{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T15:46:56Z","timestamp":1768837616559,"version":"3.49.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"S6","license":[{"start":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:00:00Z","timestamp":1670371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:00:00Z","timestamp":1670371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001858","name":"VINNOVA","doi-asserted-by":"publisher","award":["Grant 2017-02447"],"award-info":[{"award-number":["Grant 2017-02447"]}],"id":[{"id":"10.13039\/501100001858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>In recent years, neuroimaging with deep learning (DL) algorithms have made remarkable advances in the diagnosis of neurodegenerative disorders. However, applying DL in different medical domains is usually challenged by lack of labeled data. To address this challenge, transfer learning (TL) has been applied to use state-of-the-art convolution neural networks pre-trained on natural images. Yet, there are differences in characteristics between medical and natural images, also image classification and targeted medical diagnosis tasks. The purpose of this study is to investigate the performance of specialized and TL in the classification of neurodegenerative disorders using 3D volumes of 18F-FDG-PET brain scans.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Results show that TL models are suboptimal for classification of neurodegenerative disorders, especially when the objective is to separate more than two disorders. Additionally, specialized CNN model provides better interpretations of predicted diagnosis.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>TL can indeed lead to superior performance on binary classification in timely and data efficient manner, yet for detecting more than a single disorder, TL models do not perform well. Additionally, custom 3D model performs comparably to TL models for binary classification, and interestingly perform better for diagnosis of multiple disorders. The results confirm the superiority of the custom 3D-CNN in providing better explainable model compared to TL adopted ones.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12911-022-02054-7","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T10:03:59Z","timestamp":1670407439000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Adopting transfer learning for neuroimaging: a comparative analysis with a custom 3D convolution neural network model"],"prefix":"10.1186","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0264-8762","authenticated-orcid":false,"given":"Amira","family":"Soliman","sequence":"first","affiliation":[]},{"given":"Jose R.","family":"Chang","sequence":"additional","affiliation":[]},{"given":"Kobra","family":"Etminani","sequence":"additional","affiliation":[]},{"given":"Stefan","family":"Byttner","sequence":"additional","affiliation":[]},{"given":"Anette","family":"Davidsson","sequence":"additional","affiliation":[]},{"given":"Bego\u00f1a","family":"Mart\u00ednez-Sanchis","sequence":"additional","affiliation":[]},{"given":"Valle","family":"Camacho","sequence":"additional","affiliation":[]},{"given":"Matteo","family":"Bauckneht","sequence":"additional","affiliation":[]},{"given":"Roxana","family":"Stegeran","sequence":"additional","affiliation":[]},{"given":"Marcus","family":"Ressner","sequence":"additional","affiliation":[]},{"given":"Marc","family":"Agudelo-Cifuentes","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Chincarini","sequence":"additional","affiliation":[]},{"given":"Matthias","family":"Brendel","sequence":"additional","affiliation":[]},{"given":"Axel","family":"Rominger","sequence":"additional","affiliation":[]},{"given":"Rose","family":"Bruffaerts","sequence":"additional","affiliation":[]},{"given":"Rik","family":"Vandenberghe","sequence":"additional","affiliation":[]},{"given":"Milica G.","family":"Kramberger","sequence":"additional","affiliation":[]},{"given":"Maja","family":"Trost","sequence":"additional","affiliation":[]},{"given":"Nicolas","family":"Nicastro","sequence":"additional","affiliation":[]},{"given":"Giovanni B.","family":"Frisoni","sequence":"additional","affiliation":[]},{"given":"Afina W.","family":"Lemstra","sequence":"additional","affiliation":[]},{"given":"Bart