"P\u00e9rez-Garc\u00eda F et al (2020) Simulation of brain resection for cavity segmentation using self-supervised and semi-supervised learning. In: Medical image computing and computer assisted intervention\u2014MICCAI 2020 115\u2013125. Springer, Cham","DOI":"10.1007\/978-3-030-59716-0_12"},{"key":"316_CR58","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1002\/hbm.24750","volume":"40","author":"F Isensee","year":"2019","unstructured":"Isensee F et al (2019) Automated brain extraction of multisequence MRI using artificial neural networks. Hum Brain Mapp 40:4952\u20134964","journal-title":"Hum Brain Mapp"},{"key":"316_CR59","doi-asserted-by":"publisher","first-page":"106236","DOI":"10.1016\/j.cmpb.2021.106236","volume":"208","author":"F P\u00e9rez-Garc\u00eda","year":"2021","unstructured":"P\u00e9rez-Garc\u00eda F, Sparks R, Ourselin S (2021) TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning. Comput Methods Programs Biomed 208:106236","journal-title":"Comput Methods Programs Biomed"},{"key":"316_CR60","unstructured":"Cardoso MJ et al (2022) MONAI: an open-source framework for deep learning in healthcare. arXiv [cs.LG]"},{"key":"316_CR61","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017). Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). IEEE, pp 2261\u20132269","DOI":"10.1109\/CVPR.2017.243"},{"key":"316_CR62","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1016\/j.neuroimage.2019.06.017","volume":"200","author":"SM Smith","year":"2019","unstructured":"Smith SM, Vidaurre D, Alfaro-Almagro F, Nichols TE, Miller KL (2019) Estimation of brain age delta from brain imaging. Neuroimage 200:528\u2013539","journal-title":"Neuroimage"},{"key":"316_CR63","unstructured":"Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. In: International conference on machine learning. PMLR, pp 3145\u20133153"},{"key":"316_CR64","doi-asserted-by":"publisher","first-page":"1617","DOI":"10.1038\/s41593-019-0471-7","volume":"22","author":"T Kaufmann","year":"2019","unstructured":"Kaufmann T et al (2019) Common brain disorders are associated with heritable patterns of apparent aging of the brain. Nat Neurosci 22:1617\u20131623","journal-title":"Nat Neurosci"},{"key":"316_CR65","doi-asserted-by":"publisher","first-page":"2312","DOI":"10.1093\/brain\/awaa160","volume":"143","author":"VM Bashyam","year":"2020","unstructured":"Bashyam VM et al (2020) MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide. Brain 143:2312\u20132324","journal-title":"Brain"},{"key":"316_CR66","doi-asserted-by":"publisher","first-page":"119504","DOI":"10.1016\/j.neuroimage.2022.119504","volume":"261","author":"SM Hofmann","year":"2022","unstructured":"Hofmann SM et al (2022) Towards the interpretability of deep learning models for multi-modal neuroimaging: finding structural changes of the ageing brain. Neuroimage 261:119504","journal-title":"Neuroimage"},{"key":"316_CR67","doi-asserted-by":"publisher","first-page":"3235","DOI":"10.1002\/hbm.25011","volume":"41","author":"G Levakov","year":"2020","unstructured":"Levakov G, Rosenthal G, Shelef I, Raviv TR, Avidan G (2020) From a deep learning model back to the brain-Identifying regional predictors and their relation to aging. Hum Brain Mapp 41:3235\u20133252","journal-title":"Hum Brain Mapp"},{"key":"316_CR68","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/s40708-024-00244-9","volume":"11","author":"MLN De Bonis","year":"2024","unstructured":"De Bonis MLN et al (2024) Explainable brain age prediction: a comparative evaluation of morphometric and deep learning pipelines. Brain Inform 11:33","journal-title":"Brain Inform"},{"key":"316_CR69","doi-asserted-by":"publisher","first-page":"e70243","DOI":"10.1002\/hbm.70243","volume":"46","author":"NT Siegel","year":"2025","unstructured":"Siegel NT, Kainmueller D, Deniz F, Ritter K, Schulz M-A (2025) Do transformers and CNNs learn different concepts of brain age? Hum Brain Mapp 46:e70243","journal-title":"Hum Brain