{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T16:03:39Z","timestamp":1791734619276,"version":"4.3.4"},"reference-count":62,"publisher":"MIT Press","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":48,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004895","name":"European Social Fund","doi-asserted-by":"publisher","award":["713-241202"],"award-info":[{"award-number":["713-241202"]}],"id":[{"id":"10.13039\/501100004895","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","award":["14505\/2470"],"award-info":[{"award-number":["14505\/2470"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Free State Saxony\u2019s excellence initiative","award":["14575\/2470"],"award-info":[{"award-number":["14575\/2470"]}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","award":["464596826"],"award-info":[{"award-number":["464596826"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"DFG","doi-asserted-by":"publisher","award":["209933838"],"award-info":[{"award-number":["209933838"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BMBF","award":["01IS22065"],"award-info":[{"award-number":["01IS22065"]}]},{"name":"BMBF","award":["01IS22065"],"award-info":[{"award-number":["01IS22065"]}]},{"name":"Max Planck Society and the Fraunhofer Gesellschaft","award":["NEUROHUM"],"award-info":[{"award-number":["NEUROHUM"]}]},{"name":"BMBF","award":["01IS14013A-E, 01GQ1115, 01GQ0850, 01IS18025A, 031L0207D, 01IS18037A, 13GW0206, 13GW0488, 16SV9156"],"award-info":[{"award-number":["01IS14013A-E, 01GQ1115, 01GQ0850, 01IS18025A, 031L0207D, 01IS18037A, 13GW0206, 13GW0488, 16SV9156"]}]},{"DOI":"10.13039\/501100014188","name":"MSIT","doi-asserted-by":"crossref","award":["No. 2019-0-00079, No. 2022-0-00984"],"award-info":[{"award-number":["No. 2019-0-00079, No. 2022-0-00984"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,2,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Deep learning models highly accurately predict brain age from MRI but their explanatory capacity is limited. Explainable artificial intelligence (XAI) methods can identify relevant voxels contributing to model estimates, yet they do not reveal which biological features these voxels represent. In this study, we closed this gap by relating voxel-based contributions to brain-age estimates, extracted with XAI, to human-interpretable structural features of the aging brain. To this end, we associated participant-level XAI-based relevance maps extracted from two ensembles of 3D-convolutional neural networks (3D-CNNs) that were trained on T1-weighted and fluid-attenuated inversion recovery images of 1855 participants (age range 18\u201382 years), with regional cortical and subcortical gray matter volume and thickness, perivascular spaces (PVS), and water diffusion-based fractional anisotropy of major white matter tracts. We found that all neuroimaging markers of brain aging, except for PVS, were highly correlated with the XAI-based relevance maps. Overall, the strongest correlation was found between ventricular volume and relevance (r = 0.69), and by feature, temporal-parietal cortical thickness and volume, cerebellar gray matter volume, and frontal-occipital white matter tracts showed the strongest correlations with XAI-based relevance. Our ensembles of 3D-CNNs took into account a plethora of known aging processes in the brain to perform age prediction. Some age-associated features like PVS were not consistently considered by the models, and the cerebellum was more important than expected. Taken together, we highlight the ability of end-to-end deep learning models combined with XAI to reveal biologically relevant, multi-feature relationships in the brain.<\/jats:p>","DOI":"10.1162\/imag_a_00497","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T13:31:52Z","timestamp":1739885512000},"update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":9,"title":["The utility of explainable AI for MRI analysis: Relating model predictions to neuroimaging features of the aging brain"],"prefix":"10.1162","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0958-501X","authenticated-orcid":false,"given":"Simon M.","family":"Hofmann","sequence":"first","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Neural Data Science and Statistical Computing, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Department of Electrical Engineering and Computer Science, Technical University Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8566-6009","authenticated-orcid":false,"given":"Ole","family":"Goltermann","sequence":"additional","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Max