{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:08:36Z","timestamp":1788934116572,"version":"build-2803163510"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T00:00:00Z","timestamp":1669593600000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000005","name":"United States Department of Defense","doi-asserted-by":"crossref","award":["W81XWH-15-1-0286"],"award-info":[{"award-number":["W81XWH-15-1-0286"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000005","name":"United States Department of Defense","doi-asserted-by":"crossref","award":["W81XWH1910534"],"award-info":[{"award-number":["W81XWH1910534"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["K23NS070891"],"award-info":[{"award-number":["K23NS070891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"crossref","award":["1R61NS113315-01"],"award-info":[{"award-number":["1R61NS113315-01"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Amgen Investigator Sponsored Study","award":["20187183"],"award-info":[{"award-number":["20187183"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,29]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Data-driven machine-learning methods on neuroimaging (e.g. MRI) are of great interest for the investigation and classification of neurological diseases. However, traditional machine learning requires domain knowledge to delineate the brain regions first, followed by feature extraction from the regions. Compared with this semi-automated approach, recently developed deep learning methods have advantages since they do not require such prior knowledge; instead, deep learning methods can automatically find features that differentiate MRIs from different cohorts. In the present study, we developed a deep learning-based classification pipeline distinguishing brain MRIs of individuals with one of three types of headaches [migraine (n = 95), acute post-traumatic headache (n = 48) and persistent post-traumatic headache (n = 49)] from those of healthy controls (n = 532) and identified the brain regions that most contributed to each classification task. Our pipeline included: (i) data preprocessing; (ii) binary classification of healthy controls versus headache type using a 3D ResNet-18; and (iii) biomarker extraction from the trained 3D ResNet-18. During the classification at the second step of our pipeline, we resolved two common issues in deep learning methods, limited training data and imbalanced samples from different categories, by incorporating a large public data set and resampling among the headache cohorts. Our method achieved the following classification accuracies when tested on independent test sets: (i) migraine versus healthy controls\u201475% accuracy, 66.7% sensitivity and 83.3% specificity; (2) acute post-traumatic headache versus healthy controls\u201475% accuracy, 66.7% sensitivity and 83.3% specificity; and (3) persistent post-traumatic headache versus healthy controls\u201491.7% accuracy, 100% sensitivity and 83.3% specificity. The most significant biomarkers identified by the classifier for migraine were caudate, caudal anterior cingulate, superior frontal, thalamus and ventral diencephalon. For acute post-traumatic headache, lateral occipital, cuneus, lingual, pericalcarine and superior parietal regions were identified as most significant biomarkers. Finally, for persistent post-traumatic headache, the most significant biomarkers were cerebellum, middle temporal, inferior temporal, inferior parietal and superior parietal. In conclusion, our study shows that the deep learning methods can automatically detect aberrations in the brain regions associated with different headache types. It does not require any human knowledge as input which significantly reduces human effort. It uncovers the great potential of deep learning methods for classification and automatic extraction of brain imaging\u2013based biomarkers for these headache types.<\/jats:p>","DOI":"10.1093\/braincomms\/fcac311","type":"journal-article","created":{"date-parts":[[2022,11,28]],"date-time":"2022-11-28T09:10:06Z","timestamp":1669626606000},"source":"Crossref","is-referenced-by-count":33,"title":["Headache classification and automatic biomarker extraction from structural MRIs using deep learning"],"prefix":"10.1093","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7145-215X","authenticated-orcid":false,"given":"Md Mahfuzur","family":"Rahman Siddiquee","sequence":"first","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University , Tempe, AZ , USA"},{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jay","family":"Shah","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University , Tempe, AZ , USA"},{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Chong","sequence":"additional","affiliation":[{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"},{"name":"Department of Neurology, Mayo Clinic , Phoenix, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simona","family":"Nikolova","sequence":"additional","affiliation":[{"name":"Department