{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T10:36:49Z","timestamp":1788431809905,"version":"build-2803163510"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T00:00:00Z","timestamp":1776902400000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82371905"],"award-info":[{"award-number":["82371905"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fujian Provincial Finance Project","award":["22SCZZX023"],"award-info":[{"award-number":["22SCZZX023"]}]},{"DOI":"10.13039\/501100017686","name":"Fujian Provincial Health Technology Project","doi-asserted-by":"publisher","award":["2024CXA027"],"award-info":[{"award-number":["2024CXA027"]}],"id":[{"id":"10.13039\/501100017686","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cancer Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>To systematically evaluate and compare the diagnostic efficacy of radiomics models derived from noncontrast CT (NCCT) versus multiparametric MRI in differentiating glioblastoma (GBM) from primary central nervous system lymphoma (PCNSL).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective, multicenter study, 543 patients with pathologically confirmed GBM (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009401) or PCNSL (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009142) were divided into 3 cohorts. 1084 quantitative features were extracted from contrast-enhancing (CE) and non-enhancing (NE) regions across NCCT and five MRI sequences (T2WI, T1WI, ADC, FLAIR, and CE-T1WI). Feature selection employed ANOVA, Kruskal-Wallis test, and recursive feature elimination, followed by nested cross-validation (5-fold outer, 3-fold inner) to construct four machine learning classifiers: support vector machine, linear discriminant analysis, logistic regression, and decision tree. Model performance was rigorously assessed through AUC, accuracy, sensitivity, specificity with bootstrap-derived 95% confidence intervals. The Shapley Additive Explanation (SHAP) analysis was employed to explore the interpretability of models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The CE-T1WI radiomics model demonstrated superior diagnostic capability, with its AUCs of train\/internal test\/external test in CE regions and NE regions were 0.962\/0.963\/0.907 and 0.966\/0.892\/0.867, respectively. Notably, the CT-based model was not significantly different from other MRI models except for CE-T1WI model. The AUCs of train\/internal test\/external test for CT model in CE and NE regions were 0.941\/0.906\/0.822 and 0.902\/0.891 \/0.782, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Both NCCT and multiparametric MRI are valuable in identifying GBM and PCNSL. The CE-T1WI radiomics model has the best diagnostic efficacy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s40644-026-01018-8","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:48:09Z","timestamp":1773694089000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: CT vs MRI"],"prefix":"10.1186","volume":"26","author":[{"given":"Feifei","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhui","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoye","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujie","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youquan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dairong","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jieyun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"1018_CR1","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1001\/jama.2023.0023","volume":"3297","author":"LR Schaff","year":"2023","unstructured":"Schaff LR, Mellinghoff IK. Glioblastoma and Other Primary Brain Malignancies in Adults: A Review. JAMA. 2023;3297:574\u201387.","journal-title":"JAMA"},{"key":"1018_CR2","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1186\/s13046-022-02349-7","volume":"411","author":"L Rong","year":"2022","unstructured":"Rong L, Li N, Zhang Z. Emerging therapies for glioblastoma: current state and future directions. J Exp Clin Cancer Res. 2022;411:142.","journal-title":"J Exp Clin Cancer Res"},{"key":"1018_CR3","doi-asserted-by":"publisher","first-page":"4314","DOI":"10.1002\/cncr.30965","volume":"12322","author":"CH Han","year":"2017","unstructured":"Han CH, Batchelor TT. Diagnosis and management of primary central nervous system lymphoma. Cancer. 