{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T21:30:06Z","timestamp":1770499806262,"version":"3.49.0"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000005","name":"U.S. Department of Defense","doi-asserted-by":"publisher","award":["W81XWH-15-1-0286"],"award-info":[{"award-number":["W81XWH-15-1-0286"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K23NS070891"],"award-info":[{"award-number":["K23NS070891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000871","name":"Mayo Clinic","doi-asserted-by":"publisher","award":["internal funds"],"award-info":[{"award-number":["internal funds"]}],"id":[{"id":"10.13039\/100000871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Multicenter and multi-scanner imaging studies may be necessary to ensure sufficiently large sample sizes for developing accurate predictive models. However, multicenter studies, incorporating varying research participant characteristics, MRI scanners, and imaging acquisition protocols, may introduce confounding factors, potentially hindering the creation of generalizable machine learning models. Models developed using one dataset may not readily apply to another, emphasizing the importance of classification model generalizability in multi-scanner and multicenter studies for producing reproducible results. This study focuses on enhancing generalizability in classifying individual migraine patients and healthy controls using brain MRI data through a data harmonization strategy. We propose identifying a \u2019healthy core\u2019\u2014a group of homogeneous healthy controls with similar characteristics\u2014from multicenter studies. The Maximum Mean Discrepancy (MMD) in Geodesic Flow Kernel (GFK) space is employed to compare two datasets, capturing data variabilities and facilitating the identification of this \u2018healthy core\u2019. Homogeneous healthy controls play a vital role in mitigating unwanted heterogeneity, enabling the development of highly accurate classification models with improved performance on new datasets. Extensive experimental results underscore the benefits of leveraging a \u2019healthy core\u2019. We utilized two datasets: one comprising 120 individuals (66 with migraine and 54 healthy controls), and another comprising 76 individuals (34 with migraine and 42 healthy controls). Notably, a homogeneous dataset derived from a cohort of healthy controls yielded a significant 25% accuracy improvement for both episodic and chronic migraineurs.<\/jats:p>","DOI":"10.1371\/journal.pone.0288300","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T18:21:43Z","timestamp":1735669303000},"page":"e0288300","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["Healthy core: Harmonizing brain MRI for supporting multicenter migraine classification studies"],"prefix":"10.1371","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6371-7055","authenticated-orcid":true,"given":"Hyunsoo","family":"Yoon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd J.","family":"Schwedt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Catherine D.","family":"Chong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oyekanmi","family":"Olatunde","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0529-7048","authenticated-orcid":true,"given":"Teresa","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"issue":"5","key":"pone.0288300.ref001","doi-asserted-by":"crossref","first-page":"1104","DOI":"10.1016\/j.pain.2011.01.026","article-title":"Affective brain regions are activated during the processing of pain-related words in migraine patients","volume":"152","author":"J Eck","year":"2011","journal-title":"Pain"},{"issue":"1","key":"pone.0288300.ref002","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s10194-017-0782-6","article-title":"Functional connectivity and cognitive impairment in migraine with and without aura","volume":"18","author":"V Lo Buono","year":"2017","journal-title":"The journal of headache and pain"},{"issue":"6","key":"pone.0288300.ref003","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1002\/hbm.24030","article-title":"Deep in the brain: changes in subcortical function immediately preceding a migraine attack","volume":"39","author":"N Meylakh","year":"2018","journal-title":"Human brain mapping"},{"issue":"4","key":"pone.0288300.ref004","doi-asserted-by":"crossref","first-page":"984","DOI":"10.1002\/hbm.24854","article-title":"Neuroimaging features of whole\u2010brain functional connectivity predict attack frequency of migraine","volume":"41","author":"J Mu","year":"2020","journal-title":"Human brain mapping"},{"issue":"1","key":"pone.0288300.ref005","first-page":"1","article-title":"Impaired effective functional connectivity of the sensorimotor network in interictal episodic migraineurs without aura","volume":"21","author":"HL Wei","year":"2020","journal-title":"The Journal of Headache and Pain"},{"key":"pone.0288300.ref006","doi-asserted-by":"crossref","first-page":"485","DOI":"10.3389\/fpsyt.2020.00485","article-title":"The link between structural and functional brain abnormalities in depression: a systematic review of Multimodal Neuroimaging Studies","volume":"11","author":"DS Scheepens","year":"2020","journal-title":"Frontiers in psychiatry"},{"issue":"1","key":"pone.0288300.ref007","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s40122-021-00240-5","article-title":"Structural and functional brain changes in