{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T10:12:52Z","timestamp":1792404772697,"version":"4.4.0"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1UL1TR001430"],"award-info":[{"award-number":["1UL1TR001430"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientist Development","award":["17SDG33670323"],"award-info":[{"award-number":["17SDG33670323"]}]},{"DOI":"10.13039\/100000968","name":"American Heart Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000968","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hariri Research Award"},{"name":"Hariri Institute for Computing and Computational Science & Engineering at Boston University"},{"name":"Framingham Heart Study\u2019s National Heart, Lung and Blood Institute","award":["N01-HC-25195"],"award-info":[{"award-number":["N01-HC-25195"]}]},{"name":"Framingham Heart Study\u2019s National Heart, Lung and Blood Institute","award":["HHSN268201500001I"],"award-info":[{"award-number":["HHSN268201500001I"]}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R56-AG062109"],"award-info":[{"award-number":["R56-AG062109"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["AG008122"],"award-info":[{"award-number":["AG008122"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01-AG016495"],"award-info":[{"award-number":["R01-AG016495"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01-AG033040"],"award-info":[{"award-number":["R01-AG033040"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Boston University\u2019s Affinity Research Collaboratives"},{"name":"Boston University Alzheimer\u2019s Disease Center","award":["P30-AG013846"],"award-info":[{"award-number":["P30-AG013846"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Alzheimer\u2019s disease is the primary cause of dementia worldwide, with an increasing morbidity burden that may outstrip diagnosis and management capacity as the population ages. Current methods integrate patient history, neuropsychological testing and MRI to identify likely cases, yet effective practices remain variably applied and lacking in sensitivity and specificity. Here we report an interpretable deep learning strategy that delineates unique Alzheimer\u2019s disease signatures from multimodal inputs of MRI, age, gender, and Mini-Mental State Examination score. Our framework linked a fully convolutional network, which constructs high resolution maps of disease probability from local brain structure to a multilayer perceptron and generates precise, intuitive visualization of individual Alzheimer\u2019s disease risk en route to accurate diagnosis. The model was trained using clinically diagnosed Alzheimer\u2019s disease and cognitively normal subjects from the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) dataset (n\u2009=\u2009417) and validated on three independent cohorts: the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) (n\u2009=\u2009382), the Framingham Heart Study (n\u2009=\u2009102), and the National Alzheimer\u2019s Coordinating Center (NACC) (n\u2009=\u2009582). Performance of the model that used the multimodal inputs was consistent across datasets, with mean area under curve values of 0.996, 0.974, 0.876 and 0.954 for the ADNI study, AIBL, Framingham Heart Study and NACC datasets, respectively. Moreover, our approach exceeded the diagnostic performance of a multi-institutional team of practicing neurologists (n\u2009=\u200911), and high-risk cerebral regions predicted by the model closely tracked post-mortem histopathological findings. This framework provides a clinically adaptable strategy for using routinely available imaging techniques such as MRI to generate nuanced neuroimaging signatures for Alzheimer\u2019s disease diagnosis, as well as a generalizable approach for linking deep learning to pathophysiological processes in human disease.<\/jats:p>","DOI":"10.1093\/brain\/awaa137","type":"journal-article","created":{"date-parts":[[2020,4,8]],"date-time":"2020-04-08T15:12:39Z","timestamp":1586358759000},"page":"1920-1933","source":"Crossref","is-referenced-by-count":457,"title":["Development and validation of an interpretable deep learning framework for Alzheimer\u2019s disease classification"],"prefix":"10.1093","volume":"143","author":[{"given":"Shangran","family":"Qiu","sequence":"first","affiliation":[{"name":"Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA"},{"name":"College of Arts and Sciences, Boston University, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prajakta S","family":"Joshi","sequence":"first","affiliation":[{"name":"Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew I","family":"Miller","sequence":"first","affiliation":[{"name":"Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chonghua","family":"Xue","sequence":"first","affiliation":[{"name":"Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Arts and Sciences, Boston University, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cody","family":"Karjadi","sequence":"first","affiliation":[{"name":"The Framingham Heart Study, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gary H","family":"Chang","sequence":"first","affiliation":[{"name":"Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anant S","family":"Joshi","sequence":"first","affiliation":[{"name":"College of Computing, Georgia Institute of Technology, Atlanta, GA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brigid","family":"Dwyer","sequence":"first","affiliation":[{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuhan","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michelle","family":"Kaku","sequence":"first","affiliation":[{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Neurology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7367-5410","authenticated-orcid":false,"given":"Yazan