{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:44:41Z","timestamp":1791924281155,"version":"4.3.4"},"reference-count":52,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Alzheimer\u2019s Disease"],"published-print":{"date-parts":[[2025,8]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>High-order cognitive functions depend on collaborative actions and information exchange between multiple brain regions. These inter-regional interactions can be characterized by mutual information (MI). Alzheimer's disease (AD) is known to affect many high-order cognitive functions, suggesting an alteration to inter-regional MI, which remains unstudied.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To examine whether inter-regional MI can effectively distinguish different stages of AD from normal control (NC) through a connectome-based graph convolutional network (GCN).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>MI was calculated between the mean time series of each pair of brain regions, forming the connectome which was input to a multi-level connectome based GCN (MLC-GCN) to predict the different stages of AD and NC. The spatio-temporal feature extraction in MLC-GCN was used to capture multi-level functional connectivity patterns generating connectomes. The GCN predictor learns and optimizes graph representations at each level, concatenating the representations for final classification. We validated our model on 552 subjects from ADNI and OASIS3. The MI-based model was compared to models with several different connectomes defined by Kullback-Leibler divergence, cross-entropy, cross-sample entropy, and correlation coefficient. Model performance was evaluated using 5-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The MI-based connectome achieved the highest prediction performance for both ADNI2 and OASIS3 where it's accuracy\/Area Under the Curve\/F1 were 87.72%\/0.96\/0.88 and 84.11%\/0.96\/0.91 respectively. Model visualization revealed that prominent MI features located in temporal, prefrontal, and parietal cortices.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>MI-based connectomes can reliably differentiate NC, mild cognitive impairment and AD. Compared to other four measures, MI demonstrated the best performance. The model should be further tested with other independent datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/13872877251350306","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T07:11:08Z","timestamp":1752563468000},"page":"1021-1035","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Alzheimer's disease classification using mutual information generated graph convolutional network for functional MRI"],"prefix":"10.1177","volume":"106","author":[{"given":"Yinghua","family":"Fu","sequence":"first","affiliation":[{"name":"Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Detre","sequence":"additional","affiliation":[{"name":"Neurology and Radiology, University of Pennsylvania Perelman School of Medicine, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ze","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"for the Alzheimer's Disease Neuroimaging Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2017.02.001"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13195-016-0207-9"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/alz.13859"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-141419"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1433"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2704614"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1186\/alzrt100"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11065-014-9249-6"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.11.025"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(03)00340-9"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2010.08.042"},{"key":"e_1_3_3_13_2","volume-title":"On hippocampus associative modeling by approximating nonlinear Kullback-Leibler sparsity constraint2021 International Conference on Computer Communication and Informatics (ICCCI)","author":"Ghosh S","unstructured":"Ghosh S, Chandra A, Mudi R. On hippocampus associative modeling by approximating nonlinear Kullback-Leibler sparsity constraint. In: 2021 International Conference on Computer Communication and Informatics (ICCCI), Coimbatore, India, Piscataway, NJ: IEEE, 27\u201329 January 2021."},{"key":"e_1_3_3_14_2","volume-title":"Distribution of connectivity strengths across functional regions has higher entropy in schizophrenia patients than in controls2024 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)","author":"Maksymchuk N","unstructured":"Maksymchuk N, Miller RL, Calhoun VD. Distribution of connectivity strengths across functional regions has higher entropy in schizophrenia patients than in controls. In: 2024 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI), 2024."},{"key":"e_1_3_3_15_2","first-page":"473","volume-title":"Analysis of functional MRI data using mutual informationInternational Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Tsai A","unstructured":"Tsai A, Fisher JWIII, Wible C, et al. Analysis of functional MRI data using mutual information. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, 1999, pp.473\u2013480."},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2007.08.018"},{"key":"e_1_3_3_17_2","first-page":"542","volume-title":"Brain functional connectivity analysis using mutual information2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP)","author":"Wang Z","unstructured":"Wang Z, Alahmadi A, Zhu D, et al. Brain functional connectivity analysis using mutual information. In: 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2015, pp.542\u2013546."},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03707-y"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhaa292"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3051604"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3294967"},{"key":"e_1_3_3_22_2","unstructured":"Zhu W Fu Y Wang Z. MLC-GCN: Multi-level generated connectome based GCN for AD analysis. arXiv preprint. 