migraine","volume":"10","author":"S Ashina","year":"2021","journal-title":"Pain and Therapy"},{"issue":"05","key":"pone.0288300.ref008","doi-asserted-by":"crossref","first-page":"455","DOI":"10.3414\/ME14-02-0030","article-title":"A generic data harmonization process for cross-linked research and network interaction","volume":"54","author":"D Firnkorn","year":"2015","journal-title":"Methods of information in medicine"},{"issue":"11","key":"pone.0288300.ref009","doi-asserted-by":"crossref","first-page":"4213","DOI":"10.1002\/hbm.24241","article-title":"Statistical harmonization corrects site effects in functional connectivity measurements from multi\u2010site fMRI data","volume":"39","author":"M Yu","year":"2018","journal-title":"Human brain mapping"},{"issue":"5","key":"pone.0288300.ref010","doi-asserted-by":"crossref","first-page":"1507","DOI":"10.1002\/hbm.24463","article-title":"& Alzheimer\u2019s Disease Neuroimaging Initiative, Quantitative assessment of field strength, total intracranial volume, sex, and age effects on the goodness of harmonization for volumetric analysis on the ADNI database","volume":"40","author":"D Ma","year":"2019","journal-title":"Human brain mapping"},{"issue":"4","key":"pone.0288300.ref011","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1002\/hbm.25688","article-title":"Alzheimer\u2019s Disease Neuroimaging Initiative, Mitigating site effects in covariance for machine learning in neuroimaging data","volume":"43","author":"AA Chen","year":"2022","journal-title":"Human brain mapping"},{"key":"pone.0288300.ref012","doi-asserted-by":"crossref","first-page":"1146175","DOI":"10.3389\/fnins.2023.1146175","article-title":"Characterization of the effects of outliers on ComBat harmonization for removing inter-site data heterogeneity in multisite neuroimaging studies","volume":"17","author":"Q Han","year":"2023","journal-title":"Frontiers in Neuroscience"},{"key":"pone.0288300.ref013","doi-asserted-by":"crossref","unstructured":"Hu, F, Lucas, A, Chen, AA, Coleman, K, Horng, H, Ng, RW,\u2026 & Alzheimer\u2019s Disease Neuroimaging Initiative. (2023). DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data. bioRxiv.","DOI":"10.1101\/2023.04.24.537396"},{"key":"pone.0288300.ref014","doi-asserted-by":"crossref","unstructured":"Yao, T, Rheault, F, Cai, LY, Nath, V, Asad, Z, Newlin, N, et al (2023, April). Deep constrained spherical deconvolution for robust harmonization. In Medical Imaging 2023: Image Processing (Vol. 12464, pp. 169\u2013176). SPIE.","DOI":"10.1117\/12.2654398"},{"key":"pone.0288300.ref015","doi-asserted-by":"crossref","unstructured":"Souza, R, Stanley, EA, Camacho, M, Wilms, M, & Forkert, ND (2023, April). An analysis of intensity harmonization techniques for Parkinson\u2019s multi-site MRI datasets. In Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series (Vol. 12465, p. 124652B).","DOI":"10.1117\/12.2653948"},{"key":"pone.0288300.ref016","doi-asserted-by":"crossref","unstructured":"El-Gazzar, A., Thomas, R. M., & van Wingen, G. (2023). Harmonization techniques for machine learning studies using multi-site functional MRI data. bioRxiv, 2023\u201306.","DOI":"10.1101\/2023.06.14.544758"},{"key":"pone.0288300.ref017","doi-asserted-by":"crossref","unstructured":"Tzeng, E, Hoffman, J, Saenko, K, & Darrell, T, Adversarial discriminative domain adaptation. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2017; 7167\u20137176.","DOI":"10.1109\/CVPR.2017.316"},{"key":"pone.0288300.ref018","doi-asserted-by":"crossref","unstructured":"Tang, H, Chen, K, & Jia, K, Unsupervised domain adaptation via structurally regularized deep clustering. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2020; 8725\u20138735.","DOI":"10.1109\/CVPR42600.2020.00875"},{"key":"pone.0288300.ref019","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":"Classification Committee of the International Headache Society","year":"2013","journal-title":"Cephalalgia"},{"issue":"6","key":"pone.0288300.ref020","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":"TJ Schwedt","year":"2015","journal-title":"Headache: The Journal of Head and Face Pain"},{"issue":"9","key":"pone.0288300.ref021","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":"CD Chong","year":"2017","journal-title":"Cephalalgia"},{"issue":"2","key":"pone.0288300.ref022","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1006\/nimg.1998.0395","article-title":"Cortical surface-based analysis: I. Segmentation and surface reconstruction","volume":"9","author":"AM Dale","year":"1999","journal-title":"Neuroimage"},{"issue":"1","key":"pone.0288300.ref023","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/42.906426","article-title":"Automated manifold surgery: constructing geometrically accurate and topologically correct models of the human cerebral cortex","volume":"20","author":"B Fischl","year":"2001","journal-title":"IEEE transactions on medical imaging"},{"issue":"3","key":"pone.0288300.ref024","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/S0896-6273(02)00569-X","article-title":"Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain","volume":"33","author":"B Fischl","year":"2002","journal-title":"Neuron"},{"issue":"3","key":"pone.0288300.ref025","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1016\/j.neuroimage.2004.03.032","article-title":"A hybrid approach to the skull stripping problem in MRI","volume":"22","author":"F S\u00e9gonne","year":"2004","journal-title":"Neuroimage"},{"issue":"1","key":"pone.0288300.ref026","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"A Gretton","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"pone.0288300.ref027","unstructured":"Long M, Cao Y, Wang J, & Jordan M, Learning transferable features with deep adaptation networks. In International conference on machine learning. 