Mapp"},{"key":"316_CR70","doi-asserted-by":"publisher","first-page":"21213","DOI":"10.1073\/pnas.1902376116","volume":"116","author":"J Wang","year":"2019","unstructured":"Wang J et al (2019) Gray matter age prediction as a biomarker for risk of dementia. Proc Natl Acad Sci U S A 116:21213\u201321218","journal-title":"Proc Natl Acad Sci U S A"},{"key":"316_CR71","doi-asserted-by":"publisher","first-page":"117458","DOI":"10.1016\/j.neuroimage.2020.117458","volume":"225","author":"L Bellantuono","year":"2021","unstructured":"Bellantuono L et al (2021) Predicting brain age with complex networks: From adolescence to adulthood. Neuroimage 225:117458","journal-title":"Neuroimage"},{"key":"316_CR72","doi-asserted-by":"publisher","first-page":"120665","DOI":"10.1016\/j.neuroimage.2024.120665","volume":"296","author":"B Dufumier","year":"2024","unstructured":"Dufumier B et al (2024) Exploring the potential of representation and transfer learning for anatomical neuroimaging: application to psychiatry. Neuroimage 296:120665","journal-title":"Neuroimage"},{"key":"316_CR73","doi-asserted-by":"publisher","first-page":"103600","DOI":"10.1016\/j.ebiom.2021.103600","volume":"72","author":"L Baecker","year":"2021","unstructured":"Baecker L, Garcia-Dias R, Vieira S, Scarpazza C, Mechelli A (2021) Machine learning for brain age prediction: introduction to methods and clinical applications. EBioMedicine 72:103600","journal-title":"EBioMedicine"},{"key":"316_CR74","doi-asserted-by":"publisher","first-page":"101939","DOI":"10.1016\/j.compmedimag.2021.101939","volume":"91","author":"P Besson","year":"2021","unstructured":"Besson P, Parrish T, Katsaggelos AK, Bandt SK (2021) Geometric deep learning on brain shape predicts sex and age. Comput Med Imaging Graph 91:101939","journal-title":"Comput Med Imaging Graph"},{"key":"316_CR75","doi-asserted-by":"publisher","first-page":"imag_a_00497","DOI":"10.1162\/imag_a_00497","volume":"3","author":"SM Hofmann","year":"2025","unstructured":"Hofmann SM et al (2025) The utility of explainable AI for MRI analysis: Relating model predictions to neuroimaging features of the aging brain. Imaging Neurosci (Camb) 3:imag_a_00497","journal-title":"Imaging Neurosci (Camb)"},{"key":"316_CR76","doi-asserted-by":"publisher","first-page":"674055","DOI":"10.3389\/fnins.2021.674055","volume":"15","author":"A Lombardi","year":"2021","unstructured":"Lombardi A et al (2021) Explainable deep learning for personalized age prediction with brain morphology. Front Neurosci 15:674055","journal-title":"Front Neurosci"},{"key":"316_CR77","doi-asserted-by":"publisher","first-page":"1385","DOI":"10.1038\/mp.2017.62","volume":"23","author":"JH Cole","year":"2018","unstructured":"Cole JH et al (2018) Brain age predicts mortality. Mol Psychiatry 23:1385\u20131392","journal-title":"Mol Psychiatry"},{"key":"316_CR78","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3389\/fnagi.2014.00094","volume":"6","author":"K Franke","year":"2014","unstructured":"Franke K, Ristow M, Gaser C, Alzheimer\u2019s Disease Neuroimaging Initiative (2014) Gender-specific impact of personal health parameters on individual brain aging in cognitively unimpaired elderly subjects. Front Aging Neurosci 6:94","journal-title":"Front Aging Neurosci"},{"key":"316_CR79","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1007\/s00429-020-02184-6","volume":"226","author":"N Bittner","year":"2021","unstructured":"Bittner N et al (2021) When your brain looks older than expected: combined lifestyle risk and BrainAGE. Brain Struct Funct 226:621\u2013645","journal-title":"Brain Struct Funct"},{"key":"316_CR80","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.pscychresns.2017.05.006","volume":"266","author":"I Nenadi\u0107","year":"2017","unstructured":"Nenadi\u0107 I, Dietzek M, Langbein K, Sauer H, Gaser C (2017) BrainAGE score indicates accelerated brain aging in schizophrenia, but not bipolar disorder. Psychiatry Res Neuroimaging 266:86\u201389","journal-title":"Psychiatry Res Neuroimaging"},{"key":"316_CR81","volume-title":"Advances