Planck School of Cognition, Leipzig, Germany"},{"name":"Institute of Systems Neuroscience, University Medical Center Hamburg-Eppendorf, Hamburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4003-9121","authenticated-orcid":false,"given":"Nico","family":"Scherf","sequence":"additional","affiliation":[{"name":"Neural Data Science and Statistical Computing, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden\/Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3861-7685","authenticated-orcid":false,"given":"Klaus-Robert","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Science, Technical University Berlin, Berlin, Germany"},{"name":"Max Planck School of Cognition, Leipzig, Germany"},{"name":"BIFOLD - Berlin Institute for the Foundations of Learning and Data, Berlin, Germany"},{"name":"Department of Artificial Intelligence, Korea University, Seoul, Korea (the Republic of)"},{"name":"Max Planck Institute for Informatics, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0424-9933","authenticated-orcid":false,"given":"Markus","family":"L\u00f6ffler","sequence":"additional","affiliation":[{"name":"Institute for Medical Informatics, Statistics and Epidemiology; University of Leipzig, Leipzig, Germany"},{"name":"Leipzig Research Centre for Civilization Diseases (LIFE), Leipzig, Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2604-2404","authenticated-orcid":false,"given":"Arno","family":"Villringer","sequence":"additional","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Max Planck School of Cognition, Leipzig, Germany"},{"name":"Clinic for Cognitive Neurology, University Hospital Leipzig, Leipzig, Germany"},{"name":"Center for Stroke Research, Charit\u00e9 \u2013 Universit\u00e4tsmedizin Berlin, Berlin, Germany"},{"name":"Berlin School of Mind and Brain, Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4442-5778","authenticated-orcid":false,"given":"Michael","family":"Gaebler","sequence":"additional","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Berlin School of Mind and Brain, Humboldt-Universit\u00e4t zu Berlin, Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9054-6688","authenticated-orcid":false,"given":"A. Veronica","family":"Witte","sequence":"additional","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Max Planck School of Cognition, Leipzig, Germany"},{"name":"Clinic for Cognitive Neurology, University Hospital Leipzig, Leipzig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5401-852X","authenticated-orcid":false,"given":"Frauke","family":"Beyer","sequence":"additional","affiliation":[{"name":"Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany"},{"name":"Clinic for Cognitive Neurology, University Hospital Leipzig, Leipzig, Germany"},{"name":"Bordeaux Population Health Center, University of Bordeaux, Bordeaux, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"issue":"9","key":"2025022719564235900_imag_a_00497-b1","doi-asserted-by":"crossref","first-page":"1006","DOI":"10.1038\/s42256-023-00711-8","article-title":"From attribution maps to human-understandable explanations through concept relevance propagation","volume":"5","author":"Achtibat","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"2025022719564235900_imag_a_00497-b2","unstructured":"Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2020). Sanity checks for saliency maps. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montr\u00e9al, Canada. http:\/\/arxiv.org\/abs\/1810.03292"},{"key":"2025022719564235900_imag_a_00497-b3","unstructured":"Alber, M., Lapuschkin, S., Seegerer, P., H\u00e4gele, M., Sch\u00fctt, K. T., Montavon, G., Samek, W., M\u00fcller, K.-R., D\u00e4hne, S., & Kindermans, P.-J. (2019). iNNvestigate Neural Networks!Journal of Machine Learning Research, 20(93), 1\u20138. http:\/\/jmlr.org\/papers\/v20\/18-540.html"},{"issue":"1","key":"2025022719564235900_imag_a_00497-b4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/j.media.2007.06.004","article-title":"Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain","volume":"12","author":"Avants","year":"2008","journal-title":"Medical Image Analysis"},{"key":"2025022719564235900_imag_a_00497-b5","doi-asserted-by":"crossref","first-page":"252","DOI":"10.3389\/fnagi.2018.00252","article-title":"Biological brain age prediction using cortical thickness data: A large scale cohort study","volume":"10","author":"Aycheh","year":"2018","journal-title":"Frontiers in Aging Neuroscience"},{"issue":"7","key":"2025022719564235900_imag_a_00497-b6","doi-asserted-by":"crossref","first-page":"e0130140","DOI":"10.1371\/journal.pone.0130140","article-title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","volume":"10","author":"Bach","year":"2015","journal-title":"PLoS One"},{"key":"2025022719564235900_imag_a_00497-b7","doi-asserted-by":"crossref","unstructured":"Bacon, F.