of Neurology, Mayo Clinic , Phoenix, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gina","family":"Dumkrieger","sequence":"additional","affiliation":[{"name":"Department of Neurology, Mayo Clinic , Phoenix, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoxin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University , Tempe, AZ , USA"},{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teresa","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University , Tempe, AZ , USA"},{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Todd J","family":"Schwedt","sequence":"additional","affiliation":[{"name":"ASU-Mayo Center for Innovative Imaging , Tempe, AZ , USA"},{"name":"Department of Neurology, Mayo Clinic , Phoenix, AZ , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,11,26]]},"reference":[{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1016\/j.jalz.2018.08.005","article-title":"Understanding disease progression and improving Alzheimer\u2019s disease clinical trials: Recent highlights from the Alzheimer\u2019s disease neuroimaging initiative","volume":"15","author":"Veitch","year":"2019","journal-title":"Alzheimer\u2019s Dement"},{"key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/j.neuroimage.2017.03.057","article-title":"A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer\u2019s disease and its prodromal stages","volume":"155","author":"Rathore","year":"2017","journal-title":"Neuroimage"},{"issue":"21","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"15467","DOI":"10.1007\/s11042-019-7469-8","article-title":"Deep learning based diagnosis of Parkinson\u2019s disease using convolutional neural network","volume":"79","author":"Sivaranjini","year":"2020","journal-title":"Multimed Tools Appl"},{"issue":"6","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1111\/head.12584","article-title":"Accurate classification of chronic migraine via brain magnetic resonance imaging","volume":"55","author":"Schwedt","year":"2015","journal-title":"Headache"},{"issue":"7","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1111\/head.13121","article-title":"Migraine subclassification via a data-driven automated approach using multimodality factor mixture modeling of brain structure measurements","volume":"57","author":"Schwedt","year":"2017","journal-title":"Headache"},{"key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"221","DOI":"10.3389\/fneur.2020.00221","article-title":"What we gain from machine learning studies in headache patients","volume":"11","author":"Messina","year":"2020","journal-title":"Front Neurol"},{"issue":"7553","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1093\/ehjqcco\/qcv005","article-title":"Big biomedical data and cardiovascular disease research: Opportunities and challenges","volume":"1","author":"Denaxas","year":"2015","journal-title":"Eur Hear J Qual Care Clin Outcomes"},{"issue":"11","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1980","DOI":"10.1088\/1361-6579\/aa8e1f","article-title":"High-accuracy automatic classification of Parkinsonian tremor severity using machine learning method","volume":"38","author":"Jeon","year":"2017","journal-title":"Physiol Meas"},{"issue":"8","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"440","DOI":"10.1038\/s41582-020-0377-8","article-title":"Applications of machine learning to diagnosis and treatment of neurodegenerative diseases","volume":"16","author":"Myszczynska","year":"2020","journal-title":"Nat Rev Neurol"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/s10916-019-1475-2","article-title":"A deep learning approach for automated diagnosis and multi-class classification of Alzheimer\u2019s disease stages using resting-state fMRI and residual neural networks","volume":"44","author":"Ramzan","year":"2020","journal-title":"J Med Syst"},{"issue":"5","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"820","DOI":"10.1109\/JPROC.2021.3054390","article-title":"A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises","volume":"109","author":"Zhou","year":"2021","journal-title":"Proc IEEE"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/s10194-022-01447-3","article-title":"The headache registry of the German migraine and headache society (DMKG): Baseline data of the first 1,351 patients","volume":"23","author":"Ruscheweyh","year":"2022","journal-title":"J Headache Pain"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1111\/head.13688","article-title":"The American Registry for Migraine Research: Research methods and baseline data for an initial patient cohort","volume":"60","author":"Schwedt","year":"2020","journal-title":"Headache"},{"issue":"4","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1016\/j.ncl.2019.06.001","article-title":"Migraine: Epidemiology, burden, and comorbidity","volume":"37","author":"Burch","year":"2019","journal-title":"Neurol