{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T15:17:20Z","timestamp":1786202240884,"version":"build-2736575974"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T00:00:00Z","timestamp":1739836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100008383","name":"Stichting ParkinsonFonds","doi-asserted-by":"crossref","award":["2022\/1891"],"award-info":[{"award-number":["2022\/1891"]}],"id":[{"id":"10.13039\/501100008383","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur J Nucl Med Mol Imaging"],"published-print":{"date-parts":[[2025,7]]},"abstract":"Abstract<\/jats:title>\n \n Purpose<\/jats:title>\n Center-specific effects in PET brain scans arise due to differences in technical and procedural aspects. This restricts the merging of data between centers and introduces source-specific bias.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n We demonstrate the use of the recently proposed machine learning method Iterated Relevance Matrix Analysis (IRMA) for harmonization of center-specific effects in brain\n \n \n $$^{18}$$<\/jats:tex-math>\n \n \n \n \n 18<\/mml:mn>\n <\/mml:mmultiscripts>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n F-Fluorodeoxyglucose (\n \n \n $$^{18}$$<\/jats:tex-math>\n \n \n \n \n 18<\/mml:mn>\n <\/mml:mmultiscripts>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n F-FDG) PET scans. The center difference is learned by applying IRMA on PCA-based feature vectors of healthy controls (HC), resulting in a subspace\n \n \n $$\\varvec{V}$$<\/jats:tex-math>\n \n \n V<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , representing information not comparable between centers, and the remaining subspace\n \n \n $$\\varvec{U}$$<\/jats:tex-math>\n \n \n U<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , where no center differences are present. In this proof-of-concept study, we demonstrate the properties of the method using data from four centers. After center-harmonization, a Generalized Matrix Learning Vector Quantization (GMLVQ) model was trained to discriminate between Parkinson\u2019s disease, Alzheimer\u2019s disease and Dementia with Lewy Bodies.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n At the initial IRMA iteration, the system was able to determine the center origin of the four HC cohorts almost perfectly. The method required six iterations, corresponding to a six-dimensional subspace\n \n \n $$\\varvec{V}$$<\/jats:tex-math>\n \n \n V<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n , to determine the entire center difference. An uncorrected disease classification model was highly biased to center-specific effects, creating a falsely inflated performance when applying internal (cross-) validation. The cross-validation performance of the center-harmonized model remained high, while it generalized significantly better to unseen test cohorts. Furthermore, the framework is highly transparent, providing analytic reconstructions of the correction and visualizations of the data in voxel space.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n \n IRMA can be used to learn and disregard center-specific information in features extracted from brain\n \n \n $$^{18}$$<\/jats:tex-math>\n \n \n \n \n 18<\/mml:mn>\n <\/mml:mmultiscripts>\n <\/mml:math>\n <\/jats:alternatives>\n <\/jats:inline-formula>\n F-FDG PET scans, while retaining disease-specific information.