\n           (1620). Novum organum. https:\/\/doi.org\/10.1093\/oseo\/instance.00007242","DOI":"10.1093\/oseo\/instance.00007242"},{"key":"2025022719564235900_imag_a_00497-b8","doi-asserted-by":"crossref","first-page":"118036","DOI":"10.1016\/j.neuroimage.2021.118036","article-title":"Individual variation underlying brain age estimates in typical development","volume":"235","author":"Ball","year":"2021","journal-title":"NeuroImage"},{"issue":"7","key":"2025022719564235900_imag_a_00497-b9","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1177\/0271678X20972856","article-title":"Body mass index, time of day and genetics affect perivascular spaces in the white matter","volume":"41","author":"Barisano","year":"2021","journal-title":"Journal of Cerebral Blood Flow & Metabolism"},{"issue":"7","key":"2025022719564235900_imag_a_00497-b10","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 14 468 individuals worldwide","volume":"143","author":"Bashyam","year":"2020","journal-title":"Brain"},{"issue":"2","key":"2025022719564235900_imag_a_00497-b11","doi-asserted-by":"crossref","first-page":"560","DOI":"10.1016\/j.jmr.2011.09.022","article-title":"Microstructural and physiological features of tissues elucidated by quantitative-diffusion-tensor MRI","volume":"213","author":"Basser","year":"2011","journal-title":"Journal of Magnetic Resonance"},{"key":"2025022719564235900_imag_a_00497-b12","doi-asserted-by":"crossref","first-page":"104639","DOI":"10.1016\/j.neubiorev.2022.104639","article-title":"Don\u2019t forget the little brain: A framework for incorporating the cerebellum into the understanding of cognitive aging","volume":"137","author":"Bernard","year":"2022","journal-title":"Neuroscience & Biobehavioral Reviews"},{"key":"2025022719564235900_imag_a_00497-b13","doi-asserted-by":"crossref","DOI":"10.3389\/fnagi.2019.00194","article-title":"Layer-wise relevance propagation for explaining deep neural network decisions in MRI-based Alzheimer\\textquotesingles disease classification","volume":"11","author":"B\u00f6hle","year":"2019","journal-title":"Frontiers in Aging Neuroscience"},{"key":"2025022719564235900_imag_a_00497-b14","doi-asserted-by":"crossref","first-page":"641600","DOI":"10.3389\/fninf.2021.641600","article-title":"3D segmentation of perivascular spaces on T1-weighted 3 Tesla MR images with a convolutional autoencoder and a U-shaped neural network","volume":"15","author":"Boutinaud","year":"2021","journal-title":"Frontiers in Neuroinformatics"},{"key":"2025022719564235900_imag_a_00497-b15","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neuroimage.2016.11.068","article-title":"The role of myelination in measures of white matter integrity: Combination of diffusion tensor imaging and two-photon microscopy of CLARITY intact brains","volume":"147","author":"Chang","year":"2017","journal-title":"NeuroImage"},{"key":"2025022719564235900_imag_a_00497-b16","unstructured":"Chollet, F.\n           (2015). Keras. https:\/\/keras.io\/"},{"key":"2025022719564235900_imag_a_00497-b17","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"},{"issue":"6","key":"2025022719564235900_imag_a_00497-b18","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1038\/s41380-020-00975-1","article-title":"Three major dimensions of human brain cortical ageing in relation to cognitive decline across the eighth decade of life","volume":"26","author":"Cox","year":"2021","journal-title":"Molecular Psychiatry"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b19","doi-asserted-by":"crossref","first-page":"302","DOI":"10.5853\/jos.2017.02922","article-title":"Cerebral small vessel disease: A review focusing on pathophysiology, biomarkers, and machine learning strategies","volume":"20","author":"Cuadrado-Godia","year":"2018","journal-title":"Journal of Stroke"},{"issue":"1","key":"2025022719564235900_imag_a_00497-b20","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1136\/jnnp.70.1.9","article-title":"Prevalence of cerebral white matter lesions in elderly people: A population based magnetic resonance imaging study. The Rotterdam Scan Study","volume":"70","author":"De