{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T21:03:37Z","timestamp":1774645417420,"version":"3.50.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T00:00:00Z","timestamp":1681171200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017501","name":"Science-Health Joint Medical Scientific Research Project of Chongqing","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017501","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>To construct a machine learning model based on radiomics of multiparametric magnetic resonance imaging (MRI) combined with clinical parameters for predicting Sonic Hedgehog (SHH) and Group 4 (G4) molecular subtypes of pediatric medulloblastoma (MB).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>The preoperative MRI images and clinical data of 95 patients with MB were retrospectively analyzed, including 47 cases of SHH subtype and 48 cases of G4 subtype. Radiomic features were extracted from T1-weighted imaging (T1), contrast-enhanced T1 weighted imaging (T1c), T2-weighted imaging (T2), T2 fluid-attenuated inversion recovery imaging (T2FLAIR), and apparent diffusion coefficient (ADC) maps, using variance thresholding, SelectKBest, and Least Absolute Shrinkage and Selection Operator (LASSO) regression algorithms. The optimal features were filtered using LASSO regression, and a logistic regression (LR) algorithm was used to build a machine learning model. The receiver operator characteristic (ROC) curve was plotted to evaluate the prediction accuracy, and verified by its calibration, decision and nomogram. The Delong test was used to compare the differences between different models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>A total of 17 optimal features, with non-redundancy and high correlation, were selected from 7,045 radiomics features, and used to build an LR model. The model showed a classification accuracy with an under the curve (AUC) of 0.960 (95% CI: 0.871\u22121.000) in the training cohort and 0.751 (95% CI: 0.587\u22120.915) in the testing cohort, respectively. The location of the tumor, pathological type, and hydrocephalus status of the two subtypes of patients differed significantly (<jats:italic>p<\/jats:italic> &amp;lt; 0.05). When combining radiomics features and clinical parameters to construct the combined prediction model, the AUC improved to 0.965 (95% CI: 0.898\u22121.000) in the training cohort and 0.849 (95% CI: 0.695\u22121.000) in the testing cohort, respectively. There was a significant difference in the prediction accuracy, as measured by AUC, between the testing cohorts of the two prediction models, which was confirmed by Delong\u2019s test (<jats:italic>p<\/jats:italic> = 0.0144). Decision curves and nomogram further validate that the combined model can achieve net benefits in clinical work.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The combined prediction model, constructed based on radiomics of multiparametric MRI and clinical parameters can potentially provide a non-invasive clinical approach to predict SHH and G4 molecular subtypes of MB preoperatively.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2023.1157858","type":"journal-article","created":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T05:15:14Z","timestamp":1681190114000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Preoperative prediction of sonic hedgehog and group 4 molecular subtypes of pediatric medulloblastoma based on radiomics of multiparametric MRI combined with clinical parameters"],"prefix":"10.3389","volume":"17","author":[{"given":"Yuanlin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longlun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihong","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjiao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zanyong","family":"Tong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Jing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lusheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuting","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,4,11]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s13311-017-0526-y","article-title":"Medulloblastoma: molecular classification-based personal therapeutics.","volume":"14","author":"Archer","year":"2017","journal-title":"Neurotherapeutics"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255500","article-title":"Magnetic resonance radiomics features and prognosticators in different molecular subtypes of pediatric medulloblastoma.","volume":"16","author":"Chang","year":"2021","journal-title":"PLoS One"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2368","DOI":"10.1007\/s00330-020-07250-5","article-title":"Radiomics using CT images for preoperative prediction of futile resection in intrahepatic cholangiocarcinoma.","volume":"31","author":"Chu","year":"2021","journal-title":"Eur. Radiol."},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1177\/1756286418775375","article-title":"MRI features as a helpful tool to predict the molecular subgroups of medulloblastoma: state of the art.","volume":"11","author":"Colafati","year":"2018","journal-title":"Ther. Adv. Neurol. Disord."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1186\/s43046-021-00060-w","article-title":"Medulloblastoma: clinicopathological parameters, risk stratification, and survival analysis of immunohistochemically validated molecular subgroups.","volume":"33","author":"Eid","year":"2021","journal-title":"J. Egypt. Natl. Canc. Inst."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14092285","article-title":"New developments in the pathogenesis, therapeutic targeting, and treatment of pediatric medulloblastoma.","volume":"14","author":"Fang","year":"2022","journal-title":"Cancers"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2595","DOI":"10.1007\/s00247-022-05411-w","article-title":"The role of apparent diffusion coefficient histogram metrics for differentiating pediatric medulloblastoma histological variants and molecular groups.","volume":"52","author":"Gon\u00e7alves","year":"2022","journal-title":"Pediatr. Radiol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1002\/med.21846","article-title":"A review in radiomics: making personalized medicine a reality via routine imaging.","volume":"42","author":"Guiot","year":"2022","journal-title":"Med. Res. Rev."