{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T18:48:07Z","timestamp":1793472487538,"version":"4.5.0"},"reference-count":41,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Key Research Project of Higher Education Institutions of Henan Province, China","award":["24A416002"],"award-info":[{"award-number":["24A416002"]}]},{"name":"the Key Research and Development and Promotion Project of Henan Province, China","award":["202102310534"],"award-info":[{"award-number":["202102310534"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Alzheimer\u2019s disease (AD) is a common type of dementia, with mild cognitive impairment (MCI) being a key precursor. Early MCI diagnosis is crucial for slowing AD progression, but distinguishing MCI from normal controls (NC) is challenging due to subtle imaging differences. Furthermore, differentiating early MCI (EMCI) from late MCI (LMCI) is also important for interventions. This study proposes a deep learning-based approach using a weighted probability-based ensemble method to integrate results from three-dimensional residual networks (3D ResNet). (1) This study employs 3D ResNet-18, 3D ResNet-34, and 3D ResNet-50 architectures with the Convolutional Block Attention Module (CBAM). The attention mechanism enhances performance by helping the model focus on pertinent information. Data augmentation techniques are applied to address limited data and improve accuracy. (2) To overcome the limitation of the individual convolutional neural network (CNN), an ensemble learning method is adopted. The method assigns weights to each 3D CNN model based on prediction accuracy and integrates them to obtain the final result. Our method achieves accuracy of 94.87%, 92.31%, 95.49%, and 95.97% for MCI vs. NC, MCI vs. AD, EMCI vs. LMCI, and NC vs. EMCI vs. LMCI vs. AD, respectively. The results demonstrate the effectiveness of our method for AD diagnosis.<\/jats:p>","DOI":"10.1371\/journal.pone.0324520","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T13:33:52Z","timestamp":1749648832000},"page":"e0324520","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":7,"title":["An ensemble-based 3D residual network for the classification of Alzheimer\u2019s disease"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-3192","authenticated-orcid":true,"given":"Xiaoli","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1046-6662","authenticated-orcid":true,"given":"Jiayi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenchen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawen","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angchao","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuan","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"pone.0324520.ref001","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1016\/j.inffus.2020.09.002","article-title":"Alzheimer\u2019s disease multiclass diagnosis via multimodal neuroimaging embedding feature selection and fusion","volume":"66","author":"Y Zhang","year":"2021","journal-title":"Information Fusion"},{"key":"pone.0324520.ref002","doi-asserted-by":"crossref","first-page":"101947","DOI":"10.1016\/j.media.2020.101947","article-title":"Graph convolution network with similarity awareness and adaptive calibration for disease-induced deterioration prediction","volume":"69","author":"X Song","year":"2021","journal-title":"Med Image Anal"},{"key":"pone.0324520.ref003","doi-asserted-by":"crossref","first-page":"866230","DOI":"10.3389\/fnagi.2022.866230","article-title":"Automated classification of mild cognitive impairment by machine learning with hippocampus-related white matter network","volume":"14","author":"Y Zhou","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"pone.0324520.ref004","doi-asserted-by":"crossref","first-page":"63605","DOI":"10.1109\/ACCESS.2019.2913847","article-title":"Deep learning framework for Alzheimer\u2019s disease diagnosis via 3D-CNN and FSBi-LSTM","volume":"7","author":"C Feng","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0324520.ref005","article-title":"Comparison of machine learning approaches for enhancing Alzheimer\u2019s disease classification","volume":"9","author":"Q Li","year":"2021","journal-title":"PeerJ"},{"issue":"15","key":"pone.0324520.ref006","doi-asserted-by":"crossref","first-page":"8686","DOI":"10.3390\/app13158686","article-title":"A novel deep dense block-based model for detecting Alzheimer\u2019s disease","volume":"13","author":"SB \u00c7elebi","year":"2023","journal-title":"Applied Sci"},{"issue":"6","key":"pone.0324520.ref007","doi-asserted-by":"crossref","first-page":"1961","DOI":"10.18280\/ts.390608","article-title":"Performance analysis of machine learning and deep learning models for classification of Alzheimer\u2019s disease from brain MRI","volume":"39","author":"I Thayumanasamy","year":"2022","journal-title":"Traitement Sig"},{"key":"pone.0324520.ref008","doi-asserted-by":"crossref","first-page":"101645","DOI":"10.1016\/j.nicl.2018.101645","article-title":"Automated classification of Alzheimer\u2019s disease and mild cognitive impairment using a single MRI and deep neural networks","volume":"21","author":"S Basaia","year":"2019","journal-title":"Neuroimage Clin"},{"key":"pone.0324520.ref009","article-title":"Deep learning-based feature representation for AD\/MCI classification.","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2013","author":"H-I Suk","year":"2013"},{"key":"pone.0324520.ref010","volume-title":"Going deeper with convolutions. