{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T11:00:19Z","timestamp":1775473219539,"version":"3.50.1"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003196","name":"Ministero della Salute","doi-asserted-by":"publisher","award":["T4-AN.09"],"award-info":[{"award-number":["T4-AN.09"]}],"id":[{"id":"10.13039\/501100003196","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose:<\/jats:title>\n                    <jats:p>Accurate prediction of overall survival (OS) in glioblastoma patients is critical for advancing personalized treatments and improving clinical trial design. Conventional radiomics approaches rely on manually engineered features, which limit their ability to capture complex, high-dimensional imaging patterns. This study employs a deep learning architecture to process MRI data for automated glioma segmentation and feature extraction, leveraging high-level representations from the encoder\u2019s latent space.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Multimodal MRI data from the BraTS2020 dataset and a proprietary dataset from Fondazione IRCCS Istituto Neurologico Carlo Besta (Milan, Italy) were processed independently using a U-Net-like model pre-trained on BraTS2018 and fine-tuned on BraTS2020. Features extracted from the encoder\u2019s latent space represented hierarchical imaging patterns. These features were combined with clinical variable (patient\u2019s age) and reduced via principal component analysis (PCA) to enhance computational efficiency. Machine learning classifiers\u2014including random forest, XGBoost, and a fully connected neural network\u2014were trained on the reduced feature vectors for OS classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>In the four-modality BraTS4CH setting, the multi-layer perceptron achieved the best performance (F1 = 0.71, AUC = 0.74, accuracy = 0.71). When limited to two modalities on BraTS2020 (BraTS2CH), MLP again led (F1 = 0.67, AUC = 0.70, accuracy = 0.67). On the IRCCS Besta two-modality cohort (Besta2CH), XGBoost produced the highest F1-score and accuracy (F1 = 0.65, accuracy = 0.66), while MLP obtained the top AUC (0.70). These results are competitive with\u2014and in some metrics exceed\u2014state-of-the-art reports, demonstrating the robustness and scalability of our automated framework relative to traditional radiomics and AI-driven approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>Integrating encoder-derived features from multimodal MRI data with clinical variables offers a scalable and effective approach for OS prediction in glioblastoma patients. This study demonstrates the potential of deep learning to address traditional radiomics limitations, paving the way for more precise and personalized prognostic tools.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11548-025-03548-1","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T12:53:38Z","timestamp":1764852818000},"page":"473-482","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Glioblastoma survival prediction through MRI and clinical data integration with transfer learning"],"prefix":"10.1007","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7992-5222","authenticated-orcid":false,"given":"A.","family":"Marasi","sequence":"first","affiliation":[]},{"given":"D.","family":"Milesi","sequence":"additional","affiliation":[]},{"given":"D.","family":"Aquino","sequence":"additional","affiliation":[]},{"given":"F. M.","family":"Doniselli","sequence":"additional","affiliation":[]},{"given":"R.","family":"Pascuzzo","sequence":"additional","affiliation":[]},{"given":"M.","family":"Grisoli","sequence":"additional","affiliation":[]},{"given":"A.","family":"Redaelli","sequence":"additional","affiliation":[]},{"given":"E.","family":"De Momi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"issue":"5","key":"3548_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/neuonc\/noz150","volume":"21","author":"QT Ostrom","year":"2019","unstructured":"Ostrom QT, Cioffi G, Gittleman H, Patil N, Waite K, Kruchko C, Barnholtz-Sloan JS (2019) Primary brain and other central nervous system tumors diagnosed in the united states in 2012\u20132016. Neuro Oncol 21(5):1\u2013100. https:\/\/doi.org\/10.1093\/neuonc\/noz150","journal-title":"Neuro