2015, June; 97\u2013105. PMLR (Proceedings of Machine Learning Research)."},{"key":"pone.0288300.ref028","doi-asserted-by":"crossref","unstructured":"Yan H, Ding Y, Li P, Wang Q, Xu Y, & Zuo W, Mind the class weight bias: Weighted maximum mean discrepancy for unsupervised domain adaptation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017; 2272\u20132281.","DOI":"10.1109\/CVPR.2017.107"},{"issue":"2","key":"pone.0288300.ref029","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1080\/23294515.2019.1586008","article-title":"Enhancing understanding of moral distress: the measure of moral distress for health care professionals","volume":"10","author":"EG Epstein","year":"2019","journal-title":"AJOB empirical bioethics"},{"key":"pone.0288300.ref030","doi-asserted-by":"crossref","unstructured":"Zhang W, & Wu D, Discriminative joint probability maximum mean discrepancy (DJP-MMD) for domain adaptation. In 2020 International Joint Conference on Neural Networks (IJCNN). 2020, July; 1\u20138.","DOI":"10.1109\/IJCNN48605.2020.9207365"},{"key":"pone.0288300.ref031","unstructured":"Kirchler M, Khorasani S, Kloft M, & Lippert C, Two-sample testing using deep learning. In International Conference on Artificial Intelligence and Statistics. 2020, June; 1387\u20131398. PMLR."},{"issue":"11","key":"pone.0288300.ref032","article-title":"Visualizing data using t-SNE","volume":"9","author":"L Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"issue":"12","key":"pone.0288300.ref033","doi-asserted-by":"crossref","first-page":"2776","DOI":"10.1097\/j.pain.0000000000001676","article-title":"Dynamic functional connectivity of the migraine brain: a resting-state functional magnetic resonance imaging study","volume":"160","author":"MJ Lee","year":"2019","journal-title":"Pain"},{"issue":"9","key":"pone.0288300.ref034","doi-asserted-by":"crossref","first-page":"e0163875","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":"Q Zhang","year":"2016","journal-title":"PloS one"},{"issue":"1","key":"pone.0288300.ref035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12938-018-0587-0","article-title":"Multimodal MRI-based classification of migraine: using deep learning convolutional neural network","volume":"17","author":"H Yang","year":"2018","journal-title":"Biomedical engineering online"},{"issue":"7","key":"pone.0288300.ref036","doi-asserted-by":"crossref","first-page":"1051","DOI":"10.1111\/head.13121","article-title":"Migraine subclassification via a data\u2010driven automated approach using multimodality factor mixture modeling of brain structure measurements","volume":"57","author":"TJ Schwedt","year":"2017","journal-title":"Headache: The Journal of Head and Face Pain"},{"issue":"1","key":"pone.0288300.ref037","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":"N Gaw","year":"2018","journal-title":"IISE Transactions on Healthcare Systems Engineering"},{"issue":"1","key":"pone.0288300.ref038","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1111\/j.1526-4610.2007.00723.x","article-title":"Voxel\u2010based morphometry reveals gray matter abnormalities in migraine","volume":"48","author":"W Valfr\u00e8","year":"2008","journal-title":"Headache: The Journal of Head and Face Pain"},{"issue":"7","key":"pone.0288300.ref039","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1111\/j.1526-4610.2008.01133.x","article-title":"Attack frequency and disease duration as indicators for brain damage in migraine","volume":"48","author":"N Schmitz","year":"2008","journal-title":"Headache: The Journal of Head and Face Pain"},{"issue":"8","key":"pone.0288300.ref040","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1177\/0333102412445622","article-title":"Concurrent functional and structural cortical alterations in migraine","volume":"32","author":"N Maleki","year":"2012","journal-title":"Cephalalgia"},{"issue":"5","key":"pone.0288300.ref041","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1177\/0333102418795163","article-title":"Cortical abnormalities in episodic migraine: a multi-center 3T MRI study","volume":"39","author":"S Magon","year":"2019","journal-title":"Cephalalgia"},{"issue":"6","key":"pone.0288300.ref042","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":"KL Lai","year":"2020","journal-title":"Cephalalgia"},{"key":"pone.0288300.ref043","doi-asserted-by":"crossref","unstructured":"Gong B, Shi Y, Sha F, & Grauman K, Geodesic flow kernel for unsupervised domain adaptation. In 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012, June: 2066\u20132073.","DOI":"10.1109\/CVPR.2012.6247911"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0288300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T18:22:04Z","timestamp":1735669324000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0288300"}},"subtitle":[],"editor":[{"given":"Lorenzo","family":"Faggioni","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":43,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0288300","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]}}}