{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T08:50:11Z","timestamp":1772614211122,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T00:00:00Z","timestamp":1680825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T00:00:00Z","timestamp":1680825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["81971683"],"award-info":[{"award-number":["81971683"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Beijing Municipality","award":["L182010"],"award-info":[{"award-number":["L182010"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Accurately diagnosing of Alzheimer's disease (AD) and its early stages is critical for prompt treatment or potential intervention to delay the the disease\u2019s\u00a0progression. Convolutional neural networks (CNNs) models have shown promising results in structural MRI (sMRI)-based diagnosis, but their performance, particularly for 3D models, is constrained by the lack of labeled training samples. To address the overfitting problem brought on by the insufficient training sample size, we propose a three-round learning strategy that combines transfer learning with generative adversarial learning. In the first round, a 3D Deep Convolutional Generative Adversarial Networks (DCGAN) model was trained with all available sMRI data to learn the common feature of sMRI through unsupervised generative adversarial learning. The second round involved transferring and fine-tuning, and the pre-trained discriminator (D) of the DCGAN learned more specific features for the classification task between AD and cognitively normal (CN). In the final round, the weights learned in the AD versus CN classification task were transferred to the MCI diagnosis. By highlighting brain regions with high prediction weights using 3D Grad-CAM, we further enhanced the model's interpretability. The proposed model achieved accuracies of 92.8%, 78.1%, and 76.4% in the classifications of AD versus CN, AD versus MCI, and MCI versus CN, respectively. The experimental results show that our proposed model avoids overfitting brought on by a paucity of sMRI data and enables the early detection of AD.<\/jats:p>","DOI":"10.1038\/s41598-023-33055-9","type":"journal-article","created":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T19:02:27Z","timestamp":1680894147000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Three-round learning strategy based on 3D deep convolutional GANs for Alzheimer\u2019s disease staging"],"prefix":"10.1038","volume":"13","author":[{"given":"Wenjie","family":"Kang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shen","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuicai","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,4,7]]},"reference":[{"key":"33055_CR1","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/S1474-4422(19)30290-X","volume":"19","author":"L Jia","year":"2020","unstructured":"Jia, L. et al. Dementia in China: Epidemiology, clinical management, and research advances. Lancet Neurol. 19, 81\u201392 (2020).","journal-title":"Lancet Neurol."},{"key":"33055_CR2","unstructured":"Zhao, L. 2020 Alzheimer's disease facts and figures. Alzheimers Dement. (2020)."},{"issue":"10","key":"33055_CR3","doi-asserted-by":"publisher","first-page":"5481","DOI":"10.1038\/s41380-021-01249-0","volume":"26","author":"H Hampel","year":"2021","unstructured":"Hampel, H. et al. The amyloid-\u03b2 pathway in Alzheimer\u2019s disease. Mol. Psychiatry. 26(10), 5481\u20135503 (2021).","journal-title":"Mol. Psychiatry."},{"issue":"4","key":"33055_CR4","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1148\/rg.2016150172","volume":"36","author":"MM Miller-Thomas","year":"2016","unstructured":"Miller-Thomas, M. M. et al. Multimodality review of amyloid-related diseases of the central nervous system. Radiographics 36(4), 1147\u20131163 (2016).","journal-title":"Radiographics"},{"key":"33055_CR5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1017\/S1041610297004146","volume":"9","author":"N Graham","year":"1997","unstructured":"Graham, N. Alzheimer\u2019s disease international. Int. Psychogeriatr. 9, 5\u20136 (1997).","journal-title":"Int. Psychogeriatr."