Clin"},{"issue":"6","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"932","DOI":"10.1111\/j.1526-4610.2011.01909.x","article-title":"Treatment outcomes of chronic post-traumatic headaches after mild head trauma in US soldiers: An observational study","volume":"51","author":"Erickson","year":"2011","journal-title":"Headache"},{"issue":"10","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1016\/j.injury.2012.05.027","article-title":"Injuries from combat explosions in Iraq: Injury type, location, and severity","volume":"43","author":"Eskridge","year":"2012","journal-title":"Injury"},{"issue":"7","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1682\/JRRD.2008.02.0028","article-title":"Headaches among Operation Iraqi Freedom\/Operation Enduring Freedom veterans with mild traumatic brain injury associated with exposures to explosions","volume":"45","author":"Ruff","year":"2008","journal-title":"J Rehabil Res Dev"},{"issue":"4","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1111\/j.1526-4610.2009.01345.x","article-title":"Mild head trauma and chronic headaches in returning US soldiers","volume":"49","author":"Theeler","year":"2009","journal-title":"Headache"},{"issue":"6","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"554","DOI":"10.1177\/0333102420909865","article-title":"Persistent post-traumatic headache attributed to mild traumatic brain injury: Deep phenotyping and treatment patterns","volume":"40","author":"Ashina","year":"2020","journal-title":"Cephalalgia"},{"key":"2023022702521478100_","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"2023022702521478100_","author":"Chen"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"He","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2023022702521478100_","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"Lin","year":"2017"},{"key":"2023022702521478100_","first-page":"5987","article-title":"Aggregated residual transformations for deep neural networks","author":"Xie","year":"2016"},{"key":"2023022702521478100_","author":"He"},{"key":"2023022702521478100_","first-page":"835","article-title":"Residual and plain convolutional neural networks for 3D brain MRI classification","author":"Korolev","year":"2017"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10916-019-1475-2","article-title":"A deep learning approach for automated diagnosis and multi-class classification of Alzheimer\u2019s disease stages using resting-state fMRI and residual neural networks","volume":"44","author":"Ramzan","year":"2020","journal-title":"J Med Syst"},{"key":"2023022702521478100_","first-page":"1","article-title":"A deep CNN based multi-class classification of Alzheimer\u2019s disease using MRI","author":"Farooq","year":"2017"},{"issue":"7","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1016\/j.jid.2018.01.028","article-title":"Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm","volume":"138","author":"Han","year":"2018","journal-title":"J Invest Dermatol"},{"key":"2023022702521478100_","first-page":"370","article-title":"Classification of intracranial hemorrhage subtypes using deep learning on CT scans","volume":"272","author":"Danilov","year":"2020","journal-title":"Stud Health Technol Inform"},{"issue":"9","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"2092","DOI":"10.1109\/TMI.2019.2893944","article-title":"Attention residual learning for skin lesion classification","volume":"38","author":"Zhang","year":"2019","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1177\/0333102413485658","article-title":"The International Classification of Headache Disorders, 3rd edition (beta version)","volume":"33","author":"Headache Classification Committee of the International Headache Society (IHS)","year":"2013","journal-title":"Cephalalgia"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1177\/0333102417738202","article-title":"The International Classification of Headache Disorders, 3rd edition","volume":"38","author":"Arnold","year":"2018","journal-title":"Cephalalgia"},{"issue":"6","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"575","DOI":"10.1177\/0333102420920005","article-title":"Cortical morphological changes in chronic migraine in a Taiwanese cohort: Surface- and voxel-based analyses","volume":"40","author":"Lai","year":"2020","journal-title":"Cephalalgia"},{"issue":"14","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1125","DOI":"10.1177\/0333102414531155","article-title":"Thickening of the somatosensory cortex in migraine without aura","volume":"34","author":"Kim","year":"2014","journal-title":"Cephalalgia"},{"key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.nicl.2016.02.007","article-title":"Sensory migraine aura is not associated with structural grey matter abnormalities","volume":"11","author":"Hougaard","year":"2016","journal-title":"NeuroImage Clin"},{"key":"2023022702521478100_","article-title":"Brain Development","author":"Ixi Dataset"},{"issue":"3","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1002\/hbm.10062","article-title":"Fast