{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:06:51Z","timestamp":1756512411337,"version":"3.44.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100001962","name":"A-T Children's Project","doi-asserted-by":"publisher","award":["The CATNAP Study"],"award-info":[{"award-number":["The CATNAP Study"]}],"id":[{"id":"10.13039\/100001962","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011731","name":"Action for A-T","doi-asserted-by":"publisher","award":["The CATNAP Study"],"award-info":[{"award-number":["The CATNAP Study"]}],"id":[{"id":"10.13039\/100011731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011731","name":"Action for A-T","doi-asserted-by":"publisher","award":["17NOT03"],"award-info":[{"award-number":["17NOT03"]}],"id":[{"id":"10.13039\/100011731","id-type":"DOI","asserted-by":"publisher"}]},{"name":"BraShA-T","award":["17NOT03"],"award-info":[{"award-number":["17NOT03"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Cerebellar atrophy is a known feature of ataxia-telangiectasia (A-T). However, basal ganglia dysfunction contributing to extrapyramidal movement disorders in A-T remains understudied.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Objectives<\/jats:title>\n<jats:p>To characterize basal ganglia abnormalities in A-T using a normative self-supervised deep autoencoder trained on MRI-based diffusion and perfusion features from healthy children.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Methods<\/jats:title>\n<jats:p>Mean values of apparent diffusion coefficient and cerebral blood flow perfusion maps were extracted from seven regions-of-interest: caudate, hippocampus, pallidum, putamen, thalamus, cerebellar gray matter and cerebellar white matter. A normative deep autoencoder that reconstructs these features was trained on healthy subjects. Reconstruction errors for healthy and A-T participants were computed. We used Shapley Additive Explanations (SHAP) to identify the most influential features contributing to the features\u2019 reconstruction predictions. Correlations between reconstruction errors and clinical scores in A-T patients were evaluated.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Results<\/jats:title>\n<jats:p>Features were correctly reconstructed in controls but not A-T participants, who showed significantly higher reconstruction errors. Hippocampus, caudate and putamen diffusion, and caudate and putamen perfusion were overestimated, and cerebellar diffusion and pallidum perfusion underestimated, in participants with A-T. SHAP scores revealed that caudate, putamen, and hippocampus perfusion had the greatest influence on the reconstruction of perfusion features. In contrast, cerebellar diffusion and caudate perfusion had the greatest influence on the reconstruction of diffusion features. Exploratory analysis showed that extrapyramidal movement sub-scores from A-T participants correlated with perfusion and diffusion reconstruction errors from cerebellar and subcortical structures.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>Our findings suggest that pallidum, caudate, and cerebellar gray matter are potential targets for novel treatment approaches for A-T. The approach enables identification of subtle tissue anomalies at an individual level, allowing tailored approaches.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0328828","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:29:25Z","timestamp":1756488565000},"page":"e0328828","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Personalized MRI-based characterization of subcortical anomalies in Ataxia-Telangiectasia using deep-learning"],"prefix":"10.1371","volume":"20","author":[{"given":"Catalina","family":"Saini","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3575-2113","authenticated-orcid":true,"given":"Cristian","family":"Salazar-Vilches","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caroline C.V.","family":"Blanchard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5207-5731","authenticated-orcid":true,"given":"William P.","family":"Whitehouse","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Parra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rob A.","family":"Dineen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5859-3190","authenticated-orcid":true,"given":"Stefan","family":"Pszczolkowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"issue":"1","key":"pone.0328828.ref001","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1186\/s13023-016-0543-7","article-title":"Ataxia