{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T13:54:37Z","timestamp":1784210077214,"version":"3.55.0"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T00:00:00Z","timestamp":1677715200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["P30AG062421"],"award-info":[{"award-number":["P30AG062421"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01GM138778"],"award-info":[{"award-number":["R01GM138778"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ministry of Trade, Industry and Energy, Republic of Korea","award":["20009571"],"award-info":[{"award-number":["20009571"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>In this work, we introduce a novel deep learning architecture, MUCRAN (Multi-Confound Regression Adversarial Network), to train a deep learning model on clinical brain MRI while regressing demographic and technical confounding factors. We trained MUCRAN using 17,076 clinical T1 Axial brain MRIs collected from Massachusetts General Hospital before 2019 and demonstrated that MUCRAN could successfully regress major confounding factors in the vast clinical dataset. We also applied a method for quantifying uncertainty across an ensemble of these models to automatically exclude out-of-distribution data in AD detection. By combining MUCRAN and the uncertainty quantification method, we showed consistent and significant increases in the AD detection accuracy for newly collected MGH data (post-2019; 84.6% with MUCRAN vs. 72.5% without MUCRAN) and for data from other hospitals (90.3% from Brigham and Women\u2019s Hospital and 81.0% from other hospitals). MUCRAN offers a generalizable approach for deep-learning-based disease detection in heterogenous clinical data.<\/jats:p>","DOI":"10.1371\/journal.pone.0277572","type":"journal-article","created":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T18:44:46Z","timestamp":1677782686000},"page":"e0277572","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":14,"title":["Adversarial confound regression and uncertainty measurements to classify heterogeneous clinical MRI in Mass General Brigham"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9631-2567","authenticated-orcid":true,"given":"Matthew","family":"Leming","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudeshna","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyungsoon","family":"Im","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,3,2]]},"reference":[{"key":"pone.0277572.ref001","doi-asserted-by":"crossref","first-page":"179","DOI":"10.31887\/DCNS.2018.20.3\/pfalkai","article-title":"Forty years of structural brain imaging in mental disorders: is it clinically useful or not?","volume":"20","author":"P Falkai","year":"2018","journal-title":"Dialogues Clin Neurosci"},{"key":"pone.0277572.ref002","article-title":"Convolutional Neural Networks for Classification of Alzheimer\u2019s Disease: Overview and Reproducible Evaluation","volume":"63","author":"J Wen","year":"2020","journal-title":"Medical Image Analysis"},{"key":"pone.0277572.ref003","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/978-3-030-70558-9_8","volume-title":"Mental Health Informatics: Enabling a Learning Mental Healthcare System","author":"RL Gollub","year":"2021","edition":"1"},{"key":"pone.0277572.ref004","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/s41568-021-00399-1","article-title":"Artificial intelligence in cancer research, diagnosis and therapy","volume":"21","author":"O Elemento","year":"2021","journal-title":"Nature Reviews Cancer"},{"key":"pone.0277572.ref005","unstructured":"Lee K, Lee K, Lee H, Shin J. A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks. arXiv. 2018;1807.03888."},{"key":"pone.0277572.ref006","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1038\/s41591-021-01506-3","article-title":"Federated learning for predicting clinical outcomes in patients with COVID-19","volume":"27","author":"I Dayan","year":"2021","journal-title":"Nature Medicine"},{"key":"pone.0277572.ref007","doi-asserted-by":"crossref","first-page":"118409","DOI":"10.1016\/j.neuroimage.2021.118409","article-title":"Deep learning for sex classification in resting-state and task functional brain networks from the UK Biobank","volume":"241","author":"M Leming","year":"2021","journal-title":"NeuroImage"},{"key":"pone.0277572.ref008","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2022.102309","article-title":"Construction of a confounder-free clinical MRI dataset in the Mass General Brigham system for classification of Alzheimer\u2019s disease","volume":"129","author":"M Leming","year":"2022","journal-title":"Artificial Intelligence in Medicine"},{"key":"pone.0277572.ref009","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","article-title":"Adjusting batch effects in microarray expression data using empirical Bayes methods","volume":"8","author":"WE Johnson","year":"2007","journal-title":"Biostatistics"},{"key":"pone.0277572.ref010","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-site fMRI data","volume":"39","author":"M Yu","year":"2018","journal-title":"Hum Brain Mapp"},{"key":"pone.0277572.ref011","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/j.tree.2008.10.008","article-title":"Generalized linear mixed models: A practical guide for ecology and evolution","volume":"24","author":"BM Bolker","year":"2009","journal-title":"Trends