A benchmark radiomics model to preoperatively identify the histological grade of spinal meningiomas is constructed, suggesting a need to characterize the interplay between tumor grade and extent of resection as drivers of local disease control in SMs.
Abstract
Objective
Spinal meningiomas (SMs) are common primary spinal tumors for which surgery is considered the first-line treatment when safe and feasible. The ability to extrapolate the tumor grade from preoperative imaging may significantly inform early patient expectation-setting regarding recurrence. Building on radiomics studies in cranial meningiomas, the authors aimed to construct a benchmark radiomics model to preoperatively identify the histological grade of SMs.
Methods
Institutional surgical records from May 2012 to November 2025 were queried for pathology-confirmed meningiomas below the foramen magnum, with preoperative contrast-enhanced imaging available for segmentation. SMs were classified as low-grade (WHO grade 1) and high-grade (WHO grade 2 tumors and grade 1 tumors with atypia). Tumors were manually segmented, and features were extracted using the PyRadiomics software package. An ensemble model of k-nearest neighbors, random forest, and support vector machine classifiers was trained using nested cross-validation on a subset of 10 features to differentiate tumor grades. Clinical data for the cohort were also extracted, and disease control in an adjunctive clinical series was assessed.
Results
Seventy-four patients were included in radiomics analysis, with an area under the receiver operating characteristic curve of 0.879 and a mean F1 score of 0.748. The model's top 5 features were all texture features that differed significantly (p < 0.05) across low- and high-grade SMs. These included measures of tumor textural and contrast-enhancement heterogeneity, with overlap with features reported in radiomics models for histological grading of intracranial meningiomas. Fifty-five patients with a median radiographic follow-up of 22.2 (range 1.9-86.4) months remained for clinical analysis after exclusion of patients with less than 1 month of follow-up and syndromic meningiomas. Four recurrences occurred at a median of 20.8 (range 1.8-41.8) months. High-grade tumor pathology did not significantly impact progression-free survival (p = 0.682, log-rank test; Cox regression high vs low grade hazard ratio [HR] 0.62, 95% CI 0.06-6.11, p = 0.685). Subtotal resection was associated with poorer progression-free survival than gross-total resection (p = 0.004, log-rank test; Cox regression subtotal vs gross-total resection HR 10.62, 95% CI 1.46-77.05, p = 0.019). These findings remain contextualized within a relatively limited follow-up window and small recurrence event count, suggesting a need to characterize the interplay between tumor grade and extent of resection as drivers of local disease control in SMs.
Conclusions
A preoperative radiomics model can stratify high-grade SMs using open-source tools applied to single-institution data.
Gross-total resection is the primary surgical objective in meningioma management; however, predicting resectability preoperatively remains challenging, particularly for meningiomas located in the skull base that exhibit complex anatomical relationships. There is a lack of validated reproducible models that integrate known anatomical factors for surgery; similarly, the value of radiomics as a stand-alone predictor is still unclear. The aim of this study was to develop a machine learning model that combines clinical and radiomic features to estimate early postoperative residual meningioma.
This retrospective multicenter study included 369 patients who underwent meningioma resection from 2020 to 2024 and had available preoperative contrast-enhanced T1-weighted MRI. Patient data from 3 centers (n = 307) were used to develop the model using leave-one-center-out cross-validation, and an independent cohort (n = 62) was used for external validation. Radiomic features were derived from manually segmented meningiomas, filtered for reproducibility, and integrated with 6 predefined clinical variables. The clinical-only, radiomics-only, and combined models were trained using 4 machine learning classifiers. Model performance was assessed through cross-validation, independent external validation, and receiver operating characteristic analysis. Formal incremental benefit analyses were performed on the common overlap external subset, with predictions available for all compared models.
Residual meningioma occurred in 23.5% of patients in the development cohort and 14.5% in the external cohort. Lesion location and venous sinus involvement were significantly associated with residual status. Following the feature selection, 2 stable radiomic texture features were retained. In external validation, the combined radiomics-clinical k-nearest neighbors model achieved the highest area under the curve (0.821), with sensitivity of 0.889, specificity of 0.706, and accuracy of 0.733. Clinical variables provided most of the predictive value, whereas radiomic features provided only limited incremental value when added to the clinical model. Decision curve analysis revealed net benefit for the combined model within a narrow range of low thresholds.
In this multicenter study, which included external validation, clinical variables provided most of the predictive value for postoperative residual meningioma. Radiomic features alone showed limited discrimination and only modest added value beyond clinical predictors. These combined models could serve as decision-support tools for preoperative risk assessment in meningioma surgery but are not yet suitable for routine stand-alone clinical use.
Nafiye Şanlıer, Murat Yuce, Umid Sulaimanov et al.· Neurosurgical Focus· 0 citations
Aim
To identify radiomics parameters that distinguish spinal meningiomas from schwannomas and evaluate machine learning models using MRI data.
Methods
Patients with histopathologic diagnoses of spinal meningioma (n = 25) and schwannoma (n = 26) who underwent pre-surgical MRI were enrolled. Semantic features, including tumor location, longest diameter, foraminal extension, cystic changes, spinal cord compression, enhancement patterns, dural tail, and ginkgo leaf signs, were assessed using a single 3.0 T scanner. Radiomics features were extracted from T1-weighted, T2-weighted, STIR, and post-gadolinium T1-weighted images. Support Vector Machine (SVM) models were trained and validated using conventional MRI, radiomics features, and their combination.
