{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:25:38Z","timestamp":1787030738191,"version":"build-2736575974"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Differentiating tumor from treatment-related changes (TRC) remains a key challenge in post-treatment glioblastoma (GBM) monitoring, as both can exhibit overlapping enhancement and FLAIR abnormalities on standard MRI. Our goal was to build and internally validate an explainable, calibrated, multiparametric MRI radiomics model to distinguish between tumor and treatment effects.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively included patients from the UCSD-PTGBM cohort who had post-treatment GBM MRI examinations with available reference labels for tumor-positive disease (TP) or TRC. Examinations were eligible when contrast-enhanced T1-weighted imaging, FLAIR, ADC, DSC perfusion imaging, and corresponding tumor segmentation masks were available. After applying the eligibility and exclusion criteria, the final study cohort comprised 168 patients with 224 MRI examinations, 173 TP and 51 TRC cases. Radiomic features were extracted from all four MRI sequences. Feature selection and hyperparameter tuning were performed exclusively on the training data before evaluating the model on the test set. Performance metrics, calibration, decision curve analysis, and SHAP-based interpretability were assessed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The extra trees classifier trained on the top 50 radiomic features demonstrated strong performance on the held-out test set, with an AUC of 0.887, PR-AUC of 0.952, balanced accuracy of 83.7%, sensitivity of 75.0%, and specificity of 92.3%. Platt calibration improved the Brier score from 0.229 to 0.132 and the expected calibration error from 0.275 to 0.084. Decision curve analysis indicated a net benefit across relevant clinical thresholds. SHAP analysis revealed balanced contributions from ADC, DSC, T1CE, and FLAIR modalities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>A calibrated and explainable multiparametric MRI radiomics model showed robust internal performance in differentiating tumor from treatment effects in post-treatment GBM. As these findings are hypothesis-generating from an internally validated study, external validation is needed to confirm clinical usefulness and broader applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1890956","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:28:34Z","timestamp":1787027314000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Calibrated and explainable multiparametric MRI radiomics for differentiating tumor positive disease from treatment-related changes in glioblastoma"],"prefix":"10.3389","volume":"16","author":[{"given":"Rafail C.","family":"Christodoulou","sequence":"first","affiliation":[{"name":"Division of Neuroimaging and Neurointervention, Department of Radiology, Stanford University","place":["Stanford, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Vamvouras","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National Technical University of Athens (NTUA)","place":["Athens, Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mateus A.","family":"Esmeraldo","sequence":"additional","affiliation":[{"name":"Department of Radiology, Stanford University","place":["Stanford, CA, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Platon S.","family":"Papageorgiou","sequence":"additional","affiliation":[{"name":"Department of Medicine, National and Kapodistrian University of Athens","place":["Athens, Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evros","family":"Vassiliou","sequence":"additional","affiliation":[{"name":"Department of Biological Sciences, Kean University","place":["Union, NJ, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elena E.","family":"Solomou","sequence":"additional","affiliation":[{"name":"Internal Medicine-Hematology, University of Patras Medical School","place":["Rion, Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sokratis G.","family":"Papageorgiou","sequence":"additional","affiliation":[{"name":"1st Department of Neurology, Medical School, National and Kapodistrian University of Athens, Eginition Hospital","place":["Athens, Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michalis F.","family":"Georgiou","sequence":"additional","affiliation":[{"name":"Department of Radiology, University of Miami","place":["Miami, FL, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms262412162","article-title":"Glioblastoma\u2014a contemporary overview of epidemiology, classification, pathogenesis, diagnosis, and treatment: a review article","volume":"26","author":"Kr\u00f3likowska","year":"2025","journal-title":"Ijms"},{"key":"B2","unstructured":"Current standards of care in glioblastoma therapy\n          \n          \n            \n              Fernandes\n              C\n            \n            \n              Costa\n              A\n            \n            \n              Os\u00f3rio\n              L\n            \n            \n              Lago\n              RC\n            \n            \n              Linhares\n              P\n            \n            \n              Carvalho\n              B\n            \n          \n          Brisbane (AU\n          Codon Publications\n          Glioblastoma\n          \n          2017"},{"key":"B3","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/s00701-025-06681-7","article-title":"Factors associated with poor prognosis in elderly biopsy-only glioblastoma patients","volume":"167","author":"Edriss","year":"2025","journal-title":"Acta Neurochir (Wien)"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa043330","article-title":"Radiotherapy plus concomitant and adjuvant temozolomide for glioblastoma","volume":"352","author":"Stupp","year":"2005","journal-title":"N Engl J Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s11060-017-2375-2","article-title":"Pseudoprogression, radionecrosis, inflammation or true tumor progression? challenges associated with glioblastoma response assessment in an evolving therapeutic landscape","volume":"134","author":"Ellingson","year":"2017","journal-title":"J Neuro-Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/nos307","article-title":"Differentiating tumor recurrence from treatment necrosis: a review of neuro-oncologic imaging strategies","volume":"15","author":"Verma","year":"2013","journal-title":"Neuro Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdae199","article-title":"Deep learning-based postoperative glioblastoma segmentation and extent of resection evaluation: development, external validation, and model comparison","volume":"6","author":"Cepeda","year":"2024","journal-title":"Neuro-Oncol