in neural information processing systems","author":"S Hooker","year":"2019","unstructured":"Hooker S, Erhan D, Kindermans PJ, Kim B (2019) A benchmark for interpretability methods in deep neural networks. In: Wallach H et al (eds) Advances in neural information processing systems, vol 32. Neural Information Processing Systems (NIPS), La Jolla"},{"key":"316_CR82","volume-title":"Advances in neural information processing systems","author":"J Adebayo","year":"2018","unstructured":"Adebayo J et al (2018) Sanity checks for saliency maps. In: Bengio S et al (eds) Advances in neural information processing systems, vol 31. Neural Information Processing Systems (NIPS), La Jolla"},{"key":"316_CR83","first-page":"3681","volume":"33","author":"A Ghorbani","year":"2019","unstructured":"Ghorbani A, Abid A, Zou J (2019) Interpretation of neural networks is fragile. Proc Conf AAAI Artif Intell 33:3681\u20133688","journal-title":"Proc Conf AAAI Artif Intell"},{"key":"316_CR84","unstructured":"Kindermans P-J et al (2019) The (un)reliability of saliency methods. In: Explainable AI: interpreting, explaining and visualizing deep learning. Springer, Cham, pp 267\u2013280"},{"key":"316_CR85","unstructured":"Dombrowski A-K et al (2019) Explanations can be manipulated and geometry is to blame. In: Advances in neural information processing systems, vol 32"}],"container-title":["Brain Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40708-026-00316-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-026-00316-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40708-026-00316-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:02:15Z","timestamp":1783436535000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40708-026-00316-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,6]]},"references-count":85,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["316"],"URL":"https:\/\/doi.org\/10.1186\/s40708-026-00316-y","relation":{},"ISSN":["2198-4018","2198-4026"],"issn-type":[{"value":"2198-4018","type":"print"},{"value":"2198-4026","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,6]]},"assertion":[{"value":"5 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The overall analysis was approved by the Ethics board at University Hospital Carl Gustav Carus, Dresden, Germany. This study adhered to the tenets of the Declaration of Helsinki. This study uses only anonymised secondary data from publicly available neuroimaging datasets. No new data were collected specifically for this study. All datasets were obtained in accordance with the respective data usage agreements and under appropriate ethical approvals. All scans were acquired for studies approved by local institutional review boards, research ethics committees, or human investigation committees. UK Biobank received ethical approval from the North West Multi-centre Research Ethics Committee (REC reference 11\/NW\/0382), and all participants provided informed consent. PPMI also ensures that all participants provide informed consent in accordance with IRB-approved protocols outlined in the PPMI Operations Manual and the PPMI clinical protocol that can be found at\n                      \n                      .","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"JNK holds shares in StratifAI, Synagen, Spira Labs, Saterra and Tremont AI, is Co-PI on institutional research grants from GSK and AstraZeneca, and declares honoraria or consulting fees from AstraZeneca, Bayer, Bioptimus, Daiichi Sankyo, Eisai, Janssen, Merck, MSD, Novartis, BMS, Roche, and Pfizer. DT received honoraria for lectures by Bayer, GE, Roche, AstraZeneca, and Philips and holds shares in StratifAI GmbH, Germany and in Synagen GmbH, Germany. HHK received speaker and consulting fees from Bayer, Biogen, Sanofi, Novartis, Siemens, and Teva; served on advisory boards for Biogen, Ixico, Sanofi, and Novartis and received research grants from Novartis and ELA.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"31"}}