Oncol"},{"issue":"10","key":"3548_CR2","doi-asserted-by":"publisher","first-page":"4527","DOI":"10.1002\/cam4.2362","volume":"8","author":"S Liang","year":"2019","unstructured":"Liang S, Fan X, Zhao M, Shan X, Li W, Ding P, You G, Hong Z, Yang X, Luan G, Ma W, Yang H, You Y, Yang T, Li L, Liao W, Wang L, Wu X, Yu X, Zhang J, Mao Q, Wang Y, Li W, Wang X, Jiang C, Liu X, Qi S, Liu X, Qu Y, Xu J, Wang W, Song Z, Wu J, Liu Z, Chen L, Lin Y, Zhou J, Liu X, Zhang W, Li S, Jiang T (2019) Clinical practice guidelines for the diagnosis and treatment of adult diffuse glioma-related epilepsy. Cancer Med 8(10):4527\u20134535. https:\/\/doi.org\/10.1002\/cam4.2362","journal-title":"Cancer Med"},{"issue":"12","key":"3548_CR3","doi-asserted-by":"publisher","first-page":"1521","DOI":"10.1007\/s11547-023-01725-3","volume":"128","author":"G Hajianfar","year":"2023","unstructured":"Hajianfar G, Haddadi Avval A, Hosseini SA, Nazarfi M, Oveisi M, Shiri I, Zaidi H (2023) Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics. Radiol Med 128(12):1521\u20131534. https:\/\/doi.org\/10.1007\/s11547-023-01725-3","journal-title":"Radiol Med"},{"issue":"1","key":"3548_CR4","doi-asserted-by":"publisher","first-page":"138","DOI":"10.3390\/ijms25010138","volume":"25","author":"FM Doniselli","year":"2023","unstructured":"Doniselli FM, Pascuzzo R, Agr\u00f2 M, Aquino D, Anghileri E, Farinotti M, Pollo B, Paterra R, Cuccarini V, Moscatelli M, DiMeco F, Sconfienza LM (2023) Development of a radiomic model for MGMT promoter methylation detection in glioblastoma using conventional MRI. Int J Mol Sci 25(1):138. https:\/\/doi.org\/10.3390\/ijms25010138","journal-title":"Int J Mol Sci"},{"issue":"10","key":"3548_CR5","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1056\/NEJMoa043331","volume":"352","author":"ME Hegi","year":"2005","unstructured":"Hegi ME, Diseren AC, Gorlia T, Hamou MF, Tribolet N, Weller M, Kros JM, Hainfellner JA, Mason W, Mariani L, Bromberg JE, Hau P, Mirimanoff RO, Cairncross JG, Janzer RC, Stupp R (2005) MGMT gene silencing and benefit from temozolomide in glioblastoma. N Engl J Med 352(10):997\u20131003. https:\/\/doi.org\/10.1056\/NEJMoa043331","journal-title":"N Engl J Med"},{"issue":"7390","key":"3548_CR6","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1038\/nature10866","volume":"483","author":"S Turcan","year":"2012","unstructured":"Turcan S, Rohle D, Goenka A, Walsh LA, Fang F, Yilmaz E, Campos C, Fabius AW, Lu C, Ward PS, Thompson CB, Kaufman A, Guryanova O, Levine R, Heguy A, Viale A, Morris LG, Huse JT, Mellinghoff IK, Chan TA (2012) IDH1 mutation is sufficient to establish the glioma hypermethylator phenotype. Nature 483(7390):479\u2013483. https:\/\/doi.org\/10.1038\/nature10866","journal-title":"Nature"},{"issue":"9","key":"3548_CR7","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1093\/neuonc\/nou005","volume":"16","author":"RJ Molenaar","year":"2014","unstructured":"Molenaar RJ, Verbaan D, Lamba S, Zanon C, Jeuken JW, Boots-Sprenger SH, Wesseling P, Hulsebos TJ, Troost D, Tilborg AA, Leenstra S, Vandertop WP, Bardelli A, Noorden CJ, Bleeker FE (2014) The combination of IDH1 mutations and MGMT methylation status predicts survival in glioblastoma better than either IDH1 or MGMT alone. Neuro Oncol 16(9):1263\u20131273. https:\/\/doi.org\/10.1093\/neuonc\/nou005","journal-title":"Neuro Oncol"},{"key":"3548_CR8","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1186\/1748-717X-6-115","volume":"6","author":"SE Combs","year":"2011","unstructured":"Combs SE, Rieken S, Wick W, Abdollahi A, Deimling A, Debus J, Hartmann C (2011) Prognostic significance of IDH-1 and MGMT in patients with glioblastoma: one step forward, and one step back? Radiat Oncol 6:115. https:\/\/doi.org\/10.1186\/1748-717X-6-115","journal-title":"Radiat Oncol"},{"issue":"4","key":"3548_CR9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.21037\/cco.2017.06.28","volume":"6","author":"G Shukla","year":"2017","unstructured":"Shukla G, Alexander GS, Bakas SA, Nikam R, Talekar K, Palmer JD, Shi W (2017) Advanced magnetic resonance imaging in glioblastoma: a review. Chin Clin Oncol 6(4):4. https:\/\/doi.org\/10.21037\/cco.2017.06.28","journal-title":"Chin Clin