{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T04:29:16Z","timestamp":1793161756432,"version":"4.5.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Aging Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop a machine learning model based on multimodal radiomics features from cerebellar subregions, utilizing the complementarity of cerebellar structural and metabolic imaging data for accurate diagnosis of Alzheimer\u2019s disease (AD).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 164 cognitively normal (CN) subjects and 146\u202fAD patients from the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) database were included. All participants had 3DT1-weighted magnetic resonance imaging (3DT1W MRI) and [\n                      <jats:sup>18<\/jats:sup>\n                      F]fluorodeoxyglucose positron emission tomography ([\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET) imaging data. The cerebellum was divided into 26 subregions, and radiomics features were extracted from different cerebellar regions of these two modality images, respectively. After feature selection, single-modality ([\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET, 3DT1W MRI) and multimodal ([\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET + 3DT1W MRI) random forest classification models were constructed. Model performance and clinical value were assessed using area under the curve (AUC), calibration curves, and decision curve analysis (DCA). In addition, we also used Shapley Additive exPlanations (SHAP) to clarify the contributions of features, thereby enhancing the interpretability of the model.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All three models could effectively diagnose AD, with the multimodal model showing the best performance. In the independent test set, the multimodal model achieved an AUC of 0.903, which was higher than the single-modality models based on [\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET (AUC\u202f=\u202f0.842) and 3DT1W MRI (AUC\u202f=\u202f0.804). The calibration curves and DCA demonstrated that all three models had good calibration and clinical applicability, especially the multimodal model. SHAP analysis of the multimodal model revealed that among the 15 selected features, the top seven features with the highest SHAP values were derived from [\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET images, with R_FDG_CER_III_original_firstorder_90Percentile and R_FDG_CER_VI_original_firstorder_Median being the two most important features for distinguishing AD from CN.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      The multimodal radiomics model based on cerebellar subregions, which integrates [\n                      <jats:sup>18<\/jats:sup>\n                      F]FDG PET and 3DT1W MRI data, can effectively diagnose AD and provide potential biomarkers for clinical applications.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnagi.2025.1679788","type":"journal-article","created":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T06:21:42Z","timestamp":1761546102000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Multimodal radiomics of cerebellar subregions for machine learning-driven Alzheimer\u2019s disease diagnosis"],"prefix":"10.3389","volume":"17","author":[{"given":"Xinqing","family":"Hao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiulin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changjun","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruichen","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunbo","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"103770","DOI":"10.1016\/j.nicl.2025.103770","article-title":"Altered cerebellar activation patterns in Alzheimer's disease: An activation likelihood estimation Meta-analysis","volume":"46","author":"Bernard","year":"2025","journal-title":"Neuroimage Clin."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"432","DOI":"10.3390\/jcm12165432","article-title":"Radiomics and artificial intelligence for the diagnosis and monitoring of Alzheimer's disease: a systematic review of studies in the field","volume":"12","author":"Bevilacqua","year":"2023","journal-title":"J. Clin. Med."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.schres.2024.06.044","article-title":"Unveiling altered connectivity between cognitive networks and cerebellum in schizophrenia","volume":"271","author":"Biondi","year":"2024","journal-title":"Schizophr. Res."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2967\/jnumed.118.219097","article-title":"Principal components analysis of brain metabolism predicts development of Alzheimer dementia","volume":"60","author":"Blazhenets","year":"2019","journal-title":"J. Nucl. Med."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1152\/jn.00339.2011","article-title":"The organization of the human cerebellum estimated by intrinsic functional connectivity","volume":"106","author":"Buckner","year":"2011","journal-title":"J. Neurophysiol."