robust automated brain extraction","volume":"17","author":"Smith","year":"2002","journal-title":"Hum Brain Mapp"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/S1361-8415(01)00036-6","article-title":"A global optimisation method for robust affine registration of brain images","volume":"5","author":"Jenkinson","year":"2001","journal-title":"Med Image Anal"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"Selvaraju","year":"2016","journal-title":"Int J Comput Vis"},{"key":"2023022702521478100_","first-page":"839","article-title":"Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks","author":"Chattopadhay","year":"2018"},{"key":"2023022702521478100_","first-page":"217","article-title":"M3d-CAM: A PyTorch library to generate 3D attention maps for medical deep learning","author":"Gotkowski","year":"2021","journal-title":"Inform Aktuell"},{"issue":"9","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1177\/0333102416652091","article-title":"Migraine classification using magnetic resonance imaging resting-state functional connectivity data","volume":"37","author":"Chong","year":"2017","journal-title":"Cephalalgia"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1080\/24725579.2017.1403520","article-title":"A clinical decision support system using multi-modality imaging data for disease diagnosis","volume":"8","author":"Gaw","year":"2017","journal-title":"IISE Trans Healthc Syst Eng"},{"issue":"9","key":"2023022702521478100_","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0163875","article-title":"Discriminative analysis of migraine without aura: Using functional and structural MRI with a multi-feature classification approach","volume":"11","author":"Zhang","year":"2016","journal-title":"PLoS One"},{"issue":"8","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1177\/0333102421991819","article-title":"Distinguishing persistent post-traumatic headache from migraine: Classification based on clinical symptoms and brain structural MRI data","volume":"41","author":"Chong","year":"2021","journal-title":"Cephalalgia"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1111\/head.13223","article-title":"Less cortical thickness in patients with persistent post-traumatic headache compared with healthy controls: An MRI study","volume":"58","author":"Chong","year":"2018","journal-title":"Headache"},{"issue":"5","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"1651","DOI":"10.1007\/s11682-019-00095-7","article-title":"Decreased grey matter volume in mTBI patients with post-traumatic headache compared to headache-free mTBI patients and healthy controls: A longitudinal MRI study","volume":"14","author":"Burrowes","year":"2020","journal-title":"Brain Imaging Behav"},{"issue":"1","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/s10194-017-0796-0","article-title":"Persistent post-traumatic headache vs. migraine: An MRI study demonstrating differences in brain structure","volume":"18","author":"Schwedt","year":"2017","journal-title":"J Headache Pain"},{"issue":"2","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1177\/0333102413499645","article-title":"A prospective study of prevalence and characterization of headache following mild traumatic brain injury","volume":"34","author":"Lucas","year":"2014","journal-title":"Cephalalgia"},{"issue":"6","key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"873","DOI":"10.1111\/head.13311","article-title":"Posttraumatic headache: Classification by symptom-based clinical profiles","volume":"58","author":"Lucas","year":"2018","journal-title":"Headache"},{"key":"2023022702521478100_","doi-asserted-by":"crossref","first-page":"105580","DOI":"10.1016\/j.aap.2020.105580","article-title":"Development and validation of a model predicting post-traumatic headache six months after a motor vehicle collision in adults","volume":"142","author":"Cancelliere","year":"2020","journal-title":"Accid Anal Prev"}],"container-title":["Brain Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/braincomms\/advance-article-pdf\/doi\/10.1093\/braincomms\/fcac311\/47365410\/fcac311.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/braincomms\/article-pdf\/5\/1\/fcac311\/48606667\/fcac311.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/braincomms\/article-pdf\/5\/1\/fcac311\/48606667\/fcac311.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,14]],"date-time":"2023-03-14T05:43:31Z","timestamp":1678772611000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/braincomms\/article\/doi\/10.1093\/braincomms\/fcac311\/6849385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,26]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12,29]]}},"URL":"https:\/\/doi.org\/10.1093\/braincomms\/fcac311","relation":{},"ISSN":["2632-1297"],"issn-type":[{"value":"2632-1297","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,2,1]]},"published":{"date-parts":[[2022,11,26]]},"article-number":"fcac311"}}