2017;12322:4314\u201324.","journal-title":"Cancer"},{"key":"1018_CR4","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1038\/s41598-025-85400-9","volume":"151","author":"V Cerina","year":"2025","unstructured":"Cerina V, Rui CB, Di Cristofori A, Ferlito D, Carrabba G, Giussani C, et al. Implication of tumor morphology and MRI characteristics on the accuracy of automated versus human segmentation of GBM areas. Sci Rep. 2025;151:2160.","journal-title":"Sci Rep"},{"key":"1018_CR5","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1177\/19714009241252625","volume":"376","author":"GA Ribas","year":"2024","unstructured":"Ribas GA, de Mori LH, Freddi TAL, Oliveira LDS, de Souza SR, Corr\u00eaa DG. Primary central nervous system lymphoma: Imaging features and differential diagnosis. Neuroradiol J. 2024;376:705\u201322.","journal-title":"Neuroradiol J"},{"key":"1018_CR6","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1177\/02841851241256781","volume":"657","author":"H Soydan","year":"2024","unstructured":"Soydan H, S\u00f6zmen C\u0131l\u0131z D, Cesur T, Tezg\u00f6r Aksakal E. Primary brain lymphoma and glioblastoma: evaluation of DCE T1 and DSC T2 MRI perfusion findings. Acta Radiol. 2024;657:800\u20137.","journal-title":"Acta Radiol"},{"key":"1018_CR7","doi-asserted-by":"publisher","first-page":"82","DOI":"10.3892\/br.2023.1664","volume":"195","author":"ND Hung","year":"2023","unstructured":"Hung ND, Anh NN, Minh ND, Huyen DK, Duc NM. Differentiation of glioblastoma and primary central nervous system lymphomas using multiparametric diffusion and perfusion magnetic resonance imaging. Biomed Rep. 2023;195:82.","journal-title":"Biomed Rep"},{"key":"1018_CR8","doi-asserted-by":"crossref","unstructured":"Saini J, Kumar Gupta P, Awasthi A, Pandey CM, Singh A, Patir R, et al. Multiparametric imaging-based differentiation of lymphoma and glioblastoma: using T1-perfusion, diffusion, and susceptibility-weighted MRI. Clin Radiol. 2018;73(11):986.e7\u2013e15.","DOI":"10.1016\/j.crad.2018.07.107"},{"key":"1018_CR9","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1148\/radiol.14132740","volume":"2723","author":"P Kickingereder","year":"2014","unstructured":"Kickingereder P, Wiestler B, Sahm F, Heiland S, Roethke M, Schlemmer HP, et al. Primary central nervous system lymphoma and atypical glioblastoma: multiparametric differentiation by using diffusion-, perfusion-, and susceptibility-weighted MR imaging. Radiology. 2014;2723:843\u201350.","journal-title":"Radiology"},{"key":"1018_CR10","doi-asserted-by":"publisher","first-page":"8703","DOI":"10.1007\/s00330-021-07845-6","volume":"3111","author":"G Bathla","year":"2021","unstructured":"Bathla G, Priya S, Liu Y, Ward C, Le NH, Soni N, et al. Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques. Eur Radiol. 2021;3111:8703\u201313.","journal-title":"Eur Radiol"},{"key":"1018_CR11","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1002\/jmri.27344","volume":"531","author":"W Xia","year":"2021","unstructured":"Xia W, Hu B, Li H, Geng C, Wu Q, Yang L, et al. Multiparametric-MRI-Based Radiomics Model for Differentiating Primary Central Nervous System Lymphoma From Glioblastoma: Development and Cross-Vendor Validation. J Magn Reson Imaging. 2021;531:242\u201350.","journal-title":"J Magn Reson Imaging"},{"key":"1018_CR12","doi-asserted-by":"publisher","first-page":"2482","DOI":"10.1007\/s00330-010-1817-4","volume":"2010","author":"P Schramm","year":"2010","unstructured":"Schramm P, Xyda A, Klotz E, Tronnier V, Knauth M, Hartmann M. Dynamic CT perfusion imaging of intra-axial brain tumours: differentiation of high-grade gliomas from primary CNS lymphomas. Eur Radiol. 2010;2010:2482\u201390.","journal-title":"Eur Radiol"},{"key":"1018_CR13","doi-asserted-by":"publisher","first-page":"E124","DOI":"10.1148\/radiol.2020200755","volume":"2962","author":"DM Yousem","year":"2020","unstructured":"Yousem DM, Zhou A, Alvin MD. CT Angiography for Triage of Minor Stroke: Controversial Analysis. Radiology. 2020;2962:E124\u20135.","journal-title":"Radiology"},{"key":"1018_CR14","doi-asserted-by":"crossref","unstructured":"Hooper GW, Ansari S, Johnson JM, Ginat DT. Advances in the radiological evaluation of and theranostics for glioblastoma. Cancers (Basel). 