J","family":"Alderazi","sequence":"first","affiliation":[{"name":"Department of Neurology, University of Texas Health Science Center, Houston, TX, USA"},{"name":"Department of Neurology, Texas Tech University Health Sciences Center, Lubbock, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arun","family":"Swaminathan","sequence":"first","affiliation":[{"name":"Department of Neurological Sciences, College of Medicine, University of Nebraska Medical Center, Omaha, NE, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7293-5556","authenticated-orcid":false,"given":"Sachin","family":"Kedar","sequence":"first","affiliation":[{"name":"Department of Neurological Sciences, College of Medicine, University of Nebraska Medical Center, Omaha, NE, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marie-Helene","family":"Saint-Hilaire","sequence":"first","affiliation":[{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanford H","family":"Auerbach","sequence":"first","affiliation":[{"name":"The Framingham Heart Study, Boston University School of Medicine, Boston, MA, USA"},{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Neurology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E Alton","family":"Sartor","sequence":"first","affiliation":[{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rhoda","family":"Au","sequence":"first","affiliation":[{"name":"Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, USA"},{"name":"The Framingham Heart Study, Boston University School of Medicine, Boston, MA, USA"},{"name":"Department of Neurology, Boston University School of Medicine, Boston, MA, USA"},{"name":"Department of Epidemiology, Boston University School of Public Health, Boston, MA, USA"},{"name":"Boston University Alzheimer\u2019s Disease Center, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5312-8644","authenticated-orcid":false,"given":"Vijaya B","family":"Kolachalama","sequence":"first","affiliation":[{"name":"Section of Computational Biomedicine, Department of Medicine, Boston University School of Medicine, Boston, MA, USA"},{"name":"Boston University Alzheimer\u2019s Disease Center, Boston, MA, USA"},{"name":"Whitaker Cardiovascular Institute, Boston University School of Medicine, Boston, MA, USA"},{"name":"Hariri Institute for Computing and Computational Science & Engineering, Boston University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,5,1]]},"reference":[{"key":"2020063007035270600_awaa137-B1","doi-asserted-by":"crossref","first-page":"673","DOI":"10.2174\/156720512801322609","article-title":"The Framingham Brain Donation Program: neuropathology along the cognitive continuum","volume":"9","author":"Au","year":"2012","journal-title":"Curr Alzheimer Res"},{"key":"2020063007035270600_awaa137-B2","doi-asserted-by":"crossref","first-page":"1521","DOI":"10.1212\/01.wnl.0000277459.83543.99","article-title":"The significance of medial temporal lobe atrophy: a postmortem MRI study in the very old","volume":"69","author":"Barkhof","year":"2007","journal-title":"Neurology"},{"key":"2020063007035270600_awaa137-B3","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1097\/NEN.0b013e31824b211b","article-title":"Accuracy of the clinical diagnosis of Alzheimer disease at National Institute on Aging Alzheimer Disease Centers, 2005-2010","volume":"71","author":"Beach","year":"2012","journal-title":"J Neuropathol Exp Neurol"},{"key":"2020063007035270600_awaa137-B4","first-page":"270","article-title":"The National Alzheimer\u2019s Coordinating Center (NACC) Database: an Alzheimer disease database","volume":"18","author":"Beekly","year":"2004","journal-title":"Alzheimer Dis Assoc Disord"},{"key":"2020063007035270600_awaa137-B5","doi-asserted-by":"crossref","first-page":"59","DOI":"10.2967\/jnumed.111.096578","article-title":"Effectiveness and safety of 18F-FDG PET in the evaluation of dementia: a review of the recent literature","volume":"53","author":"Bohnen","year":"2012","journal-title":"J Nucl Med"},{"key":"2020063007035270600_awaa137-B6","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1038\/538020a","article-title":"Can we open the black box of AI?","volume":"538","author":"Castelvecchi","year":"2016","journal-title":"Nature"},{"key":"2020063007035270600_awaa137-B7","doi-asserted-by":"crossref","first-page":"1559","DOI":"10.1038\/s41591-018-0177-5","article-title":"Classification and mutation prediction from non-small cell lung cancer histopathology images using deep learning","volume":"24","author":"Coudray","year":"2018","journal-title":"Nat Med"},{"key":"2020063007035270600_awaa137-B8","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.jalz.2010.03.009","article-title":"Addressing population aging and Alzheimer\u2019s disease through the Australian imaging biomarkers and lifestyle study: collaboration with the Alzheimer\u2019s Disease Neuroimaging Initiative","volume":"6","author":"Ellis","year":"2010","journal-title":"Alzheimers Dement"},{"key":"2020063007035270600_awaa137-B9","doi-asserted-by":"crossref","first-page":"774","DOI":"10.1016\/j.neuroimage.2012.01.021","article-title":"FreeSurfer","volume":"62","author":"Fischl","year":"2012","journal-title":"Neuroimage"},{"key":"2020063007035270600_awaa137-B10","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1038\/nrneurol.2009.215","article-title":"The clinical use of structural MRI in Alzheimer disease","volume":"6","author":"Frisoni","year":"2010","journal-title":"Nat Rev Neurol"},{"key":"2020063007035270600_awaa137-B11","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1136\/jnnp-2013-306285","article-title":"An algorithmic approach to structural imaging in dementia","volume":"85","author":"Harper","year":"2014","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"2020063007035270600_awaa137-B12","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1001\/jama.2018.11100","article-title":"Deep learning-a technology with the potential to transform health care","volume":"320","author":"Hinton","year":"2018","journal-title":"JAMA"},{"key":"2020063007035270600_awaa137-B13","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/S1474-4422(12)70291-0","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":"2020063007035270600_awaa137-B14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2020063007035270600_awaa137-B16","doi-asserted-by":"crossref","first-page":"5697","DOI":"10.1038\/s41598-018-22871-z","article-title":"Alzheimer\u2019s disease neuroimaging I. Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer\u2019s disease using structural MR and FDG-PET images","volume":"8","author":"Lu","year":"2018","journal-title":"Sci Rep"},{"key":"2020063007035270600_awaa137-B17","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1002\/sim.1743","article-title":"Managing and analysing data from a large-scale study on Framingham Offspring relating brain structure to cognitive function","volume":"23","author":"Massaro","year":"2004","journal-title":"Stat Med"},{"key":"2020063007035270600_awaa137-B18","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1016\/j.jalz.2018.12.001","article-title":"Predicting diagnosis and cognition with (18)F-AV-1451 tau PET and structural MRI in Alzheimer\u2019s disease","volume":"15","author":"Mattsson","year":"2019","journal-title":"Alzheimers Dement"},{"key":"2020063007035270600_awaa137-B19","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1016\/j.jalz.2011.03.005","article-title":"The diagnosis of dementia due to Alzheimer\u2019s disease: recommendations from the National Institute on Aging-Alzheimer\u2019s Association workgroups on diagnostic guidelines for Alzheimer\u2019s disease","volume":"7","author":"McKhann","year":"2011","journal-title":"Alzheimers Dement"},{"key":"2020063007035270600_awaa137-B20","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/S1474-4422(04)00853-1","article-title":"PET imaging of amyloid in Alzheimer\u2019s disease","volume":"3","author":"Nordberg","year":"2004","journal-title":"Lancet Neurol"},{"key":"2020063007035270600_awaa137-B21","doi-asserted-by":"crossref","first-page":"e601","DOI":"10.1212\/WNL.0000000000006875","article-title":"Associations between tau, Abeta, and cortical thickness with cognition in Alzheimer disease","volume":"92","author":"Ossenkoppele","year":"2019","journal-title":"Neurology"},{"key":"2020063007035270600_awaa137-B22","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1212\/WNL.0b013e3181cb3e25","article-title":"Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI): clinical characterization","volume":"74","author":"Petersen","year":"2010","journal-title":"Neurology"},{"key":"2020063007035270600_awaa137-B23","doi-asserted-by":"crossref","first-page":"737","DOI":"10.1016\/j.dadm.2018.08.013","article-title":"Fusion of deep learning models of MRI scans, Mini-Mental State Examination, and logical memory test enhances diagnosis of mild cognitive impairment","volume":"10","author":"Qiu","year":"2018","journal-title":"Alzheimer's Dementia"},{"key":"2020063007035270600_awaa137-B24","doi-asserted-by":"crossref","first-page":"1899","DOI":"10.1212\/WNL.0b013e3181c3f293","article-title":"Age, Alzheimer disease, and brain structure","volume":"73","author":"Raji","year":"2009","journal-title":"Neurology"},{"key":"2020063007035270600_awaa137-B25","doi-asserted-by":"crossref","first-page":"505","DOI":"10.1016\/S0140-6736(15)01124-1","article-title":"Alzheimer\u2019s disease","volume":"388","author":"Scheltens","year":"2016","journal-title":"Lancet"},{"key":"2020063007035270600_awaa137-B682694","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"Shelhamer","year":"2017","journal-title":". Convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell"},{"key":"2020063007035270600_awaa137-B26","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat Med"},{"key":"2020063007035270600_awaa137-B27","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1212\/01.wnl.0000194240.47892.4d","article-title":"Hippocampal atrophy in Alzheimer disease: age matters","volume":"66","author":"van de Pol","year":"2006","journal-title":"Neurology"},{"key":"2020063007035270600_awaa137-B28","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Mach Learn"},{"key":"2020063007035270600_awaa137-B29","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1016\/S1474-4422(12)70200-4","article-title":"Neuroimaging correlates of pathologically defined subtypes of Alzheimer\u2019s disease: a case-control study","volume":"11","author":"Whitwell","year":"2012","journal-title":"Lancet Neurol"}],"container-title":["Brain"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/brain\/article-pdf\/143\/6\/1920\/33446057\/awaa137.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/brain\/article-pdf\/143\/6\/1920\/33446057\/awaa137.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,7]],"date-time":"2021-03-07T18:27:40Z","timestamp":1615141660000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/brain\/article\/143\/6\/1920\/5827821"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,1]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2020,5,1]]},"published-print":{"date-parts":[[2020,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/brain\/awaa137","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/832519","asserted-by":"object"}]},"ISSN":["0006-8950","1460-2156"],"issn-type":[{"value":"0006-8950","type":"print"},{"value":"1460-2156","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,6]]},"published":{"date-parts":[[2020,5,1]]}}}