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1007\/s00259-025-07114-4","type":"journal-article","created":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T05:55:34Z","timestamp":1739858134000},"page":"2941-2958","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["IRMA: Machine learning-based harmonization of $$^{18}$$F-FDG PET brain scans in multi-center studies"],"prefix":"10.1007","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8219-6590","authenticated-orcid":false,"given":"S.S.","family":"L\u00f6vdal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"van Veen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G.","family":"Carli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. J.","family":"Renken","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"T.","family":"Shiner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N.","family":"Bregman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Orad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.","family":"Arnaldi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B.","family":"Orso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S.","family":"Morbelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"P.","family":"Mattioli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K. L.","family":"Leenders","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R.","family":"Dierckx","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"S. K.","family":"Meles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M.","family":"Biehl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"for\u00a0the\u00a0Alzheimer\u2019s\u00a0Disease\u00a0Neuroimaging\u00a0Initiative","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,2,18]]},"reference":[{"key":"7114_CR1","doi-asserted-by":"crossref","unstructured":"Brendel M, Guedj E, Yakushev I, Morbelli S, H\u00f6glinger GU, Tolboom N, Verger A, Albert NL, Cecchin D, Fernandez PA, et al. Neuroimaging biomarkers in the biological definition of Parkinson\u2019s disease and dementia with Lewy bodies-EANM position on current state, unmet needs and future perspectives. Eur J Nucl Med Mol Imaging. 2024:1\u20135.","DOI":"10.1007\/s00259-024-06803-w"},{"key":"7114_CR2","doi-asserted-by":"crossref","unstructured":"Guedj E, Varrone A, Boellaard R, Albert NL, Barthel H, Berckel B, Brendel M, Cecchin D, Ekmekcioglu O, Garibotto V, et al. EANM procedure guidelines for brain PET imaging using [18 F] FDG, version 3. Eur J Nucl Med Mol Imaging. 2022:1\u201320.","DOI":"10.1007\/s00259-022-05755-3"},{"issue":"9","key":"7114_CR3","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1097\/RLU.0000000000004251","volume":"47","author":"BJ Burkett","year":"2022","unstructured":"Burkett BJ, Babcock JC, Lowe VJ, Graff-Radford J, Subramaniam RM, Johnson DR. PET imaging of dementia: update 2022. Clin Nucl Med. 2022;47(9):763\u201373.","journal-title":"Clin Nucl Med"},{"key":"7114_CR4","doi-asserted-by":"publisher","first-page":"1534","DOI":"10.1007\/s00259-018-4031-2","volume":"45","author":"Z Walker","year":"2018","unstructured":"Walker Z, Gandolfo F, Orini S, Garibotto V, Agosta F, Arbizu J, Bouwman F, Drzezga A, Nestor P, Boccardi M, et al. Clinical utility of FDG PET in Parkinson\u2019s disease and atypical parkinsonism associated with dementia. Eur J Nucl Med Mol Imaging. 2018;45:1534\u201345.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"5","key":"7114_CR5","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1212\/WNL.0000000000002923","volume":"87","author":"CR Jack Jr","year":"2016","unstructured":"Jack CR Jr, Bennett DA, Blennow K, Carrillo MC, Feldman HH, Frisoni GB, Hampel H, Jagust WJ, Johnson KA, Knopman DS, et al. A\/T\/N: An unbiased descriptive classification scheme for Alzheimer disease biomarkers. Neurology. 2016;87(5):539\u201347.","journal-title":"Neurology"},{"issue":"2","key":"7114_CR6","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/S1474-4422(23)00404-0","volume":"23","author":"GU H\u00f6glinger","year":"2024","unstructured":"H\u00f6glinger GU, Adler CH, Berg D, Klein C, Outeiro TF, Poewe W, Postuma R, Stoessl AJ, Lang AE. A biological classification of Parkinson\u2019s disease: the SynNeurGe research diagnostic criteria. Lancet Neurol. 