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e14361","DOI":"10.1002\/alz.14361","article-title":"Integrated cerebellar radiomic-network model for predicting mild cognitive impairment in Alzheimer's disease","volume":"21","author":"Chen","year":"2025","journal-title":"Alzheimers Dement."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1016\/s1474-4422(20)30314-8","article-title":"Amyloid-PET and 18F-FDG-PET in the diagnostic investigation of Alzheimer's disease and other dementias","volume":"19","author":"Ch\u00e9telat","year":"2020","journal-title":"Lancet Neurol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.pscychresns.2014.06.006","article-title":"Patterns of cerebellar volume loss in dementia with Lewy bodies and Alzheimer\u2032s disease: a VBM-DARTEL study","volume":"223","author":"Colloby","year":"2014","journal-title":"Psychiatry Res."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1186\/s13195-017-0297-z","article-title":"Alzheimer's disease prevention: from risk factors to early intervention","volume":"9","author":"Crous-Bou","year":"2017","journal-title":"Alzheimer's Res. Ther."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.nicl.2013.10.018","article-title":"Reduced FDG-PET brain metabolism and executive function predict clinical progression in elderly healthy subjects","volume":"4","author":"Ewers","year":"2014","journal-title":"Neuroimage Clin."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"102605","DOI":"10.1016\/j.nicl.2021.102605","article-title":"Differential vulnerability of the cerebellum in healthy ageing and Alzheimer's disease","volume":"30","author":"Gellersen","year":"2021","journal-title":"Neuroimage Clin."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"102749","DOI":"10.1016\/j.nicl.2021.102749","article-title":"PET evidence of preclinical cerebellar amyloid plaque deposition in autosomal dominant Alzheimer's disease-causing Presenilin-1 E280A mutation carriers","volume":"31","author":"Ghisays","year":"2021","journal-title":"Neuroimage Clin."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1016\/j.neuroimage.2018.01.082","article-title":"Triple representation of language, working memory, social and emotion processing in the cerebellum: convergent evidence from task and seed-based resting-state fMRI analyses in a single large cohort","volume":"172","author":"Guell","year":"2018","journal-title":"Neuroimage"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"148","DOI":"10.7554\/eLife.59148","article-title":"Disynaptic cerebrocerebellar pathways originating from multiple functionally distinct cortical areas","volume":"9","author":"Henschke","year":"2020","journal-title":"eLife"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1093\/brain\/awx317","article-title":"The cerebellar cognitive affective\/Schmahmann syndrome scale","volume":"141","author":"Hoche","year":"2018","journal-title":"Brain"},{"key":"ref16","first-page":"925","article-title":"Reduction of cerebellar glucose metabolism in advanced Alzheimer's disease","volume":"38","author":"Ishii","year":"1997","journal-title":"J. Nucl. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.3390\/ijms25021018","article-title":"Aging, neurodegenerative disorders, and cerebellum","volume":"25","author":"Iskusnykh","year":"2024","journal-title":"Int. J. Mol. Sci."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1002\/ana.20799","article-title":"Brain imaging evidence of preclinical Alzheimer's disease in normal aging","volume":"59","author":"Jagust","year":"2006","journal-title":"Ann. Neurol."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"102497","DOI":"10.1016\/j.arr.2024.102497","article-title":"AI-driven innovations in Alzheimer's disease: integrating early diagnosis, personalized treatment, and prognostic modelling","volume":"101","author":"Kale","year":"2024","journal-title":"Ageing Res. Rev."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"8432","DOI":"10.1523\/jneurosci.23-23-08432.2003","article-title":"Cerebellar loops with motor cortex and prefrontal cortex of a nonhuman primate","volume":"23","author":"Kelly","year":"2003","journal-title":"J. Neurosci."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1038\/s41572-021-00269-y","article-title":"Alzheimer disease","volume":"7","author":"Knopman","year":"2021","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","article-title":"Radiomics: the bridge between medical imaging and personalized medicine","volume":"14","author":"Lambin","year":"2017","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1177\/13872877241283678","article-title":"The emerging role of the cerebellum in neurodegeneration linked to cognitive impairment","volume":"102","author":"Lin","year":"2024","journal-title":"J Alzheimer's Dis"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"372","DOI":"10.1016\/j.cnp.2022.11.002","article-title":"The underpinnings of cerebellar ataxias","volume":"7","author":"Manto","year":"2022","journal-title":"Clin. Neurophysiol. Pract."