2023;1516.","DOI":"10.3390\/cancers15164162"},{"key":"1018_CR15","doi-asserted-by":"publisher","first-page":"905227","DOI":"10.3389\/fneur.2022.905227","volume":"13","author":"G Lu","year":"2022","unstructured":"Lu G, Zhang Y, Wang W, Miao L, Mou W. Machine Learning and Deep Learning CT-Based Models for Predicting the Primary Central Nervous System Lymphoma and Glioma Types: A Multicenter Retrospective Study. Front Neurol. 2022;13:905227.","journal-title":"Front Neurol"},{"key":"1018_CR16","doi-asserted-by":"crossref","unstructured":"Liu X, Liu J. Aided diagnosis model based on deep learning for glioblastoma, solitary brain metastases, and primary central nervous system lymphoma with multi-modal MRI. Biology (Basel). 2024;132.","DOI":"10.3390\/biology13020099"},{"key":"1018_CR17","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.3174\/ajnr.A3915","volume":"358","author":"P Kickingereder","year":"2014","unstructured":"Kickingereder P, Sahm F, Wiestler B, Roethke M, Heiland S, Schlemmer HP, et al. Evaluation of microvascular permeability with dynamic contrast-enhanced MRI for the differentiation of primary CNS lymphoma and glioblastoma: radiologic-pathologic correlation. AJNR Am J Neuroradiol. 2014;358:1503\u20138.","journal-title":"AJNR Am J Neuroradiol"},{"key":"1018_CR18","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1186\/s12967-025-06185-z","volume":"231","author":"J Hu","year":"2025","unstructured":"Hu J, Sa X, Yang Y, Han Y, Wu J, Sun M, et al. Multi-transcriptomics reveals niche-specific expression programs and endothelial cells in glioblastoma. J Transl Med. 2025;231:444.","journal-title":"J Transl Med"},{"key":"1018_CR19","doi-asserted-by":"publisher","first-page":"109900","DOI":"10.1016\/j.ejrad.2021.109900","volume":"143","author":"T Mart\u00edn-Noguerol","year":"2021","unstructured":"Mart\u00edn-Noguerol T, Mohan S, Santos-Armentia E, Cabrera-Zubizarreta A, Luna A. Advanced MRI assessment of non-enhancing peritumoral signal abnormality in brain lesions. Eur J Radiol. 2021;143:109900.","journal-title":"Eur J Radiol"},{"key":"1018_CR20","doi-asserted-by":"publisher","first-page":"2425131","DOI":"10.1080\/15384047.2024.2425131","volume":"251","author":"Q Jin","year":"2024","unstructured":"Jin Q, Jiang H, Han Y, Zhang L, Li C, Zhang Y, et al. Tumor microenvironment in primary central nervous system lymphoma (PCNSL). Cancer Biol Ther. 2024;251:2425131.","journal-title":"Cancer Biol Ther"},{"key":"1018_CR21","doi-asserted-by":"publisher","first-page":"9974","DOI":"10.1038\/s41598-021-89218-z","volume":"111","author":"KY Shim","year":"2021","unstructured":"Shim KY, Chung SW, Jeong JH, Hwang I, Park CK, Kim TM, et al. Radiomics-based neural network predicts recurrence patterns in glioblastoma using dynamic susceptibility contrast-enhanced MRI. Sci Rep. 2021;111:9974.","journal-title":"Sci Rep"},{"key":"1018_CR22","doi-asserted-by":"publisher","first-page":"e0169292","DOI":"10.1371\/journal.pone.0169292","volume":"121","author":"O Eidel","year":"2017","unstructured":"Eidel O, Burth S, Neumann JO, Kieslich PJ, Sahm F, Jungk C, et al. Tumor Infiltration in Enhancing and Non-Enhancing Parts of Glioblastoma: A Correlation with Histopathology. PLoS ONE. 2017;121:e0169292.","journal-title":"PLoS ONE"},{"key":"1018_CR23","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.ejrad.2010.11.005","volume":"812","author":"A Doskaliyev","year":"2012","unstructured":"Doskaliyev A, Yamasaki F, Ohtaki M, Kajiwara Y, Takeshima Y, Watanabe Y, et al. Lymphomas and glioblastomas: differences in the apparent diffusion coefficient evaluated with high b-value diffusion-weighted magnetic resonance imaging at 3T. Eur J Radiol. 2012;812:339\u201344.","journal-title":"Eur J Radiol"},{"key":"1018_CR24","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1093\/neuonc\/nou364","volume":"178","author":"KM Schmainda","year":"2015","unstructured":"Schmainda KM, Zhang Z, Prah M, Snyder BS, Gilbert MR, Sorensen AG, et al. Dynamic susceptibility contrast MRI measures of relative cerebral blood volume as a prognostic marker for overall survival in recurrent glioblastoma: results from the ACRIN 6677\/RTOG 0625 multicenter trial. Neuro Oncol. 