2024;23(2):191\u2013204.","journal-title":"Lancet Neurol"},{"issue":"3","key":"7114_CR7","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1109\/TBME.2015.2466616","volume":"63","author":"X Zhu","year":"2015","unstructured":"Zhu X, Suk H-I, Lee S-W, Shen D. Subspace regularized sparse multitask learning for multiclass neurodegenerative disease identification. IEEE Trans Biomed Eng. 2015;63(3):607\u201318.","journal-title":"IEEE Trans Biomed Eng"},{"key":"7114_CR8","doi-asserted-by":"crossref","unstructured":"Mudali D, Biehl M, Leenders KL, Roerdink JB. LVQ and SVM classification of FDG-PET brain data. In: Advances in Self-Organizing Maps and Learning Vector Quantization: Proceedings of the 11th International Workshop WSOM 2016, Houston, Texas, USA, January 6-8, 2016. 2016. pp. 205\u2013215. Springer.","DOI":"10.1007\/978-3-319-28518-4_18"},{"key":"7114_CR9","doi-asserted-by":"crossref","unstructured":"van Veen R, Meles SK, Renken RJ, Reesink FE, Oertel WH, Janzen A, De Vries G-J, Leenders KL, Biehl M. FDG-PET combined with Learning Vector Quantization allows classification of neurodegenerative diseases and reveals the trajectory of idiopathic REM sleep behavior disorder. Comput Methods Programs Biomed. 2022;225:107042.","DOI":"10.1016\/j.cmpb.2022.107042"},{"key":"7114_CR10","doi-asserted-by":"publisher","first-page":"1005731","DOI":"10.3389\/fnagi.2022.1005731","volume":"14","author":"M Perovnik","year":"2022","unstructured":"Perovnik M, Vo A, Nguyen N, Jam\u0161ek J, Rus T, Tang CC, Tro\u0161t M, Eidelberg D. Automated differential diagnosis of dementia syndromes using FDG PET and machine learning. Front Aging Neurosci. 2022;14:1005731.","journal-title":"Front Aging Neurosci"},{"key":"7114_CR11","doi-asserted-by":"crossref","unstructured":"Kogan RV, De Jong BA, Renken RJ, Meles SK, Van Snick PJ, Golla S, Rijnsdorp S, Perani D, Leenders KL, Boellaard R, et al. Factors affecting the harmonization of disease-related metabolic brain pattern expression quantification in [18F] FDG-PET (PETMETPAT). Alzheimer\u2019s Dement: Diagn Assess Dis Monit. 2019;11:472\u201382.","DOI":"10.1016\/j.dadm.2019.04.002"},{"key":"7114_CR12","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.ejmp.2017.01.018","volume":"41","author":"P Tom\u0161e","year":"2017","unstructured":"Tom\u0161e P, Jensterle L, Rep S, Grmek M, Zaletel K, Eidelberg D, Dhawan V, Ma Y, Tro\u0161t M. The effect of 18F-FDG-PET image reconstruction algorithms on the expression of characteristic metabolic brain network in Parkinson\u2019s disease. Phys Med. 2017;41:129\u201335.","journal-title":"Phys Med"},{"issue":"Suppl 1","key":"7114_CR13","doi-asserted-by":"publisher","first-page":"11","DOI":"10.2967\/jnumed.108.057182","volume":"50","author":"R Boellaard","year":"2009","unstructured":"Boellaard R. Standards for PET image acquisition and quantitative data analysis. J Nucl Med. 2009;50(Suppl 1):11\u201320.","journal-title":"J Nucl Med"},{"issue":"2","key":"7114_CR14","doi-asserted-by":"publisher","first-page":"451","DOI":"10.3390\/diagnostics12020451","volume":"12","author":"JM Rogasch","year":"2022","unstructured":"Rogasch JM, Hofheinz F, Heek L, Voltin C-A, Boellaard R, Kobe C. Influences on PET quantification and interpretation. Diagnostics. 2022;12(2):451.","journal-title":"Diagnostics"},{"key":"7114_CR15","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/s12149-011-0514-y","volume":"25","author":"I Polycarpou","year":"2011","unstructured":"Polycarpou I, Thielemans K, Manjeshwar R, Aguiar P, Marsden PK, Tsoumpas C. Comparative evaluation of scatter correction in 3D PET using different scatter-level approximations. Ann Nucl Med. 2011;25:643\u20139.","journal-title":"Ann Nucl Med"},{"issue":"11","key":"7114_CR16","doi-asserted-by":"publisher","first-page":"1667","DOI":"10.2967\/jnumed.115.156927","volume":"56","author":"J Yan","year":"2015","unstructured":"Yan J, Chu-Shern JL, Loi HY, Khor LK, Sinha AK, Quek ST, Tham IW, Townsend D. Impact of image reconstruction settings on texture features in 18F-FDG PET. J Nucl Med. 