},{"issue":"2","key":"33055_CR6","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1080\/17453674.2019.1711323","volume":"91","author":"PHS Kalmet","year":"2020","unstructured":"Kalmet, P. H. S. et al. Deep learning in fracture detection: A narrative review. Acta Orthop. 91(2), 215\u2013220 (2020).","journal-title":"Acta Orthop."},{"issue":"2","key":"33055_CR7","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1080\/17453674.2019.1711323","volume":"91","author":"PHS Kalmet","year":"2020","unstructured":"Kalmet, P. H. S. et al. Deep learning in fracture detection: A narrative review. Acta Orthop. 91(2), 215\u2013220 (2020).","journal-title":"Acta Orthop."},{"key":"33055_CR8","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-33128-3_1","volume":"1213","author":"HP Chan","year":"2020","unstructured":"Chan, H. P., Samala, R. K., Hadjiiski, L. M. & Zhou, C. Deep learning in medical image analysis. Adv. Exp. Med. Biol. 1213, 3\u201321 (2020).","journal-title":"Adv. Exp. Med. Biol."},{"key":"33055_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101694","volume":"63","author":"J Wen","year":"2020","unstructured":"Wen, J. et al. Convolutional neural networks for classification of Alzheimer\u2019s disease: Overview and reproducible evaluation. Med. Image Anal. 63, 101694 (2020).","journal-title":"Med. Image Anal."},{"key":"33055_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2020.e05652","volume":"6","author":"K Aderghal","year":"2020","unstructured":"Aderghal, K., Afdel, K., Benois-Pineau, J. & Catheline, G. Improving Alzheimer\u2019s stage categorization with Convolutional Neural Network using transfer learning and different magnetic resonance imaging modalities. Heliyon. 6, e05652 (2020).","journal-title":"Heliyon."},{"key":"33055_CR11","doi-asserted-by":"publisher","first-page":"777","DOI":"10.3389\/fnins.2018.00777","volume":"12","author":"W Lin","year":"2018","unstructured":"Lin, W. et al. Convolutional neural networks-based MRI image analysis for the Alzheimer\u2019s disease prediction from mild cognitive impairment. Front. Neurosci. 12, 777 (2018).","journal-title":"Front. Neurosci."},{"key":"33055_CR12","doi-asserted-by":"publisher","first-page":"259","DOI":"10.3389\/fnins.2020.00259","volume":"14","author":"D Pan","year":"2020","unstructured":"Pan, D. et al. Early detection of Alzheimer\u2019s disease using magnetic resonance imaging: A novel approach combining convolutional neural networks and ensemble learning. Front. Neurosci. 14, 259 (2020).","journal-title":"Front. Neurosci."},{"key":"33055_CR13","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2020.576194","volume":"11","author":"L Nanni","year":"2020","unstructured":"Nanni, L. et al. Alzheimer\u2019s disease neuroimaging initiative: Comparison of transfer learning and conventional machine learning applied to structural brain MRI for the early diagnosis and prognosis of Alzheimer\u2019s disease. Front Neurol. 11, 576194 (2020).","journal-title":"Front Neurol."},{"key":"33055_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104678","volume":"136","author":"W Kang","year":"2021","unstructured":"Kang, W., Lin, L., Zhang, B., Shen, X. & Wu, S. Alzheimer\u2019s Disease Neuroimaging I: Multi-model and multi-slice ensemble learning architecture based on 2D convolutional neural networks for Alzheimer\u2019s disease diagnosis. Comput. Biol. Med. 136, 104678 (2021).","journal-title":"Comput. Biol. Med."},{"key":"33055_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103565","volume":"75","author":"Z Kong","year":"2022","unstructured":"Kong, Z. et al. Multi-modal data Alzheimer\u2019s disease detection based on 3D convolution. Biomed. Signal Process. Control 75, 103565 (2022).","journal-title":"Biomed. Signal Process. Control"},{"key":"33055_CR16","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.jneumeth.2019.05.006","volume":"323","author":"F Li","year":"2019","unstructured":"Li, F. & Liu, M. A hybrid convolutional and recurrent neural network for hippocampus analysis in Alzheimer\u2019s disease. J. Neurosci. Methods 323, 108\u2013118 (2019).","journal-title":"J. Neurosci. Methods"},{"issue":"5","key":"33055_CR17","doi-asserted-by":"publisher","first-page":"2330","DOI":"10.1007\/s11682-020-00427-y","volume":"15","author":"A Li","year":"2021","unstructured":"Li, A. et al. Hippocampal shape and asymmetry analysis by cascaded convolutional neural networks for Alzheimer\u2019s disease diagnosis. Brain Imaging Behav. 