MRI-based preoperative WHO grade prediction in meningioma: development and comparison of deep learning, radiomics, clinical, and combined models in multicenter data.
10 affiliations
- 1Department of Radiology, Gazimagusa State Hospital, Famagusta, Northern Cyprus.
- 2Department of Neurological Surgery, School of Medicine and Public Health, University of Wisconsin, CSC K4/822, 600 Highland Avenue, Madison, WI, 53792, USA.
- 3Icahn School of Medicine at Mount Sinai, Biomedical Engineering and Imaging Institute, New York, NY, USA.
- 4Department of Neurosurgery, Istanbul Training and Research Hospital, University of Health Sciences, Istanbul, Turkey.
- 5Department of Neurosurgery, Bakirkoy Prof. Dr. Mazhar Osman Training and Research Hospital for Psychiatry, Neurology, and Neurosurgery, University of Health Sciences, Istanbul, Turkey.
- 6Department of Neurosurgery, Gazi University Faculty of Medicine, Ankara, Turkey.
- 7Department of Neurosurgery, Prof. Dr. Suleyman Yalcin City Hospital, Istanbul Medeniyet University, Istanbul, Turkey.
- 8Department of Radiology,Istanbul Training and Research Hospital, University of Health Sciences, Istanbul, Turkey.
- 9Department of Radiology,Bagcilar Training and Research Hospital, University of Health Sciences, Istanbul, Turkey.
- 10Department of Neurological Surgery, School of Medicine and Public Health, University of Wisconsin, CSC K4/822, 600 Highland Avenue, Madison, WI, 53792, USA. [email protected].
Abstract
Purpose
The objective of this study was to develop and externally validate complementary magnetic resonance imaging (MRI)-based models and their stacked combinations for preoperative World Health Organization (WHO) grading of intracranial meningioma.Methods
This retrospective multicenter study included 455 histopathologically confirmed meningiomas: a four-center development cohort (n = 346) with leave-one-center-out cross-validation and an external cohort (n = 109). Four base models used contrast-enhanced T1-weighted MRI: tumor + peritumoral radiomics, an nnU-Net segmentation-based classifier, frozen DINOv3 transfer-learning features, and clinical variables. All 15 combinations were prespecified and stacked using a linear meta-learner trained on development out-of-fold predictions. Frozen models were externally evaluated without modification.Results
WHO 2-3 tumors comprised 24.6% overall (112/455; development 20.5%; external 37.6%). External AUCs were 0.732 for nnU-Net, 0.703 for DINOv3, 0.645 for clinical, 0.628 for radiomics. The multimodal ensemble (nnU-Net+DINOv3+Clinical) achieved the highest external AUC (0.742), exceeding radiomics (ΔAUC +0.114, p = 0.008) but not nnU-Net (ΔAUC +0.011, p = 0.737). Compared with the clinical model, discrimination was higher but nonsignificant at the prespecified threshold (ΔAUC +0.098, p = 0.050), while reclassification improved (IDI +0.109, p < 0.001). Radiomics-containing combinations performed strongly in development but lost most discrimination externally. The multimodal ensemble had an external calibration slope of 1.32 (Brier 0.190) and net benefit above default strategies at thresholds ≥ 0.23.Conclusion
The multimodal ensemble achieved the highest external AUC but did not significantly exceed nnU-Net, which was the most transportable single predictor of meningioma grade. Clinical variables did not improve discrimination but enabled interpretable feature-level attribution. Handcrafted radiomics lacked external transportability.
Related
- Multiparametric MRI radiomics and clinical features for preoperative prediction of high-grade meningioma: a two-centre retrospective study
- CT-based multi-station lymph-node radiomics for preoperative prediction of lymph node metastasis in colorectal cancer: a proof-of-concept comparison with primary-tumor radiomics
- Development and validation of machine learning models for preoperative prediction of perioperative outcomes in patients with thymic epithelial tumors
- Development and validation of a machine learning model for preoperative prediction of intraoperative hypothermia in gynecological laparoscopic surgery: a two-center cohort study
- Foundation Model-Enabled Pathology-Informed MRI Model for Preoperative Prediction of Vessels Encapsulating Tumor Clusters in Resectable Hepatocellular Carcinoma: A Multicenter Retrospective Study.