2015;56(11):1667\u201373.","journal-title":"J Nucl Med"},{"issue":"6","key":"7114_CR17","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1016\/j.rcl.2004.08.010","volume":"42","author":"PD Acton","year":"2004","unstructured":"Acton PD, Zhuang H, Alavi A. Quantification in PET. Radiol Clin. 2004;42(6):1055\u201362.","journal-title":"Radiol Clin"},{"key":"7114_CR18","doi-asserted-by":"publisher","first-page":"117229","DOI":"10.1016\/j.neuroimage.2020.117229","volume":"222","author":"FJ L\u00f3pez-Gonz\u00e1lez","year":"2020","unstructured":"L\u00f3pez-Gonz\u00e1lez FJ, Silva-Rodr\u00edguez J, Paredes-Pacheco J, Ni\u00f1erola-Baiz\u00e1n A, Efthimiou N, Mart\u00edn-Mart\u00edn C, Moscoso A, Ruibal \u00c1, Ro\u00e9-Vellv\u00e9 N, Aguiar P. Intensity normalization methods in brain FDG-PET quantification. NeuroImage. 2020;222:117229.","journal-title":"NeuroImage"},{"key":"7114_CR19","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.neuroimage.2013.03.031","volume":"77","author":"F Thiele","year":"2013","unstructured":"Thiele F, Young S, Buchert R, Wenzel F. Voxel-based classification of FDG PET in dementia using inter-scanner normalization. NeuroImage. 2013;77:62\u20139.","journal-title":"NeuroImage"},{"key":"7114_CR20","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1007\/s00259-009-1297-4","volume":"37","author":"R Boellaard","year":"2010","unstructured":"Boellaard R, O\u2019Doherty MJ, Weber WA, Mottaghy FM, Lonsdale MN, Stroobants SG, Oyen WJ, Kotzerke J, Hoekstra OS, Pruim J, et al. FDG PET and PET\/CT: EANM procedure guidelines for tumour PET imaging: version 1.0. Eur J Nucl Med Mol Imaging. 2010;37:181\u2013200.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"7114_CR21","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/s00259-014-2961-x","volume":"42","author":"R Boellaard","year":"2015","unstructured":"Boellaard R, Delgado-Bolton R, Oyen WJ, Giammarile F, Tatsch K, Eschner W, Verzijlbergen FJ, Barrington SF, Pike LC, Weber WA, et al. FDG PET\/CT: EANM procedure guidelines for tumour imaging: version 2.0. Eur J Nucl Med Mol Imaging. 2015;42:328\u201354.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"7114_CR22","doi-asserted-by":"publisher","first-page":"2856","DOI":"10.1007\/s00259-021-05201-w","volume":"48","author":"E Verwer","year":"2021","unstructured":"Verwer E, Golla S, Kaalep A, Lubberink M, Velden F, Bettinardi V, Yaqub M, Sera T, Rijnsdorp S, Lammertsma A, et al. Harmonisation of PET\/CT contrast recovery performance for brain studies. Eur J Nucl Med Mol Imaging. 2021;48:2856\u201370.","journal-title":"Eur J Nucl Med Mol Imaging"},{"issue":"1","key":"7114_CR23","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1186\/s40658-023-00588-x","volume":"10","author":"M Shekari","year":"2023","unstructured":"Shekari M, Verwer EE, Yaqub M, Daamen M, Buckley C, Frisoni GB, Visser PJ, Farrar G, Barkhof F, Gispert JD, et al. Harmonization of brain PET images in multi-center PET studies using Hoffman phantom scan. EJNMMI Phys. 2023;10(1):68.","journal-title":"EJNMMI Phys"},{"key":"7114_CR24","doi-asserted-by":"crossref","unstructured":"Hoffman EJ, Cutler PD, Guerrero TM, Digby WM, Mazziotta JC. Assessment of accuracy of PET utilizing a 3-D phantom to simulate the activity distribution of [18F] fluorodeoxyglucose uptake in the human brain. J Cereb Blood Flow Metab. 1991;11(1_suppl):17\u201325.","DOI":"10.1038\/jcbfm.1991.32"},{"issue":"1","key":"7114_CR25","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1093\/biostatistics\/kxj037","volume":"8","author":"WE Johnson","year":"2007","unstructured":"Johnson WE, Li C, Rabinovic A. Adjusting batch effects in microarray expression data using empirical Bayes methods. Biostatistics. 