Oncol"},{"key":"3548_CR10","doi-asserted-by":"publisher","first-page":"111130","DOI":"10.1016\/j.ejrad.2023","volume":"168","author":"Y Choi","year":"2023","unstructured":"Choi Y, Jang J, Kim BS, Ahn KJ (2023) Pretreatment MR-based radiomics in patients with glioblastoma: a systematic review and meta-analysis of prognostic endpoints. J Radiol 168:111130. https:\/\/doi.org\/10.1016\/j.ejrad.2023","journal-title":"J Radiol"},{"issue":"5","key":"3548_CR11","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1227\/NEU.0b013e3181f556ab","volume":"67","author":"LE Bohman","year":"2010","unstructured":"Bohman LE, Swanson KR, Moore JL, Mandigo C, Hankinson T, Assanah M, Canoll P, Bruce JN (2010) Magnetic resonance imaging characteristics of glioblastoma multiforme: implications for understanding glioma ontogeny. Neurosurgery 67(5):1319\u20131327. https:\/\/doi.org\/10.1227\/NEU.0b013e3181f556ab","journal-title":"Neurosurgery"},{"issue":"303","key":"3548_CR12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1126\/scitranslmed.aaa7582","volume":"7","author":"H Itakura","year":"2015","unstructured":"Itakura H, Achrol AS, Mitchell LA, Loya JJ, Liu T, Westbroek EM, Feroze AH, Rodriguez S, Echegaray S, Azad TD, Yeom KW, Napel S, Rubin DL, Chang SD, Harsh GR, Gevaert O (2015) Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities. Sci Transl Med 7(303):303\u2013138. https:\/\/doi.org\/10.1126\/scitranslmed.aaa7582","journal-title":"Sci Transl Med"},{"issue":"3","key":"3548_CR13","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1148\/radiol.2018180200","volume":"289","author":"S Bae","year":"2018","unstructured":"Bae S, Choi YS, Ahn SS, Kang SG, Kim EH, Lee SK (2018) Radiomic MRI phenotyping of glioblastoma: improving survival prediction. Radiology 289(3):797\u2013806. https:\/\/doi.org\/10.1148\/radiol.2018180200","journal-title":"Radiology"},{"issue":"3","key":"3548_CR14","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1093\/brain\/awab340","volume":"145","author":"G Li","year":"2022","unstructured":"Li G, Li L, Li Y, Qian Z, Wu F, He Y, Jiang H, Li R, Wang D, Zhai Y, Wang Z, Jiang T, Zhang J, Zhang W (2022) An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas. Brain 145(3):1151\u20131161. https:\/\/doi.org\/10.1093\/brain\/awab340","journal-title":"Brain"},{"issue":"1","key":"3548_CR15","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s41747-018-0068-z","volume":"2","author":"S Rizzo","year":"2018","unstructured":"Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, Bellomi M (2018) Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp 2(1):36. https:\/\/doi.org\/10.1186\/s41747-018-0068-z","journal-title":"Eur Radiol Exp"},{"key":"3548_CR16","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1186\/s13244-023-01556-w","volume":"14","author":"P Woznicki","year":"2023","unstructured":"Woznicki P, Laqua FC, Al-Haj A, Bley T, Bae\u00dfler B (2023) Addressing challenges in radiomics research: systematic review and repository of open-access cancer imaging datasets. Insights Imaging 14:216. https:\/\/doi.org\/10.1186\/s13244-023-01556-w","journal-title":"Insights Imaging"},{"key":"3548_CR17","doi-asserted-by":"publisher","first-page":"2630","DOI":"10.1007\/s00259-019-04373-w","volume":"46","author":"D Visvikis","year":"2019","unstructured":"Visvikis D, Cheze Le Rest C, Jaouen V, Hatt M (2019) Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications. J Nucl Med Mol Imaging 46:2630\u20132637. https:\/\/doi.org\/10.1007\/s00259-019-04373-w","journal-title":"J Nucl Med Mol Imaging"},{"key":"3548_CR18","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas, NV, USA, pp 770\u2013778. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"issue":"1","key":"3548_CR19","doi-asserted-by":"publisher","first-page":"19726","DOI":"10.1038\/s41598-020-74419-9","volume":"10","author":"L Pei","year":"2020","unstructured":"Pei L, Vidyaratne L, Rahman MM, Iftekharuddin KM (2020) Context aware deep learning for brain tumor segmentation, subtype classification, and survival prediction using radiology images. Sci Rep 10(1):19726. https:\/\/doi.org\/10.1038\/s41598-020-74419-9","journal-title":"Sci Rep"},{"key":"3548_CR20","doi-asserted-by":"crossref","unstructured":"Chato L, Latifi S (2017) Machine learning and deep learning techniques to predict overall