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2015 7-12 June 2015","author":"C Szegedy"},{"key":"pone.0324520.ref011","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K Simonyan","year":"2014","journal-title":"arXiv preprint arXiv:14091556"},{"key":"pone.0324520.ref012","volume-title":"Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition","author":"K He","year":"2016"},{"key":"pone.0324520.ref013","first-page":"405","volume-title":"The diagnosis of Alzheimer\u2019s disease based on enhanced residual neutral network. 2019 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC)","author":"M Xu","year":"2019"},{"issue":"12","key":"pone.0324520.ref014","doi-asserted-by":"crossref","first-page":"1460","DOI":"10.2174\/1573405617666210127161812","article-title":"Diagnosing Alzheimer\u2019s disease based on multiclass MRI scans using transfer learning techniques","volume":"17","author":"D Prakash","year":"2021","journal-title":"Curr Med Imaging"},{"issue":"11","key":"pone.0324520.ref015","first-page":"2924","article-title":"Enhancing Alzheimer\u2019s disease classification using 3D convolutional neural network and multilayer perceptron model with attention network","volume":"17","author":"EA Frimpong","year":"2023","journal-title":"KSii Transactions on Internet and Information Systems"},{"issue":"11","key":"pone.0324520.ref016","doi-asserted-by":"crossref","first-page":"5289","DOI":"10.1109\/JBHI.2021.3066832","article-title":"An explainable 3D residual self-attention deep neural network for joint atrophy localization and Alzheimer\u2019s disease diagnosis using structural MRI","volume":"26","author":"X Zhang","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0324520.ref017","doi-asserted-by":"crossref","first-page":"101694","DOI":"10.1016\/j.media.2020.101694","article-title":"Convolutional neural networks for classification of Alzheimer\u2019s disease: Overview and reproducible evaluation","volume":"63","author":"J Wen","year":"2020","journal-title":"Med Image Anal"},{"issue":"2","key":"pone.0324520.ref018","doi-asserted-by":"crossref","first-page":"254","DOI":"10.3390\/brainsci13020254","article-title":"Effects of patchwise sampling strategy to three-dimensional convolutional neural network-based Alzheimer\u2019s disease classification","volume":"13","author":"X Shen","year":"2023","journal-title":"Brain Sci"},{"key":"pone.0324520.ref019","doi-asserted-by":"crossref","first-page":"107944","DOI":"10.1016\/j.patcog.2021.107944","article-title":"Iterative sparse and deep learning for accurate diagnosis of Alzheimer\u2019s disease","volume":"116","author":"Y Chen","year":"2021","journal-title":"Pattern Recognition"},{"issue":"4","key":"pone.0324520.ref020","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1109\/JBHI.2021.3083274","article-title":"Classification of Alzheimer\u2019s disease using ensemble of deep neural networks trained through transfer learning","volume":"26","author":"M Tanveer","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"issue":"22","key":"pone.0324520.ref021","doi-asserted-by":"crossref","first-page":"7634","DOI":"10.3390\/s21227634","article-title":"Diagnosis of Alzheimer\u2019s disease with ensemble learning classifier and 3D convolutional neural network","volume":"21","author":"P Zhang","year":"2021","journal-title":"Sensors (Basel)"},{"issue":"8","key":"pone.0324520.ref022","doi-asserted-by":"crossref","first-page":"377","DOI":"10.3390\/a16080377","article-title":"Ensemble transfer learning for distinguishing cognitively normal and mild cognitive impairment patients using MRI","volume":"16","author":"P Grover","year":"2023","journal-title":"Algorithms"},{"key":"pone.0324520.ref023","doi-asserted-by":"crossref","first-page":"103411","DOI":"10.1016\/j.jbi.2020.103411","article-title":"Deep ensemble learning for Alzheimer\u2019s disease classification","volume":"105","author":"N An","year":"2020","journal-title":"J Biomed Inform"},{"key":"pone.0324520.ref024","doi-asserted-by":"crossref","first-page":"115974","DOI":"10.1109\/ACCESS.2022.3218621","article-title":"Automatic early diagnosis of Alzheimer\u2019s disease using 3D deep ensemble approach","volume":"10","author":"A Gamal","year":"2022","journal-title":"IEEE Access"},{"issue":"4","key":"pone.0324520.ref025","doi-asserted-by":"crossref","first-page":"1914","DOI":"10.3390\/s23041914","article-title":"A convolutional neural network and graph convolutional network based framework for AD classification","volume":"23","author":"L Lin","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0324520.ref026","first-page":"615","volume-title":"Deep residual nets for improved Alzheimer\u2019s diagnosis. Proceedings of the 8th ACM International Conference on Bioinformatics, Computational Biology,and Health Informatics","author":"A Valliani","year":"2017"},{"issue":"9","key":"pone.0324520.ref027","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.1109\/TMI.2021.3077079","article-title":"Dual attention multi-instance deep learning for Alzheimer\u2019s disease diagnosis with structural MRI","volume":"40","author":"W Zhu","year":"2021","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0324520.ref028","first-page":"3","article-title":"CBAM: Convolutional Block Attention Module. Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","journal-title":"Lecture Notes Comput Sci"},{"issue":"5","key":"pone.0324520.ref029","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1007\/s12559-017-9472-6","article-title":"Ensemble of Deep Neural Networks with Probability-Based Fusion for Facial Expression Recognition","volume":"9","author":"G Wen","year":"2017","journal-title":"Cogn Comput"},{"key":"pone.0324520.ref030","volume-title":"Alzheimer\u2019s Disease Neuroimaging Initiative ft, editors. 3D DenseNet Ensemble in 4-Way Classification of Alzheimer\u2019s Disease. Brain Informatics; 2020","author":"J Ruiz","year":"2020"},{"issue":"12","key":"pone.0324520.ref031","doi-asserted-by":"crossref","first-page":"4609","DOI":"10.3390\/s22124609","article-title":"Early-Stage Alzheimer\u2019s disease categorization using PET neuroimaging modality and convolutional neural networks in the 2D and 3D domains","volume":"22","author":"AB Tufail","year":"2022","journal-title":"Sensors (Basel)"},{"key":"pone.0324520.ref032","doi-asserted-by":"crossref","first-page":"116459","DOI":"10.1016\/j.neuroimage.2019.116459","article-title":"A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer\u2019s disease","volume":"208","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2020","journal-title":"Neuroimage"},{"issue":"1","key":"pone.0324520.ref033","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/IJSWIS.313715","article-title":"An efficient lightweight network based on magnetic resonance images for predicting Alzheimer\u2019s disease","volume":"18","author":"B Ji","year":"2022","journal-title":"Int J Semantic Web Info Syst"},{"issue":"14","key":"pone.0324520.ref034","doi-asserted-by":"crossref","first-page":"3948","DOI":"10.1049\/ipr2.12605","article-title":"Diagnose Alzheimer\u2019s disease by combining 3D discrete wavelet transform and 3D moment invariants","volume":"16","author":"H Lao","year":"2022","journal-title":"IET Image Process"},{"key":"pone.0324520.ref035","doi-asserted-by":"crossref","first-page":"831533","DOI":"10.3389\/fnins.2022.831533","article-title":"BMNet: A new region-based metric learning method for early Alzheimer\u2019s disease identification with FDG-PET Images","volume":"16","author":"W Cui","year":"2022","journal-title":"Front Neurosci"},{"issue":"1","key":"pone.0324520.ref036","doi-asserted-by":"crossref","first-page":"4284","DOI":"10.1038\/s41598-022-08231-y","article-title":"Searching for optimal machine learning model to classify mild cognitive impairment (MCI) subtypes using multimodal MRI data","volume":"12","author":"T Jitsuishi","year":"2022","journal-title":"Sci Rep"},{"issue":"1","key":"pone.0324520.ref037","first-page":"89","article-title":"A deep learning-based ensemble method for early diagnosis of Alzheimer\u2019s disease using MRI images","volume":"22","author":"Alzheimer\u2019s Disease Neuroimaging Initiative","year":"2024","journal-title":"Neuroinformatics"},{"issue":"1","key":"pone.0324520.ref038","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1109\/TCYB.2019.2940526","article-title":"Fused sparse network learning for longitudinal analysis of mild cognitive impairment","volume":"51","author":"P Yang","year":"2021","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"pone.0324520.ref039","doi-asserted-by":"crossref","DOI":"10.1007\/s42979-023-02581-8","article-title":"An optimal weighted ensemble of 3D CNNs for early diagnosis of Alzheimer\u2019s disease","volume":"5","author":"S Dharwada","year":"2024","journal-title":"SN Comput Sci"},{"issue":"1","key":"pone.0324520.ref040","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s40708-023-00184-w","article-title":"Four-way classification of Alzheimer\u2019s disease using deep Siamese convolutional neural network with triplet-loss function","volume":"10","author":"F Hajamohideen","year":"2023","journal-title":"Brain Inform"},{"issue":"5","key":"pone.0324520.ref041","first-page":"056001","article-title":"Spatiotemporal feature extraction and classification of Alzheimer\u2019s disease using deep learning 3D-CNN for fMRI data","volume":"7","author":"H Parmar","year":"2020","journal-title":"J Med Imaging (Bellingham)"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324520","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T13:34:03Z","timestamp":1749648843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0324520"}},"subtitle":[],"editor":[{"given":"Ghanim","family":"Ullah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":41,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0324520","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,11]]}}}