{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:36:17Z","timestamp":1792690577651,"version":"4.5.0"},"reference-count":102,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T00:00:00Z","timestamp":1749081600000},"content-version":"vor","delay-in-days":4,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176181"],"award-info":[{"award-number":["62176181"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82072099"],"award-info":[{"award-number":["82072099"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Human Brain Mapping"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    Deep learning frameworks utilizing convolutional neural networks (CNNs) have frequently been used for brain age prediction and have achieved outstanding performance. Nevertheless, deep learning remains a black box as it is hard to interpret which brain parts contribute significantly to the predictions. To tackle this challenge, we first trained a lightweight, fully CNN model for brain age estimation on a large sample data set (\n                    <jats:italic>N<\/jats:italic>\n                    \u2009=\u20093054, age range\u2009=\u2009[8,80\u2009years]) and tested it on an independent data set (\n                    <jats:italic>N<\/jats:italic>\n                    \u2009=\u2009555, age range\u2009=\u2009[8,80\u2009years]). We then developed an interpretable scheme combining network occlusion sensitivity analysis (NOSA) with a fine\u2010grained human brain atlas to uncover the learned invariance of the model. Our findings show that the dorsolateral, dorsomedial frontal cortex, anterior cingulate cortex, and thalamus had the highest contributions to age prediction across the lifespan. More interestingly, we observed that different regions showed divergent patterns in their predictions for specific age groups and that the bilateral hemispheres contributed differently to the predictions. Regions in the frontal lobe were essential predictors in both the developmental and aging stages, with the thalamus remaining relatively stable and saliently correlated with other regional changes throughout the lifespan. The lateral and medial temporal brain regions gradually became involved during the aging phase. At the network level, the frontoparietal and the default mode networks show an inverted U\u2010shape contribution from the developmental to the aging stages. The framework could identify regional contributions to the brain age prediction model, which could help increase the model interpretability when serving as an aging biomarker.\n                  <\/jats:p>","DOI":"10.1002\/hbm.70239","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T07:00:41Z","timestamp":1749106841000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Network Occlusion Sensitivity Analysis Identifies Regional Contributions to Brain Age Prediction"],"prefix":"10.1002","volume":"46","author":[{"given":"Lingfei","family":"He","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University  Tianjin China"},{"name":"Brainnetome Center  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4063-6638","authenticated-orcid":false,"given":"Siyu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University  Tianjin China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University  Tianjin China"},{"name":"Brainnetome Center  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaping","family":"Wang","sequence":"additional","affiliation":[{"name":"Brainnetome Center  Beijing China"},{"name":"National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences  Beijing China"},{"name":"Sino\u2010Danish Center  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingcheng","family":"Fan","sequence":"additional","affiliation":[{"name":"Chinese Institute for Brain Research  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congying","family":"Chu","sequence":"additional","affiliation":[{"name":"Brainnetome Center  Beijing China"},{"name":"National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4813-621X","authenticated-orcid":false,"given":"Lingzhong","family":"Fan","sequence":"additional","affiliation":[{"name":"Brainnetome Center  Beijing China"},{"name":"National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences  Beijing China"},{"name":"University of Chinese Academy of Sciences  Beijing China"},{"name":"CAS Center for Excellence in Brain Science and Intelligence Technology Institute of Automation, Chinese Academy of Sciences  Beijing China"},{"name":"University of Health and Rehabilitation Sciences  Qingdao China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4289-647X","authenticated-orcid":false,"given":"Junhai","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin Key Laboratory of Cognitive Computing and Application Tianjin University  Tianjin China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,6,5]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20655-6"},{"key":"e_1_2_8_3_1","unstructured":"Adebayo J. J.Gilmer M.Muelly I.Goodfellow M.Hardt andB.Kim.2018.\u201cSanity Checks for Saliency Maps.\u201darXiv preprint arXiv:1810.03292."},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200267"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/nn1075"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40478-022-01494-6"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.03.009"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2017.04.006"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2017.10.001"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/ana.24367"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.07.059"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/mp.2017.62"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/schbul\/16.3.433"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40708-024-00244-9"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00338-7"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-019-0626-7"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhw157"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2020.02.009"},{"key":"e_1_2_8_20_1","first-page":"568","volume-title":"Medical Image Computing and Computer\u2010Assisted Intervention","author":"Feng X.","year":"2017"},{"key":"e_1_2_8_21_1","volume-title":"TorchCAM: Class Activation Explorer","author":"Fernandez F.