2007;8(1):118\u201327.","journal-title":"Biostatistics"},{"issue":"8","key":"7114_CR26","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.2967\/jnumed.117.199935","volume":"59","author":"F Orlhac","year":"2018","unstructured":"Orlhac F, Boughdad S, Philippe C, Stalla-Bourdillon H, Nioche C, Champion L, Soussan M, Frouin F, Frouin V, Buvat I. A postreconstruction harmonization method for multicenter radiomic studies in PET. J Nucl Med. 2018;59(8):1321\u20138.","journal-title":"J Nucl Med"},{"key":"7114_CR27","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.neuroimage.2017.11.024","volume":"167","author":"J-P Fortin","year":"2018","unstructured":"Fortin J-P, Cullen N, Sheline YI, Taylor WD, Aselcioglu I, Cook PA, Adams P, Cooper C, Fava M, McGrath PJ, et al. Harmonization of cortical thickness measurements across scanners and sites. NeuroImage. 2018;167:104\u201320.","journal-title":"NeuroImage"},{"key":"7114_CR28","doi-asserted-by":"publisher","first-page":"118703","DOI":"10.1016\/j.neuroimage.2021.118703","volume":"245","author":"ME Torbati","year":"2021","unstructured":"Torbati ME, Minhas DS, Ahmad G, O\u2019Connor EE, Muschelli J, Laymon CM, Yang Z, Cohen AD, Aizenstein HJ, Klunk WE, et al. A multi-scanner neuroimaging data harmonization using RAVEL and ComBat. NeuroImage. 2021;245:118703.","journal-title":"NeuroImage"},{"key":"7114_CR29","doi-asserted-by":"crossref","unstructured":"Beer JC, Tustison NJ, Cook PA, Davatzikos C, Sheline YI, Shinohara RT, Linn KA, ADNI Initiative, et al. Longitudinal ComBat: A method for harmonizing longitudinal multi-scanner imaging data. NeuroImage. 2020;220:117129.","DOI":"10.1016\/j.neuroimage.2020.117129"},{"issue":"2","key":"7114_CR30","doi-asserted-by":"publisher","first-page":"172","DOI":"10.2967\/jnumed.121.262464","volume":"63","author":"F Orlhac","year":"2022","unstructured":"Orlhac F, Eertink JJ, Cottereau A-S, Zijlstra JM, Thieblemont C, Meignan M, Boellaard R, Buvat I. A guide to ComBat harmonization of imaging biomarkers in multicenter studies. J Nucl Med. 2022;63(2):172\u20139.","journal-title":"J Nucl Med"},{"issue":"6","key":"7114_CR31","doi-asserted-by":"publisher","first-page":"2557","DOI":"10.1093\/brain\/awad059","volume":"146","author":"JL Robinson","year":"2023","unstructured":"Robinson JL, Xie SX, Baer DR, Suh E, Van Deerlin VM, Loh NJ, Irwin DJ, McMillan CT, Wolk DA, Chen-Plotkin A, et al. Pathological combinations in neurodegenerative disease are heterogeneous and disease-associated. Brain. 2023;146(6):2557\u201369.","journal-title":"Brain"},{"issue":"1","key":"7114_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-024-49402-x","volume":"15","author":"SE Mastenbroek","year":"2024","unstructured":"Mastenbroek SE, Vogel JW, Collij LE, Serrano GE, Tremblay C, Young AL, Arce RA, Shill HA, Driver-Dunckley ED, Mehta SH, et al. Disease progression modelling reveals heterogeneity in trajectories of Lewy-type $$\\alpha $$-synuclein pathology. Nat Commun. 2024;15(1):1\u201315.","journal-title":"Nat Commun"},{"key":"7114_CR33","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.patcog.2019.01.046","volume":"91","author":"JV Psutka","year":"2019","unstructured":"Psutka JV, Psutka J. Sample size for maximum-likelihood estimates of gaussian model depending on dimensionality of pattern space. Pattern Recognit. 2019;91:25\u201333.","journal-title":"Pattern Recognit"},{"key":"7114_CR34","doi-asserted-by":"publisher","first-page":"3432","DOI":"10.1007\/s00259-021-05303-5","volume":"48","author":"M Ferreira","year":"2021","unstructured":"Ferreira M, Lovinfosse P, Hermesse J, Decuypere M, Rousseau C, Lucia F, Schick U, Reinhold C, Robin P, Hatt M, et al. [18 F] FDG PET radiomics to predict disease-free survival in cervical cancer: A multi-scanner\/center study with external validation. Eur J Nucl Med Mol Imaging. 