15(5), 2330\u20132339 (2021).","journal-title":"Brain Imaging Behav."},{"key":"33055_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2019.116459","volume":"208","author":"M Liu","year":"2020","unstructured":"Liu, M. et al. A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer\u2019s disease. Neuroimage 208, 116459 (2020).","journal-title":"Neuroimage"},{"key":"33055_CR19","doi-asserted-by":"crossref","unstructured":"Huang, Z., Sun, M., & Guo, C. Automatic diagnosis of Alzheimer's disease and mild cognitive impairment based on CNN\u2009+\u2009SVM networks with end-to-end training. Comput. Intell. Neurosci. 9121770 (2021).","DOI":"10.1155\/2021\/9121770"},{"key":"33055_CR20","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, F., Yan, H., Wang, K., & Ma, Y., Alzheimer's Disease Neuroimaging I, et al. A multi-model deep convolutional neural network for automatic hippocampus segmentation and classification in Alzheimer's disease. Neuroimage. 208, 116459 (2020).","DOI":"10.1016\/j.neuroimage.2019.116459"},{"key":"33055_CR21","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., & Ozair, S., et al. Generative adversarial networks (2014). arXiv:abs\/1406.2661."},{"issue":"1","key":"33055_CR22","volume":"7","author":"CJ Weber","year":"2021","unstructured":"Weber, C. J. et al. The Worldwide Alzheimer\u2019s Disease Neuroimaging Initiative: ADNI-3 updates and global perspectives. Alzheimers Dement (N Y). 7(1), e12226 (2021).","journal-title":"Alzheimers Dement (N Y)."},{"key":"33055_CR23","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1186\/1741-7015-9-101","volume":"9","author":"PS Aisen","year":"2011","unstructured":"Aisen, P. S. Q&A: The Alzheimer\u2019s disease neuroimaging initiative. BMC Med. 9, 101 (2011).","journal-title":"BMC Med."},{"key":"33055_CR24","unstructured":"Radford, A., Metz, L., & Chintala, S. J. C. Unsupervised representation learning with deep convolutional generative adversarial networks (2016). arXiv:abs\/1511.06434."},{"key":"33055_CR25","doi-asserted-by":"publisher","first-page":"220","DOI":"10.3389\/fnagi.2019.00220","volume":"11","author":"T Jo","year":"2019","unstructured":"Jo, T., Nho, K. & Saykin, A. J. Deep learning in Alzheimer\u2019s disease: Diagnostic classification and prognostic prediction using neuroimaging data. Front Aging Neurosci. 11, 220 (2019).","journal-title":"Front Aging Neurosci."},{"key":"33055_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.compmedimag.2019.01.005","volume":"73","author":"R Cui","year":"2019","unstructured":"Cui, R. & Liu, M. Alzheimer\u2019s disease neuroimaging initiative: RNN-based longitudinal analysis for diagnosis of Alzheimer\u2019s disease. Comput. Med. Imag. Graph. 73, 1\u201310 (2019).","journal-title":"Comput. Med. Imag. Graph."},{"key":"33055_CR27","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.626154","volume":"14","author":"J Hu","year":"2020","unstructured":"Hu, J. et al. Deep learning-based classification and voxel-based visualization of frontotemporal dementia and Alzheimer\u2019s disease. Front. Neurosci. 14, 626154 (2020).","journal-title":"Front. Neurosci."},{"key":"33055_CR28","first-page":"1770","volume":"912","author":"Z Huang","year":"2021","unstructured":"Huang, Z., Sun, M. & Guo, C. Automatic diagnosis of Alzheimer\u2019s disease and mild cognitive impairment based on CNN + SVM networks with end-to-end training. Comput. Intell. Neurosci. 912, 1770 (2021).","journal-title":"Comput. Intell. Neurosci."},{"key":"33055_CR29","doi-asserted-by":"publisher","first-page":"646013","DOI":"10.3389\/fnins.2021.646013","volume":"15","author":"W Lin","year":"2021","unstructured":"Lin, W. et al. Alzheimer\u2019s Disease Neuroimaging Initiative: Bidirectional mapping of brain MRI and PET with 3D reversible GAN for the diagnosis of alzheimer\u2019s disease. Front. Neurosci. 15, 646013 (2021).","journal-title":"Front. Neurosci."