N. M. van","family":"Berckel","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Pilotto","sequence":"additional","affiliation":[]},{"given":"Alessandro","family":"Padovani","sequence":"additional","affiliation":[]},{"given":"Silvia","family":"Morbelli","sequence":"additional","affiliation":[]},{"given":"Dag","family":"Aarsland","sequence":"additional","affiliation":[]},{"given":"Flavio","family":"Nobili","sequence":"additional","affiliation":[]},{"given":"Valentina","family":"Garibotto","sequence":"additional","affiliation":[]},{"name":"the Alzheimer\u2019s Disease Neuroimaging Initiative","sequence":"additional","affiliation":[]},{"given":"Miguel","family":"Ochoa-Figueroa","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,12,7]]},"reference":[{"issue":"9503","key":"2054_CR1","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1016\/S0140-6736(05)67889-0","volume":"366","author":"CP Ferri","year":"2005","unstructured":"Ferri CP, Prince M, Brayne C, Brodaty H, Fratiglioni L, Ganguli M, Hall K, Hasegawa K, Hendrie H, Huang Y, et al. Global prevalence of dementia: a Delphi consensus study. The lancet. 2005;366(9503):2112\u20137.","journal-title":"The lancet"},{"issue":"S1","key":"2054_CR2","doi-asserted-by":"publisher","first-page":"S83","DOI":"10.1017\/cjn.2016.2","volume":"43","author":"DB Hogan","year":"2016","unstructured":"Hogan DB, Fiest KM, Roberts JI, Maxwell CJ, Dykeman J, Pringsheim T, Steeves T, Smith EE, Pearson D, Jett\u00e9 N. The prevalence and incidence of dementia with lewy bodies: a systematic review. Can J Neurol Sci. 2016;43(S1):S83\u201395.","journal-title":"Can J Neurol Sci"},{"issue":"9","key":"2054_CR3","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1001\/archneurol.2009.106","volume":"66","author":"ST Farias","year":"2009","unstructured":"Farias ST, Mungas D, Reed BR, Harvey D, DeCarli C. Progression of mild cognitive impairment to dementia in clinic-vs community-based cohorts. Arch Neurol. 2009;66(9):1151\u20137.","journal-title":"Arch Neurol"},{"key":"2054_CR4","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/RBME.2018.2886237","volume":"12","author":"MR Ahmed","year":"2018","unstructured":"Ahmed MR, Zhang Y, Feng Z, Lo B, Inan OT, Liao H. Neuroimaging and machine learning for dementia diagnosis: recent advancements and future prospects. IEEE Rev Biomed Eng. 2018;12:19\u201333.","journal-title":"IEEE Rev Biomed Eng"},{"key":"2054_CR5","doi-asserted-by":"crossref","unstructured":"Nobili F, Arbizu J, Bouwman F, Drzezga A, Agosta F, Nestor P, Walker Z, Boccardi M, E.-E. T.\u00a0F. for the Prescription of FDG-PET\u00a0for Dementing Neurodegenerative\u00a0Disorders, Festari C, et\u00a0al. European association of nuclear medicine and european academy of neurology recommendations for the use of brain 18f-fluorodeoxyglucose positron emission tomography in neurodegenerative cognitive impairment and dementia: Delphi consensus. European J Neurol. 2018; 25\u00a0(10) 1201\u20131217.","DOI":"10.1111\/ene.13728"},{"key":"2054_CR6","doi-asserted-by":"publisher","first-page":"77131","DOI":"10.1109\/ACCESS.2020.2989396","volume":"8","author":"S Al-Shoukry","year":"2020","unstructured":"Al-Shoukry S, Rassem TH, Makbol NM. Alzheimer\u2019s diseases detection by using deep learning algorithms: a mini-review. IEEE Access. 2020;8:77131\u201341.","journal-title":"IEEE Access"},{"key":"2054_CR7","doi-asserted-by":"crossref","unstructured":"Ding Y, Sohn JH, Kawczynski MG,Trivedi H, Harnish R, Jenkins NW, Lituiev D, Copeland TP, Aboian MS, Mari\u00a0Aparici C, et\u00a0al. A deep learning model to predict a diagnosis of alzheimer disease by using 18f-fdg pet of the brain, Radiology. 2019;290\u00a0(2) 456\u2013464.","DOI":"10.1148\/radiol.2018180958"},{"key":"2054_CR8","doi-asserted-by":"crossref","unstructured":"Singh S, Srivastava A, Mi L, Caselli RJ, Chen K, Goradia D, Reiman EM, Wang Y. Deep-learning-based classification of fdg-pet data for alzheimer\u2019s disease categories, in: 13th international conference on medical information processing and analysis, Vol. 10572, International Society for Optics and Photonics, 2017; p. 105720J.","DOI":"10.1117\/12.2294537"},{"issue":"2","key":"2054_CR9","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s00259-019-04538-7","volume":"47","author":"H Choi","year":"2020","unstructured":"Choi H, Kim YK, Yoon EJ, Lee J-Y, Lee DS. Cognitive signature of brain fdg pet based on deep learning: domain transfer from alzheimer\u2019s disease to parkinson\u2019s disease. Eur J Nucl Med Mol Imaging. 2020;47(2):403\u201312.