},{"key":"B9","doi-asserted-by":"publisher","first-page":"497","DOI":"10.2214\/AJR.18.20623","article-title":"Radiomics in pulmonary lesion imaging.","volume":"212","author":"Hassani","year":"2019","journal-title":"Am. J. Roentgenol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s41586-019-1434-6","article-title":"Resolving medulloblastoma cellular architecture by single-cell genomics.","volume":"572","author":"Hovestadt","year":"2019","journal-title":"Nature"},{"key":"B11","doi-asserted-by":"publisher","first-page":"154","DOI":"10.3174\/ajnr.A5899","article-title":"MR imaging-based radiomic signatures of distinct molecular subgroups of medulloblastoma.","volume":"40","author":"Iv","year":"2019","journal-title":"Am. J. Neuroradiol."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1177\/02841851221143496","article-title":"Radiomics-based machine learning models for prediction of medulloblastoma subgroups: a systematic review and meta-analysis of the diagnostic test performance.","author":"Karabacak","year":"2022","journal-title":"Acta Radiol."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.4103\/1793-5482.151516","article-title":"Medulloblastoma: a common pediatric tumor: prognostic factors and predictors of outcome.","volume":"10","author":"Kumar","year":"2015","journal-title":"Asian J. Neurosurg."},{"key":"B14","doi-asserted-by":"publisher","first-page":"3757","DOI":"10.21037\/tcr-21-1277","article-title":"Bibliometrics research on radiomics of lung cancer.","volume":"10","author":"Liang","year":"2021","journal-title":"Transl. Cancer Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1007\/s00401-016-1545-1","article-title":"The 2016 World Health Organization classification of tumors of the central nervous system: a summary.","volume":"131","author":"Louis","year":"2016","journal-title":"<underline>Acta Neuropathol.<\/underline>"},{"key":"B16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.critrevonc.2016.05.012","article-title":"Childhood medulloblastoma.","volume":"105","author":"Massimino","year":"2016","journal-title":"Crit. Rev. Oncol. Hematol."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1038\/s41572-019-0063-6","article-title":"Medulloblastoma.","volume":"5","author":"Northcott","year":"2019","journal-title":"Nat. Rev. Dis. Primers"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1001\/archneur.65.11.1419","article-title":"Management of and prognosis with medulloblastoma: therapy at a crossroads.","volume":"65","author":"Packer","year":"2008","journal-title":"Arch. Neurol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1007\/s00401-016-1569-6","article-title":"Risk stratification of childhood medulloblastoma in the molecular era: the current consensus.","volume":"131","author":"Ramaswamy","year":"2016","journal-title":"Acta Neuropathol."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20211359","article-title":"Machine-learning approach to predict molecular subgroups of medulloblastoma using multiparametric MRI-based tumor radiomics.","volume":"95","author":"Saju","year":"2022","journal-title":"Br. J. Radiol."},{"key":"B21","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/s00401-011-0922-z","article-title":"Molecular subgroups of medulloblastoma: the current consensus.","volume":"123","author":"Taylor","year":"2012","journal-title":"Acta Neuropathol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11060-018-2906-5","article-title":"The clinical importance of medulloblastoma extent of resection: a systematic review.","volume":"139","author":"Thompson","year":"2018","journal-title":"J. Neurooncol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/S1470-2045(15)00581-1","article-title":"Prognostic value of medulloblastoma extent of resection after accounting for molecular subgroup: a retrospective integrated clinical and molecular analysis.","volume":"17","author":"Thompson","year":"2016","journal-title":"Lancet Oncol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1016\/S1470-2045(18)30242-0","article-title":"Spectrum and prevalence of genetic predisposition in medulloblastoma: a retrospective genetic study and prospective validation in a clinical trial cohort.","volume":"19","author":"Waszak","year":"2018","journal-title":"Lancet Oncol."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.558162","article-title":"Radiomic features from multi-parameter MRI combined with clinical parameters predict molecular subgroups in patients with medulloblastoma.","volume":"10","author":"Yan","year":"2020","journal-title":"Front. Oncol."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.657288","article-title":"Preoperative prediction of meningioma consistency via machine learning-based radiomics.","volume":"11","author":"Zhai","year":"2021","journal-title":"Front. Oncol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1148\/radiol.212137","article-title":"MRI radiogenomics of pediatric medulloblastoma: a multicenter study.","volume":"304","author":"Zhang","year":"2022","journal-title":"Radiology"},{"key":"B28","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1093\/neuonc\/now050","article-title":"Molecular subgroups of adult medulloblastoma: a long-term single-institution study.","volume":"18","author":"Zhao","year":"2016","journal-title":"Neuro Oncol."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1157858\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,11]],"date-time":"2023-04-11T05:15:21Z","timestamp":1681190121000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1157858\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,11]]},"references-count":28,"alternative-id":["10.3389\/fnins.2023.1157858"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2023.1157858","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,11]]},"article-number":"1157858"}}