{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:42:42Z","timestamp":1791913362730,"version":"4.3.4"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T00:00:00Z","timestamp":1765756800000},"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. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Alzheimer\u2019s disease (AD), the most prevalent form of dementia, affects more than 50 million individuals worldwide and demands accurate and timely diagnosis to improve patient outcomes. Traditional machine-learning approaches for AD detection using MRI often rely on manual feature extraction, which is labor-intensive and limits scalability. There is a growing need for automated, high-accuracy methods that can support clinical workflows and respond to the expected tripling of AD cases by 2050.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes an automated feature-extraction approach using a pre-trained ResNet50 convolutional neural network (CNN) applied to brain MRI scans. Extracted deep features were classified using three different algorithms: Softmax, Support Vector Machine (SVM), and Random Forest (RF). Performance was evaluated on two benchmark datasets: ADNI and MIRIAD.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the tested models, the ResNet50-Softmax combination demonstrated the highest performance, surpassing state-of-the-art benchmarks (85.7%\u201398.59%). It achieved 99% sensitivity, 98% specificity, and an overall 99% accuracy on the ADNI dataset. On the MIRIAD dataset, the model also performed strongly, reaching 96% accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results confirm that transfer learning using ResNet50 significantly enhances the accuracy and scalability of AD diagnosis from MRI data. By eliminating the need for manual feature extraction and offering near-perfect classification performance, this approach can streamline clinical neuroimaging workflows. These findings highlight the potential of deep learning models to support early diagnosis and meet the increasing global burden of Alzheimer\u2019s disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2025.1664418","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T11:56:08Z","timestamp":1765886168000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Toward accurate Alzheimer\u2019s detection: transfer learning with ResNet50 for MRI-based diagnosis"],"prefix":"10.3389","volume":"19","author":[{"given":"Jabli Mohamed","family":"Amine","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moussa","family":"Mourad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,15]]},"reference":[{"key":"B1","first-page":"149","article-title":"An efficient 3D deep convolutional network for Alzheimer\u2019s disease diagnosis using MR images","volume-title":"2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI)","author":"B\u00e4ckstr\u00f6m","year":"2018"},{"key":"B2","doi-asserted-by":"publisher","first-page":"312","DOI":"10.3389\/fnins.2019.00446","article-title":"A deep learning approach for the early diagnosis of Alzheimer\u2019s disease using structural MR images.","volume":"28","author":"Chen","year":"2018","journal-title":"J. Neuroimag."},{"key":"B3","first-page":"102","article-title":"EfficientNet-based deep learning approach for automated Alzheimer\u2019s disease detection from brain MRI.","volume":"89","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"B4","article-title":"A CNN-based feature extraction and machine learning approach for the diagnosis of Alzheimer\u2019s disease using brain MRI scans","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Cheng","year":"2016"},{"key":"B5","volume-title":"Artificial intelligence\/machine learning (AI\/ML)-Based software as a medical device (SaMD) action plan.","year":"2024"},{"key":"B6","doi-asserted-by":"publisher","first-page":"eaba3884","DOI":"10.1126\/sciadv.aba3884","article-title":"Altered d-glucose in brain parenchyma and cerebrospinal fluid of early Alzheimer\u2019s disease detected by dynamic glucose-enhanced MRI.","volume":"6","author":"Huang","year":"2020","journal-title":"Sci. Adv."},{"key":"B7","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/S1474-4422(13)70044-9","article-title":"Tracking pathophysiological processes in Alzheimer\u2019s disease: An updated hypothetical model of dynamic biomarkers.","volume":"12","author":"Jack","year":"2013","journal-title":"Lancet Neurol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.vph.2008.11.009","article-title":"Effect of Hydroxysafflor yellow A on human umbilical vein endothelial cells under hypoxia.","volume":"50","author":"Ji","year":"2018","journal-title":"Vascul. Pharmacol."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1145\/3341016.3341024","article-title":"Early diagnosis of Alzheimer\u2019s disease using deep learning","volume-title":"Proceedings of the 2nd international conference on control and computer vision, Jeju, Korea","author":"Ji","year":"2019"},{"key":"B10","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.ijcard.2014.10.164","article-title":"Absolute change in fasting plasma glucose over 12 months is associated with 2-year and 5-year major adverse cardiovascular events in patients with drug-eluting stent implants.","volume":"179","author":"Kang","year":"2018","journal-title":"Int. J. Cardiol."