telangiectasia: a review","volume":"11","author":"C Rothblum-Oviatt","year":"2016","journal-title":"Orphanet J Rare Dis"},{"key":"pone.0328828.ref002","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/978-3-031-15070-8_93","article-title":"Ataxia telangiectasia","volume-title":"Essentials of cerebellum and cerebellar disorders: a primer for graduate students","author":"RA Dineen","year":"2023"},{"issue":"9","key":"pone.0328828.ref003","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1080\/1744666X.2020.1810570","article-title":"Ataxia-telangiectasia: epidemiology, pathogenesis, clinical phenotype, diagnosis, prognosis and management","volume":"16","author":"P Amirifar","year":"2020","journal-title":"Expert Rev Clin Immunol"},{"key":"pone.0328828.ref004","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.parkreldis.2017.12.009","article-title":"More than ataxia - Movement disorders in ataxia-telangiectasia","volume":"46","author":"HAG Teive","year":"2018","journal-title":"Parkinsonism Relat Disord"},{"key":"pone.0328828.ref005","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0264177","article-title":"The natural history of ataxia-telangiectasia (A-T): a systematic review","volume":"17","author":"E Petley","year":"2022","journal-title":"PLOS ONE"},{"issue":"6","key":"pone.0328828.ref006","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1212\/WNL.0b013e3181af33bd","article-title":"Clinical spectrum of ataxia-telangiectasia in adulthood","volume":"73","author":"MMM Verhagen","year":"2009","journal-title":"Neurology"},{"issue":"2","key":"pone.0328828.ref007","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1002\/ana.25394","article-title":"Genotype, extrapyramidal features, and severity of variant ataxia-telangiectasia","volume":"85","author":"K Schon","year":"2019","journal-title":"Ann Neurol"},{"issue":"4","key":"pone.0328828.ref008","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1007\/s12311-014-0557-4","article-title":"Radiological imaging in ataxia telangiectasia: a review","volume":"13","author":"I Sahama","year":"2014","journal-title":"Cerebellum"},{"key":"pone.0328828.ref009","doi-asserted-by":"crossref","first-page":"102110","DOI":"10.1016\/j.nicl.2019.102110","article-title":"Multiparametric cerebellar imaging and clinical phenotype in childhood ataxia telangiectasia","volume":"25","author":"RA Dineen","year":"2020","journal-title":"Neuroimage Clin"},{"issue":"21","key":"pone.0328828.ref010","doi-asserted-by":"crossref","first-page":"12653","DOI":"10.1073\/pnas.95.21.12653","article-title":"Selective loss of dopaminergic nigro-striatal neurons in brains of Atm-deficient mice","volume":"95","author":"R Eilam","year":"1998","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pone.0328828.ref011","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/S0306-4522(03)00322-1","article-title":"Late degeneration of nigro-striatal neurons in ATM-\/- mice","volume":"121","author":"R Eilam","year":"2003","journal-title":"Neuroscience"},{"key":"pone.0328828.ref012","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1093\/brain\/awu092","article-title":"Brain glucose metabolism in adults with ataxia-telangiectasia and their asymptomatic relatives","volume":"137","author":"ND Volkow","year":"2014","journal-title":"Brain"},{"issue":"7553","key":"pone.0328828.ref013","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nature"},{"issue":"6","key":"pone.0328828.ref014","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"ImageNet classification with deep convolutional neural networks","volume":"60","author":"A Krizhevsky","year":"2017","journal-title":"Commun ACM"},{"key":"pone.0328828.ref015","unstructured":"Baldi P. Autoencoders, unsupervised learning, and deep architectures. In: Proceedings of ICML Workshop on Unsupervised and Transfer Learning, 2012. 