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"1","key":"2054_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-016-0043-6","volume":"3","author":"K Weiss","year":"2016","unstructured":"Weiss K, Khoshgoftaar TM, Wang D. A survey of transfer learning. J of Big data. 2016;3(1):1\u201340.","journal-title":"J of Big data"},{"issue":"13","key":"2054_CR11","doi-asserted-by":"publisher","first-page":"4523","DOI":"10.3390\/app10134523","volume":"10","author":"L Alzubaidi","year":"2020","unstructured":"Alzubaidi L, Fadhel MA, Al-Shamma O, Zhang J, Santamar\u00eda J, Duan Y, Oleiwi SR. Towards a better understanding of transfer learning for medical imaging: a case study. Appl Sci. 2020;10(13):4523.","journal-title":"Appl Sci"},{"key":"2054_CR12","doi-asserted-by":"crossref","unstructured":"Zhang Y, Davison BD. Impact of imagenet model selection on domain adaptation, In: proceedings of the IEEE\/CVF winter conference on applications of computer vision workshops, 2020;pp. 173\u2013182.","DOI":"10.1109\/WACVW50321.2020.9096945"},{"key":"2054_CR13","doi-asserted-by":"crossref","unstructured":"Kornblith S, Shlens J, Le QV. Do better imagenet models transfer better?, In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2019;pp. 2661\u20132671.","DOI":"10.1109\/CVPR.2019.00277"},{"issue":"11","key":"2054_CR14","doi-asserted-by":"publisher","first-page":"2645","DOI":"10.3390\/s19112645","volume":"19","author":"M Maqsood","year":"2019","unstructured":"Maqsood M, Nazir F, Khan U, Aadil F, Jamal H, Mehmood I, Song O-Y. Transfer learning assisted classification and detection of alzheimer\u2019s disease stages using 3d mri scans. Sensors. 2019;19(11):2645.","journal-title":"Sensors"},{"key":"2054_CR15","doi-asserted-by":"crossref","unstructured":"Nobili F, Arbizu J, Bouwman F, Drzezga A, Agosta F, Nestor P, Walker Z, Boccardi M. EANM-EAN Task Force for the Prescription of FDG-PET for Dementing Neurodegenerative Disorders. European Association of Nuclear Medicine and European Academy of Neurology recommendations for the use of brain 18 F-fluorodeoxyglucose positron emission tomography in neurodegenerative cognitive impairment and dementia: Delphi consensus. Eur J Neurol. 2018;25(10):1201\u201317.","DOI":"10.1111\/ene.13728"},{"key":"2054_CR16","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions, In: proceedings of the IEEE conference on computer vision and pattern recognition, 2015;pp. 1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2054_CR17","unstructured":"Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556."},{"key":"2054_CR18","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition, In: proceedings of the IEEE conference on computer vision and pattern recognition, 2016;pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"2","key":"2054_CR19","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1007\/s00259-021-05483-0","volume":"49","author":"K Etminani","year":"2022","unstructured":"Etminani K, Soliman A, Davidsson A, Chang J, Mart\u00ednez-Sanchis B, Byttner S, Camacho V, Bauckneht M, Stegeran R, Ressner M, et al. A 3d deep learning model to predict the diagnosis of dementia with lewy bodies, alzheimer\u2019s disease and mild cognitive impairment using brain 18f-fdg pet. Eur J Nucl Med Mol Imaging. 2022;49(2):563\u201384.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"2054_CR20","unstructured":"European dlb (edlb) consortium with its core laboratory at genoa, italy, https:\/\/www.ge.infn.it\/wordpress\/?page_id=77, [Online; accessed 2022-05-09]."},{"issue":"3","key":"2054_CR21","doi-asserted-by":"publisher","first-page":"787","DOI":"10.3233\/JAD-161109","volume":"57","author":"MG Kramberger","year":"2017","unstructured":"Kramberger MG, Auestad B, Garcia-Ptacek S, Abdelnour C, Olmo JG, Walker Z, Lemstra AW, Londos E, Blanc F, Bonanni L, et al. Long-term cognitive decline in dementia with lewy bodies in a large multicenter, international cohort. J Alzheimers Dis. 2017;57(3):787\u201395.","journal-title":"J Alzheimers Dis"},{"key":"2054_CR22","doi-asserted-by":"crossref","unstructured":"McKeith IG, Dickson DW, Lowe J, Emre M, O\u2019brien J, Feldman H, Cummings J, DudaJ, Lippa C, Perry E, et\u00a0al. Diagnosis and management of dementia with lewy bodies: third report of the dlb consortium, Neurology. 2005;65\u00a0(12) 1863\u20131872.","DOI":"10.1212\/wnl.65.12.1992-a"},{"key":"2054_CR23","unstructured":"Alzheimer\u2019s disease neuroimaging initiative, http:\/\/adni.loni.usc.edu\/, [Online; accessed 2022-05-09]."