2015;178:1148\u201356.","journal-title":"Neuro Oncol"},{"key":"1018_CR25","doi-asserted-by":"publisher","first-page":"e696","DOI":"10.1016\/j.wneu.2021.01.114","volume":"149","author":"P Wang","year":"2021","unstructured":"Wang P, Shi YH, Li JY, Zhang CZ. Differentiating Glioblastoma from Primary Central Nervous System Lymphoma: The Value of Shaping and Nonenhancing Peritumoral Hyperintense Gyral Lesion on FLAIR Imaging. World Neurosurg. 2021;149:e696\u2013704.","journal-title":"World Neurosurg"},{"key":"1018_CR26","doi-asserted-by":"publisher","first-page":"848846","DOI":"10.3389\/fonc.2022.848846","volume":"12","author":"D Liu","year":"2022","unstructured":"Liu D, Chen J, Ge H, Hu X, Yang K, Liu Y, et al. Differentiation of malignant brain tumor types using intratumoral and peritumoral radiomic features. Front Oncol. 2022;12:848846.","journal-title":"Front Oncol"},{"key":"1018_CR27","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1093\/neuonc\/nov119","volume":"1710","author":"JM Lem\u00e9e","year":"2015","unstructured":"Lem\u00e9e JM, Clavreul A, Menei P. Intratumoral heterogeneity in glioblastoma: don\u2019t forget the peritumoral brain zone. Neuro Oncol. 2015;1710:1322\u201332.","journal-title":"Neuro Oncol"},{"key":"1018_CR28","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1007\/s00234-007-0272-7","volume":"4911","author":"T Hagen","year":"2007","unstructured":"Hagen T, Ahlhelm F, Reiche W. Apparent diffusion coefficient in vasogenic edema and reactive astrogliosis. Neuroradiology. 2007;4911:921\u20136.","journal-title":"Neuroradiology"},{"key":"1018_CR29","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/s10143-023-02094-1","volume":"461","author":"J Laajava","year":"2023","unstructured":"Laajava J, Korja M. Peritumoral T2\/FLAIR hyperintense MRI findings of meningiomas are not necessarily edema and may persist permanently: a systematic review. Neurosurg Rev. 2023;461:193.","journal-title":"Neurosurg Rev"},{"key":"1018_CR30","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1002\/hbm.25327","volume":"426","author":"AR Ridwan","year":"2021","unstructured":"Ridwan AR, Niaz MR, Wu Y, Qi X, Zhang S, Kontzialis M, et al. Development and evaluation of a high performance T1-weighted brain template for use in studies on older adults. Hum Brain Mapp. 2021;426:1758\u201376.","journal-title":"Hum Brain Mapp"},{"key":"1018_CR31","doi-asserted-by":"crossref","unstructured":"Demircio\u011flu A. Deep features from pretrained networks do not outperform hand-crafted features in radiomics. Diagnostics (Basel). 2023;1320.","DOI":"10.3390\/diagnostics13203266"},{"key":"1018_CR32","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1038\/s41598-023-50451-3","volume":"141","author":"F Sch\u00f6n","year":"2024","unstructured":"Sch\u00f6n F, Kieslich A, Nebelung H, Riediger C, Hoffmann RT, Zwanenburg A, et al. Comparative analysis of radiomics and deep-learning algorithms for survival prediction in hepatocellular carcinoma. Sci Rep. 2024;141:590.","journal-title":"Sci Rep"}],"container-title":["Cancer Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40644-026-01018-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40644-026-01018-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40644-026-01018-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:14:14Z","timestamp":1781640854000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s40644-026-01018-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1018"],"URL":"https:\/\/doi.org\/10.1186\/s40644-026-01018-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7305219\/v1","asserted-by":"object"}]},"ISSN":["1470-7330"],"issn-type":[{"value":"1470-7330","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"6 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","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 Institutional Review Board of The First Affiliated Hospital of Fujian Medical University, Quanzhou First Hospital Affiliated to Fujian Medical University and Henan Cancer Hospital approved this retrospective study and waived the need for written informed consent.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"54"}}