{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:50:04Z","timestamp":1791352204194,"version":"4.3.1"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"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>Background<\/jats:title>\n                    <jats:p>Current preoperative assessment of meningioma brain invasion (BI) demands imaging analytical frameworks that optimize computational efficiency while capturing multidimensional tumor-pathology correlations. Building upon the inherent advantages of 2.5D MRI in synthesizing multiplanar biological data with manageable processing loads, this study innovatively integrates deep transfer learning (DTL), a technique bridging pretrained network knowledge with target domain adaptation, to systematically identify tumor-invasive biological signatures and develop an optimized predictive system using preoperative contrast-enhanced T1-weighted imaging (CE-T1WI).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study enrolled 674 patients with pathologically confirmed meningiomas, including 53 with BI and 621 without BI. The cohort was stratified into a training set and an independent test set. Tumor regions of interest (ROIs) were delineated on CE-T1WI, and radiomics and DTL features were extracted. Radiomics and DTL features were fused via early fusion, followed by feature selection. Within the training cohort, five-fold cross-validation was performed, with SMOTE applied exclusively to the training portion of each fold; validation folds and the independent test set retained their original class distributions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The effectiveness of the models was compared using the area under the ROC curve (AUC). In the training set, ComM achieved an AUC of 0.977, while in the test set, its AUC reached 0.935. ComM demonstrated the best performance (training set: AUCComM &amp;gt; AUCDTLRM &amp;gt; AUCRadM &amp;gt; AUCClinM &amp;gt; AUCDTLM; test set: AUCComM &amp;gt; AUCDTLRM &amp;gt; AUCRadM &amp;gt; AUCDTLM &amp;gt; AUCClinM), showing excellent preoperative predictive capability for meningioma BI. The Hosmer-Lemeshow test indicated good model fit, and the calibration curve revealed that ComM was closest to the ideal curve.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ClinM, RadM, DTLM, DTLRM, and ComM based on 2.5D CE-T1WI all exhibited good performance in predicting meningioma BI. The clinical-radiomics-DTL fusion model (ComM) demonstrated the highest efficacy, suggesting that DTL provides additional features correlated with meningioma BI that differ from radiomics features. This model shows potential clinical utility for preoperative prediction; however, further external validation in larger multicenter cohorts is required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1935311","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:52:58Z","timestamp":1791348778000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Non-invasive preoperative MRI-based deep transfer learning radiomics model for predicting meningioma brain invasion"],"prefix":"10.3389","volume":"16","author":[{"given":"Dong","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Radiology, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]},{"name":"Tianjin Key Laboratory of Cerebral Blood Flow Reconstruction and Head and Neck Tumor New Technology Translation","place":["Tianjin, China"]},{"name":"Department of Radiology, Nayong Xinli Hospital","place":["Bijie, Guizhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajia","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]},{"name":"Tianjin Key Laboratory of Cerebral Blood Flow Reconstruction and Head and Neck Tumor New Technology Translation","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]},{"name":"Tianjin Key Laboratory of Cerebral Blood Flow Reconstruction and Head and Neck Tumor New Technology Translation","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiyue","family":"Jing","sequence":"additional","affiliation":[{"name":"Institute of Neurosurgery, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanzhi","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Radiology, Huanhu Hospital Affiliated to Tianjin Medical University","place":["Tianjin, China"]},{"name":"Tianjin Key Laboratory of Cerebral Blood Flow Reconstruction and Head and Neck Tumor New Technology Translation","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","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":"Acta Neuropathol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noaa190","article-title":"Extensive peritumoral edema and brain-to-tumor interface mri features enable prediction of brain invasion in meningioma: Development and validation","volume":"23","author":"Joo","year":"2021","journal-title":"Neuro Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2016.2631","article-title":"The potential of radiomic-based phenotyping in precision medicine: A review","volume":"2","author":"Aerts","year":"2016","journal-title":"JAMA Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/s42979-021-00815-1","article-title":"Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions","volume":"2","author":"Sarker","year":"2021","journal-title":"SN