37\u201349. https:\/\/proceedings.mlr.press\/v27\/baldi12a.html"},{"issue":"7","key":"pone.0328828.ref016","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1016\/j.biopsych.2015.12.023","article-title":"Understanding heterogeneity in clinical cohorts using normative models: beyond case-control studies","volume":"80","author":"AF Marquand","year":"2016","journal-title":"Biol Psychiatry"},{"key":"pone.0328828.ref017","first-page":"4","article-title":"Anomaly detection using autoencoders with nonlinear dimensionality reduction.","author":"M Sakurada","year":"2014"},{"key":"pone.0328828.ref018","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1038\/s43588-021-00126-8","article-title":"Detecting microstructural deviations in individuals with deep diffusion MRI tractometry","volume":"1","author":"M Chamberland","year":"2021","journal-title":"Nat Comput Sci"},{"issue":"7","key":"pone.0328828.ref019","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1111\/dmcn.13052","article-title":"Longitudinal analysis of the neurological features of ataxia-telangiectasia","volume":"58","author":"TJ Jackson","year":"2016","journal-title":"Dev Med Child Neurol"},{"key":"pone.0328828.ref020","doi-asserted-by":"crossref","first-page":"105224","DOI":"10.1016\/j.dib.2020.105224","article-title":"Calgary preschool magnetic resonance imaging (MRI) dataset","volume":"29","author":"JE Reynolds","year":"2020","journal-title":"Data Brief"},{"issue":"1087","key":"pone.0328828.ref021","doi-asserted-by":"crossref","first-page":"20170719","DOI":"10.1259\/bjr.20170719","article-title":"Evaluation of an internet-based animated preparatory video for children undergoing non-sedated MRI","volume":"91","author":"HL McGlashan","year":"2018","journal-title":"Br J Radiol"},{"issue":"6","key":"pone.0328828.ref022","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"NJ Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"pone.0328828.ref023","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1109\/TMI.2011.2138152","article-title":"Robust brain extraction across datasets and comparison with publicly available methods","volume":"30","author":"JE Iglesias","year":"2011","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"pone.0328828.ref024","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.media.2014.12.003","article-title":"Robust whole-brain segmentation: application to traumatic brain injury","volume":"21","author":"C Ledig","year":"2015","journal-title":"Med Image Anal"},{"issue":"2","key":"pone.0328828.ref025","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1002\/mrm.24279","article-title":"Improved partial volume correction for single inversion time arterial spin labeling data","volume":"69","author":"X Liang","year":"2013","journal-title":"Magn Reson Med"},{"issue":"1","key":"pone.0328828.ref026","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.neuroimage.2009.06.060","article-title":"Accurate and robust brain image alignment using boundary-based registration","volume":"48","author":"DN Greve","year":"2009","journal-title":"Neuroimage"},{"key":"pone.0328828.ref027","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"A Paszke","year":"2019","journal-title":"arXiv"},{"key":"pone.0328828.ref028","article-title":"A unified approach to interpreting model predictions","author":"S Lundberg","year":"2017","journal-title":"arXiv"},{"issue":"1","key":"pone.0328828.ref029","doi-asserted-by":"crossref","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"J Friedman","year":"2010","journal-title":"J Stat Soft"},{"issue":"4","key":"pone.0328828.ref030","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/S0895-4356(00)00314-0","article-title":"Adjusting for multiple testing--when and how?","volume":"54","author":"R Bender","year":"2001","journal-title":"J Clin Epidemiol"},{"key":"pone.0328828.ref031","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.nicl.2015.08.007","article-title":"Motor pathway degeneration in young ataxia telangiectasia patients: a diffusion tractography study","volume":"9","author":"I Sahama","year":"2015","journal-title":"Neuroimage Clin"},{"issue":"4","key":"pone.0328828.ref032","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1055\/s-2006-924722","article-title":"Proton MR spectroscopic imaging in ataxia-telangiectasia","volume":"37","author":"DDM Lin","year":"2006","journal-title":"Neuropediatrics"},{"issue":"1","key":"pone.0328828.ref033","first-page":"79","article-title":"Proton spectroscopy and imaging at 3T in ataxia-telangiectasia","volume":"28","author":"LI Wallis","year":"2007","journal-title":"AJNR Am J Neuroradiol"},{"issue":"4","key":"pone.0328828.ref034","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1002\/mds.870090414","article-title":"Dystonia