2024; arXiv:2408.03358."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nic.2005.09.008"},{"key":"e_1_3_3_24_2","doi-asserted-by":"crossref","unstructured":"LaMontagne PJ Benzinger TL Morris JC et al. OASIS-3: Longitudinal neuroimaging clinical and cognitive dataset for normal aging and Alzheimer disease. medRxiv 2019; https:\/\/doi.org\/10.1101\/2019.12.13.19014902 (Preprint). Posted December 15 2019.","DOI":"10.1101\/2019.12.13.19014902"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.43.11.2412-a"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2018.00052"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhw157"},{"key":"e_1_3_3_28_2","first-page":"1","article-title":"Exploring functional connectivities of the human brain using multivariate information analysis","volume":"22","author":"Chai B","year":"2009","unstructured":"Chai B, Walther D, Beck D, et al. Exploring functional connectivities of the human brain using multivariate information analysis. Adv Neural Inf Process Syst 2009; 22: 1\u20139.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_29_2","volume-title":"Decoupled weight decay regularization7th International Conference on Learning Representations","author":"Loshchilov I","unstructured":"Loshchilov I, Hutter F. Decoupled weight decay regularization. In: 7th International Conference on Learning Representations, New Orleans, 6\u20139 May 2019. https:\/\/dblp.org\/rec\/conf\/iclr\/LoshchilovH19.html"},{"key":"e_1_3_3_30_2","unstructured":"Kingma DP Ba J. Adam: A method for stochastic optimization. arXiv preprint 2014; arXiv:1412.6980."},{"key":"e_1_3_3_31_2","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava N","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014; 15: 1929\u20131958.","journal-title":"J Mach Learn Res"},{"key":"e_1_3_3_32_2","first-page":"1","volume-title":"Mixup: beyond empirical risk minimizationInternational Conference on Learning Representations","author":"Zhang H","unstructured":"Zhang H, Cisse M, Dauphin YN, et al. Mixup: beyond empirical risk minimization. In: International Conference on Learning Representations, Vancouver, April 2018, pp.1\u201313."},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/66.3.605"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704472"},{"key":"e_1_3_3_36_2","first-page":"278","volume-title":"Random decision forestsProceedings of 3rd International Conference on Document Analysis and Recognition","author":"Ho TK","unstructured":"Ho TK. Random decision forests. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, 1995, pp.278\u2013282."},{"key":"e_1_3_3_37_2","first-page":"55","volume-title":"The support vector method of function estimationNonlinear Modeling: Advanced Black-Box Techniques","author":"Vapnik V","unstructured":"Vapnik V. The support vector method of function estimation. In: Nonlinear Modeling: Advanced Black-Box Techniques, 1998, pp.55\u201385: Springer."},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2017.08.017"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.09.046"},{"key":"e_1_3_3_40_2","first-page":"70","volume-title":"FCNet: a convolutional neural network for calculating functional connectivity from functional MRIConnectomics in Neuroimaging: MICCAI 2017 Proceedings","author":"Riaz A","unstructured":"Riaz A, Asad M, SMR A-A, et al. FCNet: a convolutional neural network for calculating functional connectivity from functional MRI. In: Connectomics in Neuroimaging: MICCAI 2017 Proceedings, 2017, pp.70\u201378: Springer."},{"key":"e_1_3_3_41_2","volume-title":"Graph attention networksInternational Conference on Learning Representations","author":"Veli\u010dkovi\u0107 P","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, et al. Graph attention networks. In: International Conference on Learning Representations, 2018."},{"key":"e_1_3_3_42_2","unstructured":"Kipf TN Welling M. Semi-supervised learning with graph convolutional networks. arXiv preprint 2017; arXiv:1609.02907."},{"key":"e_1_3_3_43_2","first-page":"618","volume-title":"FBNetgen: task-aware GNN-based fMRI analysis via functional brain network generationInternational Conference on Medical Imaging with Deep Learning","author":"Kan X","unstructured":"Kan X, Cui H, Lukemire J, et al. FBNetgen: task-aware GNN-based fMRI analysis via functional brain network generation. In: International Conference on Medical Imaging with Deep Learning, 2022, pp.618\u2013637."},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.49.3.786"},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e3181f11e35"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2013.04.014"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2020.596122"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.3233\/JAD-210116"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11682-023-00764-8"},{"key":"e_1_3_3_50_2","unstructured":"Zhou Z Lian L Yin Y et al. Neural network compression via effective filter analysis and hierarchical pruning. arXiv preprint 2022; arXiv:2206.03596."},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2020.108669"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1002\/alz.14515"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3219260"}],"container-title":["Journal of Alzheimer\u2019s Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/13872877251350306","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/13872877251350306","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/13872877251350306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T10:10:54Z","timestamp":1777371054000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/13872877251350306"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,15]]},"references-count":52,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["10.1177\/13872877251350306"],"URL":"https:\/\/doi.org\/10.1177\/13872877251350306","relation":{},"ISSN":["1387-2877","1875-8908"],"issn-type":[{"value":"1387-2877","type":"print"},{"value":"1875-8908","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,15]]}}}