},{"issue":"4","key":"2054_CR24","doi-asserted-by":"publisher","first-page":"869","DOI":"10.1016\/j.nic.2005.09.008","volume":"15","author":"SG Mueller","year":"2005","unstructured":"Mueller SG, Weiner MW, Thal LJ, Petersen RC, Jack C, Jagust W, Trojanowski JQ, Toga AW, Beckett L. The alzheimer\u2019s disease neuroimaging initiative. Neuroimaging Clin N Am. 2005;15(4):869.","journal-title":"Neuroimaging Clin N Am"},{"key":"2054_CR25","unstructured":"Papers with code: image classification on imagenet, https:\/\/paperswithcode.com\/sota\/image-classification-on-imagenet, [Online; accessed 2022-05-09]."},{"issue":"3","key":"2054_CR26","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1148\/rg.343135065","volume":"34","author":"RK Brown","year":"2014","unstructured":"Brown RK, Bohnen NI, Wong KK, Minoshima S, Frey KA. Brain pet in suspected dementia: patterns of altered fdg metabolism. Radiographics. 2014;34(3):684\u2013701.","journal-title":"Radiographics"},{"issue":"1","key":"2054_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0276-2","volume":"6","author":"SS Yadav","year":"2019","unstructured":"Yadav SS, Jadhav SM. Deep convolutional neural network based medical image classification for disease diagnosis. J Big Data. 2019;6(1):1\u201318.","journal-title":"J Big Data"},{"key":"2054_CR28","unstructured":"Raghu M, Zhang C, Kleinberg J, Bengio S. Transfusion: Understanding transfer learning for medical imaging, arXiv preprint arXiv:1902.07208."},{"issue":"2","key":"2054_CR29","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1006\/nimg.1995.1012","volume":"2","author":"JC Mazziotta","year":"1995","unstructured":"Mazziotta JC, Toga AW, Evans A, Fox P, Lancaster J, et al. A probabilistic atlas of the human brain: theory and rationale for its development. Neuroimage. 1995;2(2):89\u2013101.","journal-title":"Neuroimage"},{"key":"2054_CR30","unstructured":"McInnes L, Healy J, Melville J. Umap: Uniform manifold approximation and projection for dimension reduction, arXiv preprint arXiv:1802.03426."},{"key":"2054_CR31","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","volume-title":"Computer vision - ECCV 2014","author":"MD Zeiler","year":"2014","unstructured":"Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T, editors. Computer vision - ECCV 2014. Cham: Springer International Publishing; 2014. p. 818\u201333."},{"key":"2054_CR32","unstructured":"A complete listing of adni investigators, http:\/\/adni.loni.usc.edu\/wp-content\/uploads\/how_to_apply\/ADNI_Acknowledgement_List.pdf, [Online; accessed 2022-05-09]."}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02054-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12911-022-02054-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-022-02054-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T16:06:42Z","timestamp":1704902802000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-022-02054-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,7]]},"references-count":32,"journal-issue":{"issue":"S6","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["2054"],"URL":"https:\/\/doi.org\/10.1186\/s12911-022-02054-7","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,7]]},"assertion":[{"value":"10 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 December 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This research study was conducted retrospectively using data obtained from European DLB (EDLB) Consortium. Local institutional ethics committee approvals for the retrospective analyses were available for all centers in Europe, including the transfer of fully anonymized imaging data. Regarding the data from Link\u00f6ping\u2019s University Hospital, informed consent was waived for this retrospective assessment and additionally, all patients were informed by letter that their medical data can be rendered anonymous and used for scientific purposes. All patients from the rest of the centers gave informed written consent for the imaging procedure and radiopharmaceutical application. The study has approval by the Swedish Ethical Review Authority (Etikpr\u00f6vningsmyndigheten) with approval number: 2019-00526. Part of data collection and sharing for this project was funded by the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012)","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare no conflicts of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"318"}}