2021;48:3432\u201343.","journal-title":"Eur J Nucl Med Mol Imaging"},{"key":"7114_CR35","doi-asserted-by":"crossref","unstructured":"van Veen R, Tamboli NRB, L\u00f6vdal S, Meles SK, Renken RJ, De Vries G-J, Arnaldi D, Morbelli S, Clavero P, Obeso JA, et al. Subspace corrected relevance learning with application in neuroimaging. Artif Intell Med. 2024:102786.","DOI":"10.1016\/j.artmed.2024.102786"},{"key":"7114_CR36","doi-asserted-by":"publisher","unstructured":"L\u00f6vdal S, Biehl M. Improved interpretation of feature relevances: Iterated Relevance Matrix Analysis (IRMA). In: Proceedings of the European Symposium on Artificial Neural Networks, Machine Learning and Computational Intelligence. 2023. pp. 54\u201364. https:\/\/doi.org\/10.14428\/esann\/2023.ES2023-127. ESANN.","DOI":"10.14428\/esann\/2023.ES2023-127"},{"key":"7114_CR37","doi-asserted-by":"publisher","first-page":"127367","DOI":"10.1016\/j.neucom.2024.127367","volume":"577","author":"S L\u00f6vdal","year":"2024","unstructured":"L\u00f6vdal S, Biehl M. Iterated Relevance Matrix Analysis (IRMA) for the identification of class-discriminative subspaces. Neurocomputing. 2024;577:127367.","journal-title":"Neurocomputing"},{"key":"7114_CR38","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.parkreldis.2022.05.024","volume":"100","author":"KA Jellinger","year":"2022","unstructured":"Jellinger KA. Are there morphological differences between Parkinson\u2019s disease-dementia and dementia with Lewy bodies? Parkinsonism Relat Disord. 2022;100:24\u201332.","journal-title":"Parkinsonism Relat Disord"},{"key":"7114_CR39","unstructured":"Kohonen T. Learning Vector Quantization for pattern recognition. Rep. Technical report, TKK-F-A601. Lab Comput Inform Sci. 1986;18."},{"key":"7114_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-97966-8","volume-title":"Self-Organizing Maps","author":"T Kohonen","year":"1997","unstructured":"Kohonen T. Self-Organizing Maps. Berlin, Germany: Springer; 1997."},{"key":"7114_CR41","doi-asserted-by":"crossref","unstructured":"Kohonen, T. Improved versions of Learning Vector Quantization. In: IJCNN International Joint Conference on Neural Networks. 1990. pp. 545\u2013550. IEEE.","DOI":"10.1109\/IJCNN.1990.137622"},{"key":"7114_CR42","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1007\/s00521-013-1535-3","volume":"25","author":"D Nova","year":"2014","unstructured":"Nova D, Estevez PE. A review of Learning Vector Quantization classifiers. Neural Comput Appl. 2014;25:511\u201324.","journal-title":"Neural Comput Appl"},{"key":"7114_CR43","unstructured":"Sato AS, Yamada K. Generalized Learning Vector Quantization. In: Tesauro G, Touretzky D, Leen T, editors. Advances in Neural Information Processing Systems. 1995. vol. 7, pp. 423\u2013429."},{"issue":"12","key":"7114_CR44","doi-asserted-by":"publisher","first-page":"3532","DOI":"10.1162\/neco.2009.11-08-908","volume":"21","author":"P Schneider","year":"2009","unstructured":"Schneider P, Biehl M, Hammer B. Adaptive relevance matrices in Learning Vector Quantization. Neural Comput. 2009;21(12):3532\u201361.","journal-title":"Neural Comput"},{"key":"7114_CR45","doi-asserted-by":"crossref","unstructured":"Biehl M, Hammer B, Schleif F-M, Schneider P, Villmann T. Stationarity of matrix relevance LVQ. In: 2015 International Joint Conference on Neural Networks (IJCNN). 2015. pp. 1\u20138. IEEE.","DOI":"10.1109\/IJCNN.2015.7280441"},{"key":"7114_CR46","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.nicl.2014.06.007","volume":"5","author":"L Teune","year":"2014","unstructured":"Teune L, Renken R, De Jong B, Willemsen A, Van Osch M, Roerdink J, Dierckx R, Leenders K. Parkinson\u2019s disease-related perfusion and glucose metabolic brain patterns identified with PCASL-MRI and FDG-PET imaging. NeuroImage: Clinical. 2014;5:240\u20134.","journal-title":"NeuroImage: Clinical"},{"issue":"10","key":"7114_CR47","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1002\/mds.27094","volume":"32","author":"SK Meles","year":"2017","unstructured":"Meles SK, Vadasz D, Renken RJ, Sittig-Wiegand E, Mayer G, Depboylu C, Reetz K, Overeem S, Pijpers A, Reesink FE, et al. FDG PET, dopamine transporter SPECT, and olfaction: combining biomarkers in REM sleep behavior disorder. Mov Disord. 