survival of brain tumor patients using MRI images. In: IEEE, pp 9\u201314","DOI":"10.1109\/BIBE.2017.00-86"},{"key":"3548_CR21","doi-asserted-by":"publisher","first-page":"810","DOI":"10.3389\/fnins.2019.00810","volume":"13","author":"L Sun","year":"2019","unstructured":"Sun L, Zhang S, Chen H, Luo L (2019) Brain tumor segmentation and survival prediction using multimodal MRI scans with deep learning. Front Neurosci 13:810. https:\/\/doi.org\/10.3389\/fnins.2019.00810","journal-title":"Front Neurosci"},{"key":"3548_CR22","doi-asserted-by":"crossref","unstructured":"McKinley R, Rebsamen M, Daetwyler K, Meier R, Radojewski P, Wiest R (2020) Uncertainty-driven refinement of tumor-core segmentation using 3d-to-2d networks with label uncertainty. Springer, pp 565\u2013573. arXiv:2012.06436","DOI":"10.1007\/978-3-030-72084-1_36"},{"key":"3548_CR23","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.7717\/peerj-cs.1723","volume":"9","author":"S Valbuena Rubio","year":"2023","unstructured":"Valbuena Rubio S, Garc\u00eda-Ord\u00e1s MT, Garc\u00eda-Olalla Olivera O, Alaiz-Moret\u00f3n H, Gonz\u00e1lez-Alonso MI, Ben\u00edtez-Andrades JA (2023) Survival and grade of the glioma prediction using transfer learning. PeerJ Comput Sci 9:1723. https:\/\/doi.org\/10.7717\/peerj-cs.1723","journal-title":"PeerJ Comput Sci"},{"key":"3548_CR24","doi-asserted-by":"crossref","unstructured":"Myronenko A (2018) 3d MRI brain tumor segmentation using autoencoder regularization. arXiv:1810.11654","DOI":"10.1007\/978-3-030-11726-9_28"},{"key":"3548_CR25","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TMI.2009.2035616","volume":"29","author":"S Klein","year":"2010","unstructured":"Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW (2010) elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 29:196\u2013205. https:\/\/doi.org\/10.1109\/TMI.2009.2035616","journal-title":"IEEE Trans Med Imaging"},{"key":"3548_CR26","doi-asserted-by":"publisher","unstructured":"Isensee F, Schell M, Pflueger I, Brugnara G, Bonekamp D, Neuberger U, Wick A, Schlemmer HP, Heiland S, Wick W, Bendszus M, Maier-Hein KH, Kickingereder P (2019) Hd-bet: automated brain extraction of multisequence MRI using artificial neural networks. Neuroimage 40:4952\u20134964. https:\/\/doi.org\/10.1002\/hbm.24750","DOI":"10.1002\/hbm.24750"},{"key":"3548_CR27","doi-asserted-by":"publisher","first-page":"45","DOI":"10.3389\/fninf.2013.00045","volume":"7","author":"BC Lowekamp","year":"2013","unstructured":"Lowekamp BC, Chen DT, Ib\u00e1\u00f1ez L, Blezek D (2013) The design of simpleitk. Front Neuroinform 7:45. https:\/\/doi.org\/10.3389\/fninf.2013.00045","journal-title":"Front Neuroinform"},{"key":"3548_CR28","unstructured":"MONAI consortium: 3D segmentation tutorial\u2014MONAI GitHub repository (2023). https:\/\/github.com\/Project-MONAI\/tutorials\/tree\/main\/3d_segmentation. Accessed: 27 Dec 2023"},{"key":"3548_CR29","doi-asserted-by":"publisher","unstructured":"Arias-Castro E, Donoho DL (2009) Does median filtering truly preserve edges better than linear filtering? 37:1172\u20131206. https:\/\/doi.org\/10.1214\/08-AOS604","DOI":"10.1214\/08-AOS604"},{"key":"3548_CR30","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825\u20132830"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03548-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-025-03548-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-025-03548-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T10:21:09Z","timestamp":1774866069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-025-03548-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["3548"],"URL":"https:\/\/doi.org\/10.1007\/s11548-025-03548-1","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"6 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 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 authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The present study was approved by the local ethics committee of Fondazione IRCCS Istituto Neurologico Carlo Besta (protocol code: SEURAT; date of approval: 17 May 2023).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent for study participation was waived due to the retrospective nature of the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}