\u2010G.","year":"2020"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhn232"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2013.04.006"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1038\/nn1543"},{"key":"e_1_2_8_25_1","first-page":"1327","article-title":"Age\u2010Related Total Gray Matter and White Matter Changes in Normal Adult Brain. Part I: Volumetric MR Imaging Analysis","volume":"23","author":"Ge Y.","year":"2002","journal-title":"American Journal of Neuroradiology"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3550-16.2017"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0786"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.20115"},{"key":"e_1_2_8_30_1","first-page":"119","volume-title":"Asian Conference on Computer Vision","author":"Gu J.","year":"2018"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/13854040590967577"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3108910"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abcd17"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0067-17.2017"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3563691"},{"key":"e_1_2_8_37_1","volume-title":"Neurobiology of Attention","author":"Itti L.","year":"2005"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2022.791222"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2019.01346"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102684"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13163-9"},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2007.05.019"},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0471-7"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3479-08.2008"},{"key":"e_1_2_8_46_1","article-title":"Captum: A Unified and Generic Model Interpretability Library for PyTorch","author":"Kokhlikyan N.","year":"2020","journal-title":"arXiv preprint arXiv:2009.07896"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2018.00028"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"e_1_2_8_49_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.25011"},{"key":"e_1_2_8_50_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.011"},{"key":"e_1_2_8_51_1","first-page":"4768\u2013","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_52_1","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/11.4.335"},{"key":"e_1_2_8_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-823493-8.00004-3"},{"key":"e_1_2_8_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/0028-3932(68)90019-5"},{"key":"e_1_2_8_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0028-3932(03)00017-4"},{"key":"e_1_2_8_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24995"},{"key":"e_1_2_8_57_1","first-page":"15\u2013","article-title":"Successful Brain Aging: Plasticity, Environmental Enrichment, and Lifestyle","volume":"15","author":"Mora F.","year":"2022","journal-title":"Dialogues in Clinical Neuroscience"},{"key":"e_1_2_8_58_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.25805"},{"key":"e_1_2_8_59_1","first-page":"107","volume-title":"Medical Image Analysis","author":"Niessen W. J.","year":"2016"},{"key":"e_1_2_8_60_1","first-page":"1","author":"Nigri E.","year":"2020","journal-title":"International Joint Conference on Neural Networks"},{"key":"e_1_2_8_61_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2012.00152"},{"key":"e_1_2_8_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102571"},{"key":"e_1_2_8_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2015.06.008"},{"key":"e_1_2_8_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.12.044"},{"key":"e_1_2_8_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-017-9346-9"},{"key":"e_1_2_8_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101871"},{"key":"e_1_2_8_67_1","doi-asserted-by":"publisher","DOI":"10.1001\/archneur.1994.00540210046012"},{"key":"e_1_2_8_68_1","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2009.21184"},{"key":"e_1_2_8_69_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsbl.2004.0200"},{"key":"e_1_2_8_70_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2015.03.056"},{"key":"e_1_2_8_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bandl.2013.07.006"},{"key":"e_1_2_8_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_2_8_73_1","first-page":"483","article-title":"Alteration of Normal Regional Brain FDG Uptake in Normal Aging","volume":"58","author":"Shamchi S. P.","year":"2017","journal-title":"Society of Nuclear Medicine"},{"key":"e_1_2_8_74_1","volume-title":"Exploring the Thalamus and Its Role in Cortical Function","author":"Sherman S. M.","year":"2006"},{"key":"e_1_2_8_75_1","first-page":"3145","volume-title":"International Conference on Machine Learning","author":"Shrikumar A.","year":"2017"},{"key":"e_1_2_8_76_1","first-page":"46958\u2013","article-title":"Explainable Brain Age Prediction Using Covariance Neural Networks","volume":"36","author":"Sihag S.","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_77_1","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1178"},{"key":"e_1_2_8_78_1","unstructured":"Simonyan K. andA.Zisserman.2014.\u201cVery Deep Convolutional Networks for Large\u2010Scale Image Recognition.\u201darXiv preprint arXiv:1409.1556."},{"key":"e_1_2_8_79_1","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6060052"},{"key":"e_1_2_8_80_1","unstructured":"Smilkov D. N.Thorat B.Kim F.Vi\u00e9gas andM.Wattenberg.2017.\u201cSmoothgrad: Removing Noise by Adding Noise.\u201darXiv preprint arXiv:1706.03825."},{"key":"e_1_2_8_81_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.06.017"},{"key":"e_1_2_8_82_1","doi-asserted-by":"publisher","DOI":"10.1177\/1073858404263960"},{"key":"e_1_2_8_83_1","unstructured":"Springenberg J. T. A.Dosovitskiy T.Brox andM.Riedmiller.2014.\u201cStriving for Simplicity: The All Convolutional Net.\u201darXiv preprint arXiv:1412.6806."},{"key":"e_1_2_8_84_1","first-page":"4126","article-title":"Full\u2010Gradient Representation for Neural Network Visualization","volume":"32","author":"Srinivas S.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_85_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-800105-9.00022-6"},{"key":"e_1_2_8_86_1","doi-asserted-by":"publisher","DOI":"10.1016\/0197-4580(95)00074-O"},{"key":"e_1_2_8_87_1","unstructured":"Sundararajan M. A.Taly andQ.Yan.2017. \u201cAxiomatic Attribution for Deep Networks.\u201d In2017International Conference on Machine Learning 3319\u20133328.ACM."},{"key":"e_1_2_8_88_1","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.21088"},{"key":"e_1_2_8_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-00960-4"},{"key":"e_1_2_8_90_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00338.2011"},{"key":"e_1_2_8_91_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.041"},{"key":"e_1_2_8_92_1","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1730-15.2016"},{"key":"e_1_2_8_93_1","first-page":"5998","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_94_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2005.05.020"},{"key":"e_1_2_8_95_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1902376116"},{"key":"e_1_2_8_96_1","volume-title":"The Mouse Nervous System","author":"Watson C.","year":"2012"},{"key":"e_1_2_8_97_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.134"},{"key":"e_1_2_8_98_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_8_99_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00712"},{"key":"e_1_2_8_100_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.116149"},{"key":"e_1_2_8_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_2_8_102_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.JGP.0000238502.40963.ac"},{"key":"e_1_2_8_103_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12264-020-00558-8"}],"container-title":["Human Brain Mapping"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/hbm.70239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T00:02:39Z","timestamp":1750118559000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/hbm.70239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":102,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["10.1002\/hbm.70239"],"URL":"https:\/\/doi.org\/10.1002\/hbm.70239","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.10.31.514506","asserted-by":"object"}]},"ISSN":["1065-9471","1097-0193"],"issn-type":[{"value":"1065-9471","type":"print"},{"value":"1097-0193","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]},"assertion":[{"value":"2024-10-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70239"}}