2017;32(10):1482\u20136.","journal-title":"Mov Disord"},{"key":"7114_CR48","doi-asserted-by":"crossref","unstructured":"Meles SK, Kok JG, De Jong BM, Renken RJ, De Vries JJ, Spikman JM, Ziengs AL, Willemsen AT, Horn HJ, Leenders KL, et al. The cerebral metabolic topography of spinocerebellar ataxia type 3. NeuroImage: Clinical. 2018;19:90\u20137.","DOI":"10.1016\/j.nicl.2018.03.038"},{"key":"7114_CR49","doi-asserted-by":"crossref","unstructured":"Peretti DE, Renken RJ, Reesink FE, De Jong BM, De Deyn PP, Dierckx RA, Doorduin J, Boellaard R, Garc\u00eda DV. Feasibility of pharmacokinetic parametric PET images in scaled subprofile modelling using principal component analysis. NeuroImage: Clinical. 2021;30:102625.","DOI":"10.1016\/j.nicl.2021.102625"},{"issue":"10","key":"7114_CR50","doi-asserted-by":"publisher","first-page":"2293","DOI":"10.1002\/mds.28654","volume":"36","author":"B Orso","year":"2021","unstructured":"Orso B, Arnaldi D, Girtler N, Brugnolo A, Doglione E, Mattioli P, Biassoni E, Fancellu R, Massa F, Bauckneht M, et al. Dopaminergic and serotonergic degeneration and cortical [18F] fluorodeoxyglucose positron emission tomography in de novo Parkinson\u2019s disease. Mov Disord. 2021;36(10):2293\u2013302.","journal-title":"Mov Disord"},{"key":"7114_CR51","doi-asserted-by":"crossref","unstructured":"Mattioli P, Pardini M, Fam\u00e0 F, Girtler N, Brugnolo A, Orso B, Meli R, Filippi L, Grisanti S, Massa F, et al. Cuneus\/precuneus as a central hub for brain functional connectivity of mild cognitive impairment in idiopathic REM sleep behavior patients. Eur J Nucl Med Mol Imaging. 2021;48:2834\u201345.","DOI":"10.1007\/s00259-021-05205-6"},{"key":"7114_CR52","doi-asserted-by":"crossref","unstructured":"L\u00f6vdal S, Carli G, Orso B, Biehl M, Arnaldi D, Mattioli P, Janzen A, Sittig E, Morbelli S, Booij J, et al. Investigating the aspect of asymmetry in brain-first versus body-first Parkinson\u2019s disease. Npj Parkinsons Dis. 2024;10(1):74.","DOI":"10.1038\/s41531-024-00685-3"},{"issue":"12","key":"7114_CR53","doi-asserted-by":"publisher","first-page":"1591","DOI":"10.1002\/mds.26424","volume":"30","author":"RB Postuma","year":"2015","unstructured":"Postuma RB, Berg D, Stern M, Poewe W, Olanow CW, Oertel W, Obeso J, Marek K, Litvan I, Lang AE, et al. Mds clinical diagnostic criteria for Parkinson\u2019s disease. Mov Disord. 2015;30(12):1591\u2013601.","journal-title":"Mov Disord"},{"issue":"7","key":"7114_CR54","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1212\/WNL.34.7.939","volume":"34","author":"G McKhann","year":"1984","unstructured":"McKhann G, Drachman D, Folstein M, Katzman R, Price D, Stadlan EM. Clinical diagnosis of Alzheimer\u2019s disease: Report of the nincds-adrda work group* under the auspices of department of health and human services task force on Alzheimer\u2019s disease. Neurology. 1984;34(7):939\u2013939.","journal-title":"Neurology"},{"issue":"1","key":"7114_CR55","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1212\/WNL.0000000000004058","volume":"89","author":"IG McKeith","year":"2017","unstructured":"McKeith IG, Boeve BF, Dickson DW, Halliday G, Taylor J-P, Weintraub D, Aarsland D, Galvin J, Attems J, Ballard CG, et al. Diagnosis and management of dementia with lewy bodies: Fourth consensus report of the dlb consortium. Neurology. 2017;89(1):88\u2013100.","journal-title":"Neurology"},{"issue":"4","key":"7114_CR56","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.jalz.2018.02.018","volume":"14","author":"CR Jack Jr","year":"2018","unstructured":"Jack CR Jr, Bennett DA, Blennow K, Carrillo MC, Dunn B, Haeberlein SB, Holtzman DM, Jagust W, Jessen F, Karlawish J, et al. Nia-aa research framework: toward a biological definition of Alzheimer\u2019s disease. Alzheimers Dement. 