Leeuw","year":"2001","journal-title":"Journal of Neurology, Neurosurgery & Psychiatry"},{"key":"2025022719564235900_imag_a_00497-b21","doi-asserted-by":"crossref","first-page":"117401","DOI":"10.1016\/j.neuroimage.2020.117401","article-title":"Learning patterns of the ageing brain in MRI using deep convolutional networks","volume":"224","author":"Dinsdale","year":"2021","journal-title":"NeuroImage"},{"issue":"7","key":"2025022719564235900_imag_a_00497-b22","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/S1474-4422(23)00131-X","article-title":"Neuroimaging standards for research into small vessel disease\u2014Advances since 2013","volume":"22","author":"Duering","year":"2023","journal-title":"The Lancet Neurology"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b23","doi-asserted-by":"crossref","first-page":"1149","DOI":"10.1109\/TPAMI.2020.3020738","article-title":"Building and interpreting deep similarity models","volume":"44","author":"Eberle","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025022719564235900_imag_a_00497-b24","doi-asserted-by":"crossref","first-page":"102003","DOI":"10.1016\/j.nicl.2019.102003","article-title":"Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation","volume":"24","author":"Eitel","year":"2019","journal-title":"NeuroImage: Clinical"},{"key":"2025022719564235900_imag_a_00497-b25","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.neurobiolaging.2020.02.009","article-title":"Estimating brain age based on a uniform healthy population with deep learning and structural magnetic resonance imaging","volume":"91","author":"Feng","year":"2020","journal-title":"Neurobiology of Aging"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b26","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/S0896-6273(02)00569-X","article-title":"Whole brain segmentation: Automated labeling of neuroanatomical structures in the human brain","volume":"33","author":"Fischl","year":"2002","journal-title":"Neuron"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b27","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1515\/REVNEURO.2010.21.3.187","article-title":"Structural brain changes in aging: Courses, causes and cognitive consequences","volume":"21","author":"Fjell","year":"2010","journal-title":"Reviews in the Neurosciences"},{"issue":"9","key":"2025022719564235900_imag_a_00497-b28","doi-asserted-by":"crossref","first-page":"2001","DOI":"10.1093\/cercor\/bhn232","article-title":"High consistency of regional cortical thinning in aging across multiple samples","volume":"19","author":"Fjell","year":"2009","journal-title":"Cerebral Cortex"},{"issue":"10","key":"2025022719564235900_imag_a_00497-b29","doi-asserted-by":"crossref","first-page":"2239","DOI":"10.1016\/j.neurobiolaging.2013.04.006","article-title":"Critical ages in the life course of the adult brain: Nonlinear subcortical aging","volume":"34","author":"Fjell","year":"2013","journal-title":"Neurobiology of Aging"},{"issue":"4","key":"2025022719564235900_imag_a_00497-b30","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1177\/1747493019830321","article-title":"Perivascular spaces and their associations with risk factors, clinical disorders and neuroimaging features: A systematic review and meta-analysis","volume":"14","author":"Francis","year":"2019","journal-title":"International Journal of Stroke"},{"issue":"11","key":"2025022719564235900_imag_a_00497-b31","doi-asserted-by":"crossref","first-page":"e745","DOI":"10.1016\/S2589-7500(21)00208-9","article-title":"The false hope of current approaches to explainable artificial intelligence in health care","volume":"3","author":"Ghassemi","year":"2021","journal-title":"The Lancet Digital Health"},{"key":"2025022719564235900_imag_a_00497-b32","doi-asserted-by":"crossref","first-page":"119504","DOI":"10.1016\/j.neuroimage.2022.119504","article-title":"Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain","volume":"261","author":"Hofmann","year":"2022","journal-title":"NeuroImage"},{"key":"2025022719564235900_imag_a_00497-b33","doi-asserted-by":"crossref","first-page":"624732","DOI":"10.3389\/fnagi.2021.624732","article-title":"Factors associated with the dilation of perivascular space in healthy elderly subjects","volume":"13","author":"Huang","year":"2021","journal-title":"Frontiers in Aging Neuroscience"},{"issue":"2","key":"2025022719564235900_imag_a_00497-b34","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1016\/j.neuroimage.2011.09.015","article-title":"Fsl","volume":"62","author":"Jenkinson","year":"2012","journal-title":"Neuroimage"},{"key":"2025022719564235900_imag_a_00497-b35","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1016\/j.neuroimage.2019.01.014","article-title":"Qoala-T: A supervised-learning tool for quality control of FreeSurfer segmented MRI data","volume":"189","author":"Klapwijk","year":"2019","journal-title":"NeuroImage"},{"key":"2025022719564235900_imag_a_00497-b36","doi-asserted-by":"crossref","first-page":"171","DOI":"10.3389\/fnins.2012.00171","article-title":"101 labeled brain images and a consistent human cortical labeling protocol","volume":"6","author":"Klein","year":"2012","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2025022719564235900_imag_a_00497-b37","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1002\/mrm.1910200210","article-title":"Cholesterol of myelin is the determinant of gray-white contrast in MRI of brain","volume":"20","author":"Koenig","year":"1991","journal-title":"Magnetic Resonance in Medicine"},{"key":"2025022719564235900_imag_a_00497-b38","volume-title":"Improving your statistical inferences","author":"Lakens","year":"2022"},{"issue":"1","key":"2025022719564235900_imag_a_00497-b39","doi-asserted-by":"crossref","first-page":"1096","DOI":"10.1038\/s41467-019-08987-4","article-title":"Unmasking Clever Hans predictors and assessing what machines really learn","volume":"10","author":"Lapuschkin","year":"2019","journal-title":"Nature Communications"},{"key":"2025022719564235900_imag_a_00497-b40","doi-asserted-by":"crossref","DOI":"10.1002\/hbm.25011","article-title":"From a deep learning model back to the brain\u2014Identifying regional predictors and their relation to aging","author":"Levakov","year":"2020","journal-title":"Human Brain Mapping"},{"issue":"12","key":"2025022719564235900_imag_a_00497-b41","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1177\/0963689718795148","article-title":"Cerebral small vessel disease","volume":"27","author":"Li","year":"2018","journal-title":"Cell Transplantation"},{"key":"2025022719564235900_imag_a_00497-b42","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1186\/s12889-015-1983-z","article-title":"The LIFE-Adult-Study: Objectives and design of a population-based cohort study with 10,000 deeply phenotyped adults in Germany","volume":"15","author":"Loeffler","year":"2015","journal-title":"BMC Public Health"},{"issue":"6","key":"2025022719564235900_imag_a_00497-b43","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/S0895-6111(01)00008-8","article-title":"LIPSIA\u2014A new software system for the evaluation of functional magnetic resonance images of the human brain","volume":"25","author":"Lohmann","year":"2001","journal-title":"Computerized Medical Imaging and Graphics: The Official Journal of the Computerized Medical Imaging Society"},{"key":"2025022719564235900_imag_a_00497-b44","doi-asserted-by":"crossref","first-page":"120009","DOI":"10.1016\/j.neuroimage.2023.120009","article-title":"Brain perivascular space imaging across the human lifespan","volume":"271","author":"Lynch","year":"2023","journal-title":"NeuroImage"},{"issue":"2","key":"2025022719564235900_imag_a_00497-b45","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1016\/j.neurobiolaging.2014.07.048","article-title":"White matter hyperintensities and normal-appearing white matter integrity in the aging brain","volume":"36","author":"Maniega","year":"2015","journal-title":"Neurobiology of Aging"},{"key":"2025022719564235900_imag_a_00497-b46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2017.10.011","article-title":"Methods for interpreting and understanding deep neural networks","volume":"73","author":"Montavon","year":"2018","journal-title":"Digital Signal Processing"},{"key":"2025022719564235900_imag_a_00497-b47","volume-title":"MRI atlas of human white matter","author":"Mori","year":"2005"},{"key":"2025022719564235900_imag_a_00497-b48","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":"Medical Image Analysis"},{"key":"2025022719564235900_imag_a_00497-b50","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1613\/jair.1.13200","article-title":"Explainable deep learning: A field guide for the uninitiated","volume":"73","author":"Ras","year":"2022","journal-title":"Journal of Artificial Intelligence Research"},{"key":"2025022719564235900_imag_a_00497-b51","article-title":"U-Net: Convolutional networks for biomedical image segmentation (Version 