},{"key":"33055_CR30","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1016\/j.media.2017.10.005","volume":"43","author":"M Liu","year":"2018","unstructured":"Liu, M., Zhang, J., Adeli, E. & Shen, D. Landmark-based deep multi-instance learning for brain disease diagnosis. Med. Image Anal. 43, 157\u2013168 (2018).","journal-title":"Med. Image Anal."},{"issue":"2","key":"33055_CR31","doi-asserted-by":"publisher","first-page":"254","DOI":"10.3390\/brainsci13020254","volume":"13","author":"X Shen","year":"2023","unstructured":"Shen, X., Lin, L., Xu, X. & Wu, S. Effects of patchwise sampling strategy to three-dimensional convolutional neural network-based Alzheimer\u2019s disease classification. Brain Sci. 13(2), 254 (2023).","journal-title":"Brain Sci."},{"key":"33055_CR32","doi-asserted-by":"publisher","first-page":"5665","DOI":"10.1109\/JBHI.2022.3197331","volume":"26","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Zhou, Y., Zeng, W., Qian, Q. & Song, M. An attention-based 3D CNN with multi-scale integration block for Alzheimer\u2019s disease classification. IEEE J. Biomed. Health Inform. 26, 5665\u20135673 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"33055_CR33","doi-asserted-by":"publisher","first-page":"3338","DOI":"10.21037\/qims-21-91","volume":"11","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z. et al. THAN: task-driven hierarchical attention network for the diagnosis of mild cognitive impairment and Alzheimer\u2019s disease. Quant. Imaging Med. Surg. 11, 3338\u20133354 (2021).","journal-title":"Quant. Imaging Med. Surg."},{"key":"33055_CR34","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001779","volume":"12","author":"C Sudlow","year":"2015","unstructured":"Sudlow, C. et al. UK biobank: An open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med. 12, e1001779 (2015).","journal-title":"PLoS Med."},{"key":"33055_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5334\/ojb.23","volume":"4","author":"J Manni\u00ebn","year":"2017","unstructured":"Manni\u00ebn, J. et al. The Parelsnoer Institute: A National Network of Standardized Clinical Biobanks in the Netherlands. Open Journal of Bioresources. 4, 1 (2017).","journal-title":"Open Journal of Bioresources."},{"key":"33055_CR36","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1017\/S1041610209009405","volume":"21","author":"KA Ellis","year":"2009","unstructured":"Ellis, K. A. et al. The Australian Imaging, Biomarkers and Lifestyle (AIBL) study of aging: methodology and baseline characteristics of 1112 individuals recruited for a longitudinal study of Alzheimer\u2019s disease. Int. Psychogeriatr. 21, 672\u2013687 (2009).","journal-title":"Int. Psychogeriatr."},{"key":"33055_CR37","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., Xie, H., Lau, R. Y. K., & Wang, Z., & Smolley, S.P. Least squares generative adversarial networks. In 2017 IEEE International Conference on Computer Vision (ICCV) 2017.2813\u201321.","DOI":"10.1109\/ICCV.2017.304"},{"key":"33055_CR38","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L.J.A. Wasserstein GAN (2017). arXiv:abs\/1701.07875."},{"key":"33055_CR39","unstructured":"Kumar, R., Goyal, A., Courville, A. C., & Bengio, Y. J. A. Maximum entropy generators for energy-based models (2019). arXiv:abs\/1901.08508."},{"key":"33055_CR40","doi-asserted-by":"crossref","unstructured":"Xu, X., Lin, L., Sun, S., & Wu, S. A review of the application of three-dimensional convolutional neural networks for the diagnosis of Alzheimer's disease using neuroimaging. Rev. Neurosci. (2023) (In Press).","DOI":"10.1515\/revneuro-2022-0122"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33055-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33055-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33055-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T19:03:39Z","timestamp":1680894219000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33055-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,7]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["33055"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-33055-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,7]]},"assertion":[{"value":"29 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"5750"}}