},{"key":"B11","doi-asserted-by":"crossref","DOI":"10.1109\/ISBI.2017.7950647","article-title":"Residual and plain convolutional neural networks for 3D brain MRI classification","volume-title":"Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","author":"Korolev","year":"2017"},{"key":"B12","doi-asserted-by":"publisher","first-page":"545","DOI":"10.2174\/1567205013666160314145008","article-title":"The Alzheimer\u2019s disease neuroimaging initiative none. fuzzy computer-aided Alzheimer\u2019s disease diagnosis based on MRI data.","volume":"13","author":"Krashenyi","year":"2016","journal-title":"Curr. Alzheimer Res."},{"key":"B13","doi-asserted-by":"publisher","first-page":"289","DOI":"10.3390\/brainsci9100289","article-title":"Computer-Aided diagnosis system of Alzheimer\u2019s disease based on multimodal fusion: Tissue quantification based on the hybrid fuzzy-genetic-possibilistic model and discriminative classification based on the SVDD model.","volume":"9","author":"Lazli","year":"2018","journal-title":"Brain Sci."},{"key":"B14","first-page":"120","article-title":"Hybrid CNN-Transformer architecture for improved Alzheimer\u2019s disease classification using structural MRI.","volume":"285","author":"Li","year":"2024","journal-title":"NeuroImage"},{"key":"B15","doi-asserted-by":"publisher","first-page":"46161","DOI":"10.1007\/s11042-023-17187-8","article-title":"Hierarchical graph learning with convolutional network for brain disease prediction","volume":"83","author":"Liu","year":"2024","journal-title":"Multim. Tools Appl."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TBME.2015.2496233","article-title":"Inherent structure-based multiview learning with multitemplate feature representation for Alzheimer\u2019s disease diagnosis.","volume":"63","author":"Liu","year":"2016","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1132","DOI":"10.1109\/TBME.2014.2372011","article-title":"Multimodal neuroimaging feature learning for multiclass diagnosis of Alzheimer\u2019s disease.","volume":"62","author":"Liu","year":"2015","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B18","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.2967\/jnumed.124.268756","article-title":"Updated appropriate use criteria for amyloid and tau PET: A report from the Alzheimer\u2019s Association and Society for Nuclear Medicine and Molecular Imaging Workgroup","volume":"66","author":"Rabinovici","year":"2025","journal-title":"J. Nucl. Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2510.16973","DOI":"10.48550\/arXiv.2510.16973","author":"Rajendran","year":"2025","journal-title":"Foundation models in medical image analysis: A systematic review and meta-analysis"},{"key":"B20","doi-asserted-by":"publisher","first-page":"100305","DOI":"10.1016\/j.imu.2020.100305","article-title":"Automatic classification of cognitively normal, mild cognitive impairment and Alzheimer\u2019s disease using structural MRI analysis.","volume":"18","author":"Rallabandi","year":"2020","journal-title":"Inform. Med. Unlocked"},{"key":"B21","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1136\/jnnp-2024-333819","article-title":"Vision transformers for medical image classification: Application to Alzheimer\u2019s disease diagnosis.","volume":"43","author":"Rodriguez","year":"2024","journal-title":"IEEE Trans. Med. Imag."},{"key":"B22","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1038\/s41593-024-01774-5","article-title":"Multi-modal neuroimaging biomarkers for early detection of Alzheimer\u2019s disease: A systematic review and meta-analysis.","volume":"20","author":"Smith","year":"2024","journal-title":"Alzheimer\u2019s Dement."},{"key":"B23","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1186\/s12967-024-05025-w","article-title":"DenseNet architectures for neuroimaging: Comparative analysis in Alzheimer\u2019s disease classification.","volume":"239","author":"Wang","year":"2024","journal-title":"Comp. Methods Prog. Biomed."},{"key":"B24","article-title":"A deep learning approach for the early diagnosis of Alzheimer\u2019s disease using structural MR images","volume-title":"Proceedings of the International Conference on Medical Image Computing and Computer- Assisted Intervention","author":"Wang","year":"2018"},{"key":"B25","volume-title":"The state of the art of dementia research: New frontiers.","year":"2018"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1664418\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T14:28:26Z","timestamp":1765895306000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1664418\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,15]]},"references-count":25,"alternative-id":["10.3389\/fnins.2025.1664418"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1664418","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,15]]},"article-number":"1664418"}}