Adv"},{"key":"B8","doi-asserted-by":"publisher","first-page":"18","DOI":"10.2214\/AJR.17.18003","article-title":"Multiparametric MRI for differentiation of radiation necrosis from recurrent tumor in patients with treated glioblastoma","volume":"210","author":"Nael","year":"2018","journal-title":"Am J Roentgenology"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noy133","article-title":"Incorporating diffusion- and perfusion-weighted MRI into a radiomics model improves diagnostic performance for pseudoprogression in glioblastoma patients","volume":"21","author":"Kim","year":"2019","journal-title":"Neuro Oncol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"19","DOI":"10.2214\/AJR.11.7417","article-title":"Treatment-related change versus tumor recurrence in high-grade gliomas: a diagnostic conundrum--use of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI","volume":"198","author":"Fatterpekar","year":"2012","journal-title":"AJR Am J Roentgenol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-09365-3","article-title":"Diffusion-weighted imaging and arterial spin labeling radiomics features may improve differentiation between radiation-induced brain injury and glioma recurrence","volume":"33","author":"Zhang","year":"2023","journal-title":"Eur Radiol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.23.01059","article-title":"RANO 2.0: update to the response assessment in neuro-oncology criteria for high- and low-grade gliomas in adults","volume":"41","author":"Wen","year":"2023","journal-title":"J Clin Oncol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3171\/2022.12.JNS222173","article-title":"Pseudoprogression versus true progression in glioblastoma: what neurosurgeons need to know","volume":"139","author":"Young","year":"2023","journal-title":"J Neurosurg"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A5391","article-title":"Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches","volume":"39","author":"Zhou","year":"2018","journal-title":"AJNR Am J Neuroradiol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2025.103072","article-title":"A systematic review and meta-analysis of deep learning and radiomics in predicting MGMT promoter methylation status in glioblastoma: efficacy, reliability, and clinical implications","volume":"89","author":"Chen","year":"2025","journal-title":"Displays"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/eng6100262","article-title":"Artificial intelligence in glioma diagnosis: a narrative review of radiomics and deep learning for tumor classification and molecular profiling across positron emission tomography and magnetic resonance imaging","volume":"6","author":"Christodoulou","year":"2025","journal-title":"Eng"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2025.43.16_suppl.2074","article-title":"MRI-based radiomics for prediction of isocitrate dehydrogenase subtype in glioblastoma multiforme through artificial intelligence models: a systematic review and meta analysis","volume":"43","author":"Belankar","year":"2025","journal-title":"J Clin Oncol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-025-11401-x","article-title":"Radiomics for differentiating radiation-induced brain injury from recurrence in gliomas: systematic review, meta-analysis, and methodological quality evaluation using METRICS and RQS","volume":"35","author":"Kocak","year":"2025","journal-title":"Eur Radiol"},{"key":"B20","unstructured":"The Cancer Imaging Archive (Tcia)"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdae039","article-title":"Antiangiogenic exclusion rules in glioma trials: historical perspectives and guidance for future trial design","volume":"6","author":"Sener","year":"2024","journal-title":"Neuro-Oncol Adv"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1093\/noajnl\/vdac023","article-title":"Noninvasive differentiation of molecular subtypes of adult nonenhancing glioma using MRI perfusion and diffusion parameters","volume":"4","author":"Pruis","year":"2022","journal-title":"Neuro-Oncol Adv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70056","article-title":"Practical guide to SHAP analysis: explaining supervised machine learning model predictions in drug development","volume":"17","author":"Ponce\u2010Bobadilla","year":"2024","journal-title":"Clin Transl Sci"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A4218","article-title":"Diffusion and perfusion MRI to differentiate treatment-related changes including pseudoprogression from recurrent tumors in high-grade gliomas with histopathologic evidence","volume":"36","author":"Prager","year":"2015","journal-title":"AJNR Am J Neuroradiol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2012.06.011","article-title":"Diffusion-weighted MR imaging for the differentiation of true progression from pseudoprogression following concomitant radiotherapy with temozolomide in patients with newly diagnosed high-grade gliomas","volume":"19","author":"Lee","year":"2012","journal-title":"Acad Radiol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"2913","DOI":"10.1038\/s41598-021-82467-y","article-title":"Differentiation of recurrent glioblastoma from radiation necrosis using diffusion radiomics with machine learning model development and external validation","volume":"11","author":"Park","year":"2021","journal-title":"Sci Rep"},{"key":"B27","doi-asserted-by":"publisher","first-page":"3170","DOI":"10.1038\/s41467-019-11007-0","article-title":"Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma","volume":"10","author":"Elshafeey","year":"2019","journal-title":"Nat Commun"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14153771","article-title":"Tumor progression and treatment-related changes: radiological diagnosis challenges for the evaluation of post treated glioma","volume":"14","author":"Qin","year":"2022","journal-title":"Cancers (Basel)"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2024.100849","article-title":"Systemic inflammatory markers and volume of enhancing tissue on post-contrast T1w MRI images in differentiating true tumor progression from pseudoprogression in high-grade glioma","volume":"49","author":"Satragno","year":"2024","journal-title":"Clin Transl Radiat Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1890956\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:28:35Z","timestamp":1787027315000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1890956\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":29,"alternative-id":["10.3389\/fonc.2026.1890956"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1890956","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"1890956"}}