Comput Sci"},{"key":"B5","doi-asserted-by":"publisher","first-page":"bbad254","DOI":"10.1093\/bib\/bbad254","article-title":"Deep transfer learning for clinical decision-making based on high-throughput data: Comprehensive survey with benchmark results","volume":"24","author":"Toseef","year":"2023","journal-title":"Brief Bioinform"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.912600","article-title":"Deep learning in neuroimaging: Overcoming challenges with emerging approaches","volume":"13","author":"Smucny","year":"2022","journal-title":"Front Psychiatry"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.748144","article-title":"Differentiation of brain abscess from cystic glioma using conventional mri based on deep transfer learning features and hand-crafted radiomics features","volume":"8","author":"Bo","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"B9","doi-asserted-by":"publisher","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":"B10","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1007\/s10916-024-02105-8","article-title":"Comparison of vision transformers and convolutional neural networks in medical image analysis: A systematic review","volume":"48","author":"Takahashi","year":"2024","journal-title":"J Med Syst"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.4274\/dir.2024.242631","article-title":"The future of multimodal artificial intelligence models for integrating imaging and clinical metadata: A narrative review","volume":"31","author":"Simon","year":"2024","journal-title":"Diagn Interv Radiol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"111884","DOI":"10.1016\/j.ejrad.2024.111884","article-title":"Current status and future directions of explainable artificial intelligence in medical imaging","volume":"183","author":"Saw","year":"2025","journal-title":"Eur J Radiol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/neuonc\/noaa177","article-title":"Fully automated hybrid approach to predict the idh mutation status of gliomas via deep learning and radiomics","volume":"23","author":"Choi","year":"2021","journal-title":"Neuro Oncol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/jmri.28564","article-title":"Automated mr image prescription of the liver using deep learning: Development, evaluation, and prospective implementation","volume":"58","author":"Geng","year":"2023","journal-title":"J Magn Reson Imaging"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107437","article-title":"A survey and taxonomy of 2.5d approaches for lung segmentation and nodule detection in ct images","volume":"165","author":"Jenkin Suji","year":"2023","journal-title":"Comput Biol Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.mri.2023.03.012","article-title":"A segmentation-based method improving the performance of N4 bias field correction on t2weighted mr imaging data of the prostate","volume":"101","author":"Dovrou","year":"2023","journal-title":"Magn Reson Imaging"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2016.06.008","article-title":"Spatial normalization of brain images and beyond","volume":"33","author":"Mangin","year":"2016","journal-title":"Med Image Anal"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2954751","article-title":"An efficient method for multi-parameter mapping in quantitative mri using b-spline interpolation","volume":"39","author":"van Valenberg","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16396","article-title":"A robust and automatic ct-3d ultrasound registration method based on segmentation, context, and edge hybrid metric","volume":"50","author":"He","year":"2023","journal-title":"Med Phys"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.986437","article-title":"Development and validation of a predictive model combining clinical, radiomics, and deep transfer learning features for lymph node metastasis in early gastric cancer","volume":"9","author":"Zeng","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2019.04.022","article-title":"A deep learning radiomics model for preoperative grading in meningioma","volume":"116","author":"Zhu","year":"2019","journal-title":"Eur J Radiol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s00234-022-02894-0","article-title":"A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma","volume":"64","author":"Yang","year":"2022","journal-title":"Neuroradiology"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.acra.2022.11.007","article-title":"A ct-based deep learning radiomics nomogram to predict histological grades of head and neck squamous cell carcinoma","volume":"30","author":"Zheng","year":"2023","journal-title":"Acad Radiol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1935311\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T04:52:59Z","timestamp":1791348779000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1935311\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":24,"alternative-id":["10.3389\/fonc.2026.1935311"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1935311","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1935311"}}