1)","author":"Ronneberger","year":"2015","journal-title":"arXiv"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b52","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1109\/JPROC.2021.3060483","article-title":"Explaining deep neural networks and beyond: A review of methods and applications","volume":"109","author":"Samek","year":"2021","journal-title":"Proceedings of the IEEE"},{"issue":"6","key":"2025022719564235900_imag_a_00497-b53","doi-asserted-by":"crossref","first-page":"2111","DOI":"10.1007\/s00429-022-02503-z","article-title":"Aging and white matter microstructure and macrostructure: A longitudinal multi-site diffusion MRI study of 1218 participants","volume":"227","author":"Schilling","year":"2022","journal-title":"Brain Structure and Function"},{"issue":"11","key":"2025022719564235900_imag_a_00497-b54","doi-asserted-by":"crossref","first-page":"7581","DOI":"10.1109\/TPAMI.2021.3115452","article-title":"Higher-order explanations of graph neural networks via relevant walks","volume":"44","author":"Schnake","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"2025022719564235900_imag_a_00497-b55","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1093\/brain\/114.2.761","article-title":"Periventricular lesions in the white matter on magnetic resonance imaging in the elderly: A morphometric correlation with arteriolosclerosis and dilated perivascular spaces","volume":"114","author":"Swieten","year":"1991","journal-title":"Brain"},{"key":"2025022719564235900_imag_a_00497-b56","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.3389\/fnins.2019.01321","article-title":"Analyzing neuroimaging data through recurrent deep learning models","volume":"13","author":"Thomas","year":"2019","journal-title":"Frontiers in Neuroscience"},{"key":"2025022719564235900_imag_a_00497-b57","article-title":"Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification (arXiv:2404.10433)","author":"Tinauer","year":"2024","journal-title":"arXiv"},{"issue":"1","key":"2025022719564235900_imag_a_00497-b58","doi-asserted-by":"crossref","first-page":"20254","DOI":"10.1038\/s41598-022-24541-7","article-title":"Interpretable brain disease classification and relevance-guided deep learning","volume":"12","author":"Tinauer","year":"2022","journal-title":"Scientific Reports"},{"key":"2025022719564235900_imag_a_00497-b59","doi-asserted-by":"crossref","first-page":"116137","DOI":"10.1016\/j.neuroimage.2019.116137","article-title":"MRtrix3: A fast, flexible and open software framework for medical image processing and visualisation","volume":"202","author":"Tournier","year":"2019","journal-title":"NeuroImage"},{"key":"2025022719564235900_imag_a_00497-b60","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1016\/j.neubiorev.2017.01.002","article-title":"Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications","volume":"74","author":"Vieira","year":"2017","journal-title":"Neuroscience & Biobehavioral Reviews"},{"issue":"3","key":"2025022719564235900_imag_a_00497-b61","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1038\/s41582-020-0312-z","article-title":"Perivascular spaces in the brain: Anatomy, physiology and pathology","volume":"16","author":"Wardlaw","year":"2020","journal-title":"Nature Reviews Neurology"},{"issue":"6","key":"2025022719564235900_imag_a_00497-b62","doi-asserted-by":"crossref","first-page":"e001140","DOI":"10.1161\/JAHA.114.001140","article-title":"What are white matter hyperintensities made of?","volume":"4","author":"Wardlaw","year":"2015","journal-title":"Journal of the American Heart Association"},{"key":"2025022719564235900_imag_a_00497-b63","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jocs.2018.07.003","article-title":"Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLU","volume":"28","author":"Zhang","year":"2018","journal-title":"Journal of Computational Science"}],"container-title":["Imaging Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/imag_a_00497\/2503311\/imag_a_00497.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/imag\/article-pdf\/doi\/10.1162\/imag_a_00497\/2503311\/imag_a_00497.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T19:57:23Z","timestamp":1740686243000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/imag\/article\/doi\/10.1162\/imag_a_00497\/127951\/The-utility-of-explainable-AI-for-MRI-analysis"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1162\/imag_a_00497","relation":{},"ISSN":["2837-6056"],"issn-type":[{"value":"2837-6056","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025]]},"published":{"date-parts":[[2025]]},"article-number":"imag_a_00497"}}