BibTeX
@article{huryol2026mribased,
title = {{MRI-based preoperative WHO grade prediction in meningioma: development and comparison of deep learning, radiomics, clinical, and combined models in multicenter data.}},
author = {Cagin Huryol and Umid Sulaimanov and Murat Yuce and Nafiye Sanlier and Fikret Ozturk and Oyku Ozturk and Irem Altun and Gular Ismayilova and Huseyin Bozkurt and Taha Yasin Altunkaya and Ferdi Afsin and Abdullah Soydan Mahmutoglu and Amine Durmus and Burak Karaaslan and Ilhan Aydin and Mehmet Sabri Gurbuz and Ahmet Tan Cimilli and Okan Turk and Ufuk Erginoglu and Mustafa K Baskaya},
journal = {Journal of neuro-oncology},
year = {2026},
month = oct,
doi = {10.1007/s11060-026-05827-6},
url = {https://europepmc.org/article/MED/42875623},
note = {CC BY},
}
RIS
TY - JOUR
TI - MRI-based preoperative WHO grade prediction in meningioma: development and comparison of deep learning, radiomics, clinical, and combined models in multicenter data.
AU - Cagin Huryol
AU - Umid Sulaimanov
AU - Murat Yuce
AU - Nafiye Sanlier
AU - Fikret Ozturk
AU - Oyku Ozturk
AU - Irem Altun
AU - Gular Ismayilova
AU - Huseyin Bozkurt
AU - Taha Yasin Altunkaya
AU - Ferdi Afsin
AU - Abdullah Soydan Mahmutoglu
AU - Amine Durmus
AU - Burak Karaaslan
AU - Ilhan Aydin
AU - Mehmet Sabri Gurbuz
AU - Ahmet Tan Cimilli
AU - Okan Turk
AU - Ufuk Erginoglu
AU - Mustafa K Baskaya
PY - 2026
DA - 2026/10/14
JO - Journal of neuro-oncology
DO - 10.1007/s11060-026-05827-6
UR - https://europepmc.org/article/MED/42875623
AB - Purpose The objective of this study was to develop and externally validate complementary magnetic resonance imaging (MRI)-based models and their stacked combinations for preoperative World Health Organization (WHO) grading of intracranial meningioma.Methods This retrospective multicenter study included 455 histopathologically confirmed meningiomas: a four-center development cohort (n = 346) with leave-one-center-out cross-validation and an external cohort (n = 109). Four base models used contrast-enhanced T1-weighted MRI: tumor + peritumoral radiomics, an nnU-Net segmentation-based classifier, frozen DINOv3 transfer-learning features, and clinical variables. All 15 combinations were prespecified and stacked using a linear meta-learner trained on development out-of-fold predictions. Frozen models were externally evaluated without modification.Results WHO 2-3 tumors comprised 24.6% overall (112/455; development 20.5%; external 37.6%). External AUCs were 0.732 for nnU-Net, 0.703 for DINOv3, 0.645 for clinical, 0.628 for radiomics. The multimodal ensemble (nnU-Net+DINOv3+Clinical) achieved the highest external AUC (0.742), exceeding radiomics (ΔAUC +0.114, p = 0.008) but not nnU-Net (ΔAUC +0.011, p = 0.737). Compared with the clinical model, discrimination was higher but nonsignificant at the prespecified threshold (ΔAUC +0.098, p = 0.050), while reclassification improved (IDI +0.109, p < 0.001). Radiomics-containing combinations performed strongly in development but lost most discrimination externally. The multimodal ensemble had an external calibration slope of 1.32 (Brier 0.190) and net benefit above default strategies at thresholds ≥ 0.23.Conclusion The multimodal ensemble achieved the highest external AUC but did not significantly exceed nnU-Net, which was the most transportable single predictor of meningioma grade. Clinical variables did not improve discrimination but enabled interpretable feature-level attribution. Handcrafted radiomics lacked external transportability.
SN - 0167-594X
SN - 1573-7373
ER -