2018;14(4):535\u201362.","journal-title":"Alzheimers Dement"},{"issue":"1","key":"7114_CR57","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1006\/nimg.2001.0978","volume":"15","author":"N Tzourio-Mazoyer","year":"2002","unstructured":"Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, Mazoyer B, Joliot M. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage. 2002;15(1):273\u201389.","journal-title":"NeuroImage"},{"key":"7114_CR58","doi-asserted-by":"crossref","unstructured":"Brodersen KH, Ong CS, Stephan KE, Buhmann JM. The balanced accuracy and its posterior distribution. In: 2010 20th International Conference on Pattern Recognition. 2010. pp. 3121\u20133124. IEEE.","DOI":"10.1109\/ICPR.2010.764"},{"issue":"6","key":"7114_CR59","doi-asserted-by":"publisher","first-page":"2008","DOI":"10.1137\/S1064827500377332","volume":"23","author":"AV Knyazev","year":"2002","unstructured":"Knyazev AV, Argentati ME. Principal angles between subspaces in an A-based scalar product: algorithms and perturbation estimates. SIAM J Sci Comput. 2002;23(6):2008\u201340.","journal-title":"SIAM J Sci Comput"},{"issue":"1","key":"7114_CR60","first-page":"10499","volume":"22","author":"R Van Veen","year":"2021","unstructured":"Van Veen R, Biehl M, De Vries G-J. sklvq: Scikit learning vector quantization. J Mach Learn Res. 2021;22(1):10499\u2013504.","journal-title":"J Mach Learn Res"},{"key":"7114_CR61","doi-asserted-by":"crossref","unstructured":"Carli G, Meles SK, Reesink FE, de Jong BM, Pilotto A, Padovani A, Galbiati A, Ferini-Strambi L, Leenders KL, Perani D. Comparison of univariate and multivariate analyses for brain [18F] FDG PET data in $$\\alpha $$-synucleinopathies. NeuroImage: Clinical. 2023;39:103475.","DOI":"10.1016\/j.nicl.2023.103475"},{"key":"7114_CR62","doi-asserted-by":"crossref","unstructured":"Haberl D, Spielvogel CP, Jiang Z, Orlhac F, Iommi D, Carri\u00f3 I, Buvat I, Haug AR, Papp L. Multicenter PET image harmonization using generative adversarial networks. Eur J Nucl Med Mol Imaging. 2024:1\u201315.","DOI":"10.1007\/s00259-024-06708-8"},{"issue":"3","key":"7114_CR63","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1212\/WNL.0b013e3181cb3e25","volume":"74","author":"RC Petersen","year":"2010","unstructured":"Petersen RC, Aisen PS, Beckett LA, Donohue MC, Gamst AC, Harvey DJ, Jack C Jr, Jagust WJ, Shaw LM, Toga AW, et al. Alzheimer\u2019s disease neuroimaging initiative (adni) clinical characterization. Neurology. 2010;74(3):201\u20139.","journal-title":"Neurology"}],"container-title":["European Journal of Nuclear Medicine and Molecular Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-025-07114-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00259-025-07114-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00259-025-07114-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T03:05:01Z","timestamp":1749697501000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00259-025-07114-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,18]]},"references-count":63,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["7114"],"URL":"https:\/\/doi.org\/10.1007\/s00259-025-07114-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5825843\/v1","asserted-by":"object"}]},"ISSN":["1619-7070","1619-7089"],"issn-type":[{"value":"1619-7070","type":"print"},{"value":"1619-7089","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,18]]},"assertion":[{"value":"16 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The local ethical committees approved the studies included in this retrospective work, and informed consent was obtained from all participants or their informed caregivers.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"D.A. received speaker honoraria from Idorsia, Bioprojet, Bruno, Italfarmaco, Lundbeck, PIAM, Fidia, and Valeas. The authors declare no additional competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}