in Ecology & Evolution"},{"key":"pone.0277572.ref012","doi-asserted-by":"crossref","first-page":"e0202947","DOI":"10.1371\/journal.pone.0202947","article-title":"Comparison of statistical methods and the use of quality control samples for batch effect correction in human transcriptome data","volume":"13","author":"A Esp\u00edn-P\u00e9rez","year":"2018","journal-title":"PLoS One"},{"key":"pone.0277572.ref013","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-19784-9","article-title":"Training confounder-free deep learning models for medical applications","volume":"11","author":"Q Zhao","year":"2020","journal-title":"Nature Communications"},{"key":"pone.0277572.ref014","doi-asserted-by":"crossref","first-page":"677","DOI":"10.1101\/gr.268581.120","article-title":"Semi-supervised adversarial neural networks for single-cell classification","volume":"31","author":"JC Kimmel","year":"2021","journal-title":"Genome Res"},{"key":"pone.0277572.ref015","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1038\/s42256-021-00399-8","article-title":"Designing clinically translatable artificial intelligence systems for high-dimensional medical imaging","volume":"3","author":"R Shad","year":"2021","journal-title":"Nature Machine Intelligence"},{"key":"pone.0277572.ref016","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","volume":"48","author":"Y Gal","year":"2016","journal-title":"Proceedings of the 33 rd International Conference on Machine Learning"},{"key":"pone.0277572.ref017","unstructured":"Liu JZ, Lin Z, Padhy S, Tran D, Bedrax-Weiss T, Lakshminarayanan B. Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness. arXiv. 2020;."},{"key":"pone.0277572.ref018","unstructured":"Gawlikowski J, Tassi CRN, Ali M, Lee J, Humt M, Feng J, et al. A Survey of Uncertainty in Deep Neural Networks. arXiv. 2021;."},{"key":"pone.0277572.ref019","unstructured":"Lakshminarayanan B, Pritzel A, Blundell C. Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles. NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems. 2017; p. 6405\u20136416."},{"key":"pone.0277572.ref020","article-title":"Out-of-distribution detection-assisted trustworthy machinery fault diagnosis approach with uncertainty-aware deep ensembles","volume":"226","author":"T Han","year":"2022","journal-title":"Reliability Engineering & System Safety"},{"key":"pone.0277572.ref021","first-page":"2672","article-title":"Generative Adversarial Nets","author":"IJ Goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems 27"},{"key":"pone.0277572.ref022","volume-title":"Experimental and Quasi-experimental Designs for Generalized Causal Inference","author":"TD Cook","year":"2002"},{"key":"pone.0277572.ref023","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1016\/j.neuroimage.2018.09.074","article-title":"How to control for confounds in decoding analyses of neuroimaging data","volume":"184","author":"L Snoek","year":"2019","journal-title":"NeuroImage"},{"key":"pone.0277572.ref024","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.neuroimage.2013.03.039","article-title":"Confounds in multivariate pattern analysis: theory and rule representation case study","volume":"77","author":"MT Todd","year":"2013","journal-title":"NeuroImage"},{"key":"pone.0277572.ref025","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.neuroimage.2014.04.057","article-title":"Correction of inter-scanner and within-subject variance in structural MRI based automated diagnosing","volume":"98","author":"D Kostro","year":"2014","journal-title":"NeuroImage"},{"key":"pone.0277572.ref026","doi-asserted-by":"crossref","DOI":"10.1017\/pen.2018.8","article-title":"Resting-State Functional Brain Connectivity Best Predicts the Personality Dimension of Openness to Experience","volume":"1","author":"J Dubois","year":"2018","journal-title":"Personality Neuroscience"},{"key":"pone.0277572.ref027","first-page":"3","article-title":"Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study","volume":"12461","author":"S More","year":"2021","journal-title":"Machine Learning and Knowledge Discovery in Databases"},{"key":"pone.0277572.ref028","first-page":"166","article-title":"Memantine: A Review of Possible Uses in Child and Adolescent Psychiatry","volume":"22","author":"S Hosenbocus","year":"2013","journal-title":"J Can Acad Child Adolesc Psychiatry"},{"key":"pone.0277572.ref029","unstructured":"Chintala S, Denton E, Arjovsky M, Mathieu M. How to Train a GAN? Tips and tricks to make GANs work. NIPS2016. 2016;."},{"key":"pone.0277572.ref030","unstructured":"Radford A, Metz L, Chintala S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. ICLR. 2016;."},{"key":"pone.0277572.ref031","unstructured":"Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X. Improved Techniques for Training GANs. arXiv. 2016;."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0277572","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T18:45:02Z","timestamp":1677782702000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0277572"}},"subtitle":[],"editor":[{"given":"Kapil Kumar","family":"Nagwanshi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,3,2]]},"references-count":31,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,3,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0277572","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,2]]}}}