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e336-e345","DOI":"10.1016\/s2666-7568(24)00033-3","article-title":"The time course of motor and cognitive decline in older adults and their associations with brain pathologies: a multicohort study","volume":"5","author":"Oveisgharan","year":"2024","journal-title":"Lancet Healthy Longev."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"11752","DOI":"10.1038\/s41598-022-15667-9","article-title":"Identification and validation of Alzheimer's disease-related metabolic brain pattern in biomarker confirmed Alzheimer's dementia patients","volume":"12","author":"Perovnik","year":"","journal-title":"Sci. Rep."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1005731","DOI":"10.3389\/fnagi.2022.1005731","article-title":"Automated differential diagnosis of dementia syndromes using FDG PET and machine learning","volume":"14","author":"Perovnik","year":"","journal-title":"Front. Aging Neurosci."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.arr.2016.01.002","article-title":"Brain atrophy in Alzheimer's disease and aging","volume":"30","author":"Pini","year":"2016","journal-title":"Ageing Res. Rev."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"108771","DOI":"10.1016\/j.cmpb.2025.108771","article-title":"Combining radiomics and connectomics in MRI studies of the human brain: a systematic literature review","volume":"266","author":"Pirozzi","year":"2025","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"e14428","DOI":"10.1002\/alz.14428","article-title":"Neuropathological correlates of vulnerability and resilience in the cerebellum in Alzheimer's disease","volume":"21","author":"Samstag","year":"2025","journal-title":"Alzheimers Dement."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e70039","DOI":"10.1002\/alz.70039","article-title":"Motor symptoms in autopsy-confirmed Alzheimer's disease increase the risk of progression to severe cognitive impairment","volume":"21","author":"Shaw","year":"2025","journal-title":"Alzheimers Dement."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e778","DOI":"10.1002\/mco2.778","article-title":"Machine learning-based radiomics in neurodegenerative and cerebrovascular disease","volume":"5","author":"Shi","year":"2024","journal-title":"MedComm"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1016\/j.neuroimage.2011.08.065","article-title":"Functional topography of the cerebellum for motor and cognitive tasks: an fMRI study","volume":"59","author":"Stoodley","year":"2012","journal-title":"Neuroimage"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"645171","DOI":"10.3389\/fneur.2021.645171","article-title":"Differences changes in cerebellar functional connectivity between mild cognitive impairment and Alzheimer's disease: a seed-based approach","volume":"12","author":"Tang","year":"2021","journal-title":"Front. Neurol."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"430","DOI":"10.3389\/fncel.2018.00430","article-title":"Patterns of cerebellar gray matter atrophy across Alzheimer's disease progression","volume":"12","author":"Toniolo","year":"2018","journal-title":"Front. Cell. Neurosci."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"1520","DOI":"10.1007\/s00259-024-06995-1","article-title":"The cerebellar glucose metabolism in moyamoya vasculopathy and its correlation with neurocognitive performance after cerebral revascularization surgery: a [18F]FDG PET study","volume":"52","author":"Weng","year":"2025","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"2440","DOI":"10.1007\/s00259-020-04752-8","article-title":"Multiparametric imaging hippocampal neurodegeneration and functional connectivity with simultaneous PET\/MRI in Alzheimer's disease","volume":"47","author":"Yan","year":"2020","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"e638","DOI":"10.1002\/mco2.638","article-title":"Cerebellum in Alzheimer's disease and other neurodegenerative diseases: an emerging research frontier","volume":"5","author":"Yang","year":"2024","journal-title":"MedComm"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1002\/alz.12853","article-title":"The electrophysiological and neuropathological profiles of cerebellum in APP(swe) \/PS1(\u0394E9) mice: a hypothesis on the role of cerebellum in Alzheimer's disease","volume":"19","author":"Yu","year":"2023","journal-title":"Alzheimers Dement."}],"container-title":["Frontiers in Aging Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1679788\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T06:21:43Z","timestamp":1761546103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnagi.2025.1679788\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"alternative-id":["10.3389\/fnagi.2025.1679788"],"URL":"https:\/\/doi.org\/10.3389\/fnagi.2025.1679788","relation":{},"ISSN":["1663-4365"],"issn-type":[{"value":"1663-4365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"article-number":"1679788"}}