{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T09:02:49Z","timestamp":1789635769406,"version":"4.0.0"},"reference-count":53,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T00:00:00Z","timestamp":1789603200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Mayo Clinic Comprehensive Cancer Center","award":["P30CA015083"],"award-info":[{"award-number":["P30CA015083"]}]},{"award":["P30CA015083"],"award-info":[{"award-number":["P30CA015083"]}],"id":[{"id":"https:\/\/ror.org\/012wxv498","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Glioblastoma surveillance after surgery and chemoradiation remains challenging because MRI findings of tumor recurrence can overlap with pseudo-progression, treatment-related effects, and postoperative tissue changes. Methods: We developed a seven-channel postoperative MRI framework using a deep learning transfer method to support non-invasive glioblastoma treatment-effect assessment. The model used T1 contrast-enhanced, FLAIR, T1, RSI-Cell, ADC, T2, and cerebral blood flow volumes from 124 postoperative glioblastoma patients (164 MRI timepoints) as input. Images were processed using a 3D ResNet18 encoder pretrained on 588 postoperative glioma samples and fine-tuned using task-specific classification heads. The cohort comprised 124 patients contributing 164 postoperative MRI timepoints, all acquired at 3T on scanners from a single vendor. Performance was evaluated with nested five-fold cross-validation stratified and assigned at the patient level, so that all timepoints from a given patient fell in one-fold and the training epoch was selected on an inner split rather than on the fold being reported. Because some of the clinical labels were incomplete, the number of evaluable timepoints differed by task (recurrence versus pseudo-progression, 164; MGMT, 99; short-term survival, 139). The whole procedure was repeated under three independent random seeds and results are reported as the mean and standard deviation across seeds. Results: The strongest clinical endpoint was recurrence versus pseudo-progression, where nested cross-validation across three random seeds gave a pooled out-of-fold AUC of 0.935 (SD = 0.014), area under the precision-recall curve of 0.973, balanced accuracy of 0.880, sensitivity of 0.917, and specificity of 0.843. No other endpoint reached reliable discrimination. Radiation decision reached an AUC of 0.658 (SD = 0.039), while MGMT promoter methylation (AUC = 0.532, SD = 0.082) and short-term survival (AUC = 0.514, SD = 0.027) were indistinguishable from chance. Conclusions: In this single-center proof-of-concept study, postoperative MRI successfully distinguished tumor recurrence from pseudo-progression. However, the models did not reliably predict the other three outcomes related to molecular status, treatment planning, and prognosis. Overall, the model learned imaging features specifically associated with recurrence, rather than a more general representation of the tumor that can predict many different clinical outcomes. These findings support technical feasibility for a single endpoint rather than clinical readiness, for which external multi-center validation is required.<\/jats:p>","DOI":"10.3390\/cancers18183015","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T08:03:17Z","timestamp":1789632197000},"page":"3015","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Channel Postoperative MRI and Deep Transfer Learning to Distinguish Glioblastoma Recurrence from Pseudo-Progression: A Proof-of-Concept Study"],"prefix":"10.3390","volume":"18","author":[{"given":"Ian D.","family":"Li","sequence":"first","affiliation":[{"name":"Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Cristina","family":"Correia","sequence":"additional","affiliation":[{"name":"Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-3473","authenticated-orcid":false,"given":"Choong-Yong","family":"Ung","sequence":"additional","affiliation":[{"name":"Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic College of Medicine and Science, Rochester, MN 55905, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1093\/neuonc\/noab106","article-title":"The 2021 WHO Classification of Tumors of the Central Nervous System: A summary","volume":"23","author":"Louis","year":"2021","journal-title":"Neuro-Oncology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1038\/s41571-020-00447-z","article-title":"EANO guidelines on the diagnosis and treatment of diffuse gliomas of adulthood","volume":"18","author":"Weller","year":"2021","journal-title":"Nat. Rev. Clin. Oncol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"987","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":"ref_4","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1056\/NEJMoa043331","article-title":"MGMT gene silencing and benefit from temozolomide in glioblastoma","volume":"352","author":"Hegi","year":"2005","journal-title":"N. Engl. J. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"515","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-Oncology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1002\/jmri.26306","article-title":"Perfusion MRI in treatment evaluation of glioblastomas: Clinical relevance of current and future techniques","volume":"49","author":"Smits","year":"2019","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Malik, D.G., Rath, T.J., Urcuyo Acevedo, J.C., Canoll, P.D., Swanson, K.R., Boxerman, J.L., Quarles, C.C., Schmainda, K.M., Burns, T.C., and Hu, L.S. (2022). Advanced MRI protocols to discriminate glioma from treatment effects: State of the art and future directions. Front. Radiol., 2.","DOI":"10.3389\/fradi.2022.809373"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"13258","DOI":"10.1038\/s41598-022-16726-x","article-title":"Discriminators of pseudo-progression and true progression in high-grade gliomas: A systematic review and meta-analysis","volume":"12","author":"Taylor","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.1200\/JCO.2009.26.3541","article-title":"Updated response assessment criteria for high-grade gliomas: Response Assessment in Neuro-Oncology Working Group","volume":"28","author":"Wen","year":"2010","journal-title":"J. Clin. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5187","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":"ref_11","doi-asserted-by":"crossref","first-page":"633","DOI":"10.1097\/WCO.0b013e328332363e","article-title":"Pseudo-progression and pseudoresponse in the treatment of gliomas","volume":"22","author":"Brandsma","year":"2009","journal-title":"Curr. Opin. Neurol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ganau, M. (2025). Towards a New Dawn for Neuro-Oncology: Nanomedicine at the Service of Drug Delivery for Primary and Secondary Brain Tumours. Brain Sci., 15.","DOI":"10.3390\/brainsci15020136"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chuang, M.T., Liu, Y.S., Tsai, Y.S., Chen, Y.C., and Wang, C.K. (2016). Differentiating radiation-induced necrosis from recurrent brain tumor using MR perfusion and spectroscopy: A meta-analysis. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0141438"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1093\/neuonc\/now148","article-title":"MR perfusion-weighted imaging in the evaluation of high-grade gliomas after treatment: A systematic review and meta-analysis","volume":"19","author":"Patel","year":"2017","journal-title":"Neuro-Oncology"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4638","DOI":"10.1158\/0008-5472.CAN-13-3534","article-title":"Diffusion-weighted imaging in cancer: Physical foundations and applications of restriction spectrum imaging","volume":"74","author":"White","year":"2014","journal-title":"Cancer Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1186\/s13244-021-01102-6","article-title":"Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging","volume":"12","author":"Alksas","year":"2021","journal-title":"Insights Imaging"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s40644-024-00682-y","article-title":"Artificial intelligence-based MRI radiomics and radiogenomics in glioma","volume":"24","author":"Fan","year":"2024","journal-title":"Cancer Imaging"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e210284","DOI":"10.1148\/ryai.210284","article-title":"Toward foundational deep learning models for medical imaging in the new era of transformer networks","volume":"4","author":"Willemink","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e240597","DOI":"10.1148\/radiol.240597","article-title":"Foundation models in radiology: What, how, why, and why not","volume":"314","author":"Paschali","year":"2025","journal-title":"Radiology"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"170117","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing The Cancer Genome Atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci. Data"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)","volume":"34","author":"Menze","year":"2015","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_22","unstructured":"Baid, U., Ghodasara, S., Mohan, S., Bilello, M., Calabrese, E., Colak, E., Farahani, K., Kalpathy-Cramer, J., Kitamura, F.C., and Pati, S. (2021). The RSNA-ASNR-MICCAI BraTS 2021 benchmark on brain tumor segmentation and radiogenomic classification. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e220058","DOI":"10.1148\/ryai.220058","article-title":"The University of California San Francisco preoperative diffuse glioma MRI dataset","volume":"4","author":"Calabrese","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, X., Chan, M.D., Zhou, X., and Qian, X. (2019). Transparency guided ensemble convolutional neural networks for stratification of pseudo-progression and true progression of glioblastoma multiform. arXiv.","DOI":"10.1016\/j.jvcir.2020.102880"},{"key":"ref_25","unstructured":"Parekh, V.S., Laterra, J., Bettegowda, C., Bocchieri, A.E., Pillai, J.J., and Jacobs, M.A. (2019). Multiparametric deep learning and radiomics for tumor grading and treatment response assessment of brain cancer: Preliminary results. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"17133","DOI":"10.1038\/s41598-025-02026-7","article-title":"A self-supervised multimodal deep learning approach to differentiate post-radiotherapy progression from pseudo-progression in glioblastoma","volume":"15","author":"Gomaa","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Guo, W., and Mirzaei, G. (2026). Timepoint-Specific Benchmarking of Deep Learning Models for Glioblastoma Follow-Up MRI. Cancers, 18.","DOI":"10.3390\/cancers18010036"},{"key":"ref_28","unstructured":"Tikhonov, D., Scatolin, M., Banerjee, M., Ji, Q., Jaheen, A., Salem, M., Elsayed, A., Wang, H., Hashmi, S., and Yaqub, M. (2025). Predicting brain tumor response to therapy using a hybrid deep learning and radiomics approach. arXiv."},{"key":"ref_29","unstructured":"Bhattacharya, M., Kurtz, A.P., Iwamoto, F.M., Prasanna, P., and Singh, G. (2025). NeuroRAD-FM: A foundation model for neuro-oncology with distributionally robust training. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"055018","DOI":"10.1088\/2057-1976\/ad6573","article-title":"Adaptive fine-tuning based transfer learning for the identification of MGMT promoter methylation status","volume":"10","author":"Schmitz","year":"2024","journal-title":"Biomed. Phys. Eng. Express"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Oakden-Rayner, L., Dunnmon, J., Carneiro, G., and Re, C. (2020, January 2\u20134). Hidden stratification causes clinically meaningful failures in machine learning for medical imaging. Proceedings of the CHIL \u201820: Proceedings of the ACM Conference on Health, Inference, and Learning, Toronto, ON, Canada.","DOI":"10.1145\/3368555.3384468"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/s41597-022-01618-6","article-title":"Inflation of test accuracy due to data leakage in deep learning-based classification of OCT images","volume":"9","author":"Tampu","year":"2022","journal-title":"Sci. Data"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"e210064","DOI":"10.1148\/ryai.210064","article-title":"External validation of deep learning algorithms for radiologic diagnosis: A systematic review","volume":"4","author":"Yu","year":"2022","journal-title":"Radiol. Artif. Intell."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e220232","DOI":"10.1148\/ryai.220232","article-title":"A guide to cross-validation for artificial intelligence in medical imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106496","DOI":"10.1016\/j.compbiomed.2022.106496","article-title":"Multi-task deep learning for medical image computing and analysis: A review","volume":"153","author":"Zhao","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_36","unstructured":"Cardoso, M.J., Li, W., Brown, R., Ma, N., Kerfoot, E., Wang, Y., Murrey, B., Myronenko, A., Zhao, C., and Yang, D. (2022). MONAI: An open-source framework for deep learning in healthcare. arXiv."},{"key":"ref_37","unstructured":"Chen, S., Ma, K., and Zheng, Y. (2019). Med3D: Transfer learning for 3D medical image analysis. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The Cancer Imaging Archive (TCIA): Maintaining and operating a public information repository","volume":"26","author":"Clark","year":"2013","journal-title":"J. Digit. Imaging"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1038\/s41597-025-06499-z","article-title":"The University of California San Diego Post-Treatment Glioblastoma (UCSD-PTGBM) annotated multimodal MRI Dataset","volume":"13","author":"Gagnon","year":"2026","journal-title":"Sci. Data"},{"key":"ref_41","unstructured":"Loshchilov, I., and Hutter, F. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., and Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","article-title":"Index for rating diagnostic tests","volume":"3","author":"Youden","year":"1950","journal-title":"Cancer"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., and Batra, D. (2017, January 22\u201329). Grad-CAM: Visual explanations from deep networks via gradient-based localization. Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Daghighi, S., Bahrami, N., Tom, W.J., Coley, N., Seibert, T.M., Hattangadi-Gluth, J.A., Piccioni, D.E., Dale, A.M., Farid, N., and McDonald, C.R. (2020). Restriction Spectrum Imaging differentiates true tumor progression from immune-mediated pseudo-progression: Case report of a patient with glioblastoma. Front. Oncol., 10.","DOI":"10.3389\/fonc.2020.00024"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"12336","DOI":"10.21037\/qims-2025-245","article-title":"Dynamic susceptibility contrast perfusion in differentiation between recurrence and pseudo-progression in glioblastoma: A systematic review and meta-analysis","volume":"15","author":"Wo","year":"2025","journal-title":"Quant. Imaging Med. Surg."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Kim, B.H., Lee, H., Choi, K.S., Nam, J.G., Park, C., Park, S., Chung, J.W., and Choi, S.H. (2022). Validation of MRI-based models to predict MGMT promoter methylation in gliomas: BraTS 2021 Radiogenomics Challenge. Cancers, 14.","DOI":"10.3390\/cancers14194827"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"5802","DOI":"10.1007\/s00330-024-10594-x","article-title":"Quality assessment of the MRI-radiomics studies for MGMT promoter methylation prediction in glioma: A systematic review and meta-analysis","volume":"34","author":"Doniselli","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"102989","DOI":"10.1016\/j.media.2023.102989","article-title":"MGMT promoter methylation status prediction using MRI scans? An extensive experimental evaluation of deep learning models","volume":"90","author":"Saeed","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"31821","DOI":"10.1038\/s41598-025-17895-1","article-title":"Enhanced glioma semantic segmentation using U-net and pre-trained backbone U-net architectures","volume":"15","author":"Khorasani","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_52","unstructured":"(2026, March 04). MU-Glioma-Post|University of Missouri Post-Pperative Glioma Dataset. The Cancer Imaging Archive, Available online: https:\/\/www.cancerimagingarchive.net\/collection\/mu-glioma-post\/."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"1847","DOI":"10.1038\/s41597-025-06011-7","article-title":"MU-Glioma Post: A comprehensive dataset of automated MR multi-sequence segmentation and clinical features","volume":"12","author":"Mahmoud","year":"2025","journal-title":"Sci. Data"}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/18\/3015\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T08:18:40Z","timestamp":1789633120000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/18\/3015"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,17]]},"references-count":53,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["cancers18183015"],"URL":"https:\/\/doi.org\/10.3390\/cancers18183015","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,17]]}}}