in ataxia telangiectasia: report of a case with putaminal lesions and decreased striatal [123I]iodobenzamide binding","volume":"9","author":"M Koepp","year":"1994","journal-title":"Mov Disord"},{"issue":"4","key":"pone.0328828.ref035","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1002\/mdc3.12287","article-title":"Bilateral deep brain stimulation of the globus pallidus pars interna in a patient with variant ataxia-telangiectasia","volume":"3","author":"D Georgiev","year":"2016","journal-title":"Mov Disord Clin Pract"},{"issue":"23","key":"pone.0328828.ref036","doi-asserted-by":"crossref","first-page":"7009","DOI":"10.3390\/jcm13237009","article-title":"Artificial intelligence in the diagnosis and quantitative phenotyping of hyperkinetic movement disorders: a systematic review","volume":"13","author":"JA Vizcarra","year":"2024","journal-title":"J Clin Med"},{"issue":"4","key":"pone.0328828.ref037","doi-asserted-by":"crossref","DOI":"10.1093\/cercor\/bhae132","article-title":"Integration of graph network with kernel SVM and logistic regression for identification of biomarkers in SCA12 and its diagnosis","volume":"34","author":"S Agrawal","year":"2024","journal-title":"Cereb Cortex"},{"issue":"6","key":"pone.0328828.ref038","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1002\/mds.29370","article-title":"A novel metric for predicting severity of disease features in Friedreich\u2019s Ataxia","volume":"38","author":"LN Rodden","year":"2023","journal-title":"Mov Disord"},{"key":"pone.0328828.ref039","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1109\/TNSRE.2022.3161272","article-title":"Federated deep learning for the diagnosis of cerebellar ataxia: privacy preservation and auto-crafted feature extractor","volume":"30","author":"T Ngo","year":"2022","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"pone.0328828.ref040","doi-asserted-by":"crossref","first-page":"639871","DOI":"10.3389\/fnhum.2021.639871","article-title":"Clinical recognition of sensory ataxia and cerebellar ataxia","volume":"15","author":"Q Zhang","year":"2021","journal-title":"Front Hum Neurosci"},{"issue":"1","key":"pone.0328828.ref041","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1002\/mds.28311","article-title":"Prediction of the age at onset of spinocerebellar ataxia type 3 with machine learning","volume":"36","author":"L Peng","year":"2021","journal-title":"Mov Disord"},{"issue":"6","key":"pone.0328828.ref042","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1002\/mds.28508","article-title":"Voice analysis with machine learning: one step closer to an objective diagnosis of essential tremor","volume":"36","author":"A Suppa","year":"2021","journal-title":"Mov Disord"},{"issue":"3","key":"pone.0328828.ref043","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1002\/mds.28866","article-title":"A machine-learning derived huntington\u2019s disease progression model: insights for clinical trial design","volume":"37","author":"A Mohan","year":"2022","journal-title":"Mov Disord"},{"key":"pone.0328828.ref044","doi-asserted-by":"crossref","first-page":"61","DOI":"10.3389\/fnsys.2019.00061","article-title":"The cortico-basal ganglia-cerebellar network: past, present and future perspectives","volume":"13","author":"D Milardi","year":"2019","journal-title":"Front Syst Neurosci"},{"issue":"36","key":"pone.0328828.ref045","doi-asserted-by":"crossref","first-page":"6910","DOI":"10.1523\/JNEUROSCI.0763-20.2020","article-title":"HippoBellum: acute cerebellar modulation alters hippocampal dynamics and function","volume":"40","author":"Z Zeidler","year":"2020","journal-title":"J Neurosci"},{"key":"pone.0328828.ref046","doi-asserted-by":"crossref","first-page":"101977","DOI":"10.1016\/j.smrv.2024.101977","article-title":"Cerebral blood flow in sleep: a systematic review and meta-analysis","volume":"77","author":"RFM Al-Shama","year":"2024","journal-title":"Sleep Med Rev"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:29:33Z","timestamp":1756488573000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0328828"}},"subtitle":[],"editor":[{"given":"Alpen","family":"Ortug","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":46,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,29]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0328828","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]}}}