Results
A significant gender difference was found, with more females in the meningioma group (84%, P = .039). Other significant factors included the longest tumor dimension (P = .03), presence of a dural tail sign (P < .001), intratumoral cystic changes (P = .003), ginkgo leaf sign (P = .01), and spinal cord compression (P < .001). Of the 444 extracted radiomics parameters, 186 demonstrated good reproducibility (ICC ≥ 0.75). Among these, 49 were retained for model construction. Model 1 (conventional MRI) achieved an AUC of 0.902, an accuracy of 0.882, a sensitivity of 0.884, and a specificity of 0.880. Model 2 (radiomics features) achieved an AUC of 0.909, an accuracy of 0.843, a sensitivity of 0.961, and a specificity of 0.720. Model 3 (combined features) demonstrated the highest performance with an AUC of 0.997, accuracy of 0.960, sensitivity of 1.000, and specificity of 0.920.
Conclusion
Combining radiomics with conventional MRI improves diagnostic accuracy in differentiating spinal meningiomas from schwannomas, supporting radiomics as a valuable non-invasive tool for preoperative diagnosis. Multicenter studies are needed to validate these findings and expand clinical applications.
Y. Güneş, S. Duran, Karabekir Ercan et al.· The Annals of Clinical and A...· 0 citations
Meningiomas are the most common primary central nervous system tumors and their biological behavior is closely related to histopathological grade and proliferative activity. This study investigated the associations between World Health Organization (WHO) grade, tumor location, mitotic activity, and Ki-67 labeling index in previously untreated meningiomas. We retrospectively analyzed 298 surgically treated primary meningiomas diagnosed between 2013 and 2025, re-evaluated according to the 2021 WHO Classification of Central Nervous System Tumors. Mitotic counts and Ki-67 labeling indices were assessed in hotspot areas. Associations between proliferation markers, grade, and anatomical location were analyzed statistically, and receiver operating characteristic (ROC) analyses determined optimal cut-off values. Of the tumors, 55.0% were WHO Grade 1, 41.6% Grade 2, and 3.4% Grade 3. Both markers increased significantly with grade and showed a strong positive correlation (ρ = 0.79, P < .001). Convexity meningiomas were associated with higher grades and increased proliferative activity, whereas skull base and spinal tumors predominantly exhibited lower grades and lower proliferation indices. ROC analyses demonstrated comparable discriminatory performance for Ki-67 and mitotic counts across WHO grades. In summary, proliferation markers strongly correlate with WHO grade and vary by tumor location, supporting their combined value in meningioma risk stratification.
Neşe Yeldir, Mohammad Sargolzaeimoghaddam, Maral Sargolzaeimoghaddam et al.· Journal of Neuropathology an...· 0 citations
Introduction: Gliomas are the most common primary brain tumours worldwide and can be broadly classified as low-grade or high-grade based on molecular and histopathological features. Methodology: A retrospective single-centre single-surgeon unmatched case‒control study was conducted using sociodemographic, clinical, and radiological information available from the Asiri Central Brain Tumour Registry on 36 patients histologically diagnosed with low-grade gliomas that presented to the Asiri Central Hospital, Sri Lanka between 2019-2022 and 36 patients with high-grade gliomas. Initial bivariate analysis was conducted using chi-square tests and Fisher’s exact tests, followed by multivariate analysis using logistic regression to develop the final model.Results: The mean age of the participants was 39.51 years (SD = 20.57 years), and the majority were males (n = 43, 59.37%). The initial bivariate analysis revealed that increased age (p = 0.004), hypertension (p = 0.005), dyslipidaemia(p = 0.042), total duration from symptom onset to presentation(p = 0.006) and contrast enhancement with IV gadolinium in MRI(p = 0.002) were significant factors for high-grade gliomas. The final logistic regression model identified male sex (p = 0.110, OR = 2.645), advanced age above 50 years(p = 0.014, OR = 5.217), speech deficit as a presenting complaint(p = 0.066, OR = 9.939) and contrast enhancement on MRI(p = 0.064, OR = 2.798) as predictors(Omnibus ꭓ2 (4) = 20.395, p < 0.001, R2 = 0.247 (Cox & Snell), 0.329 (Negelkerke) as predictors for high-grade gliomas.Conclusion: Sociodemographic and clinical characteristics combined with features of conventional MRIs can be utilized by clinicians to predict glioma grade preoperatively to plan and prepare treatment strategies.
W. Weerasekara, G. Jayaweera, D. Safeer et al.· The Sri Lanka Journal of Sur...· 0 citations
Background On conventional magnetic resonance imaging, pseudoprogression after radiotherapy for high-grade glioma may closely resemble true tumor progression, leading to unnecessary surgery, premature treatment escalation, or delayed appropriate therapy. We developed and internally validated an exploratory multivariable model for individualized pseudoprogression risk estimation. Methods This single-center retrospective cohort included 222 patients with World Health Organization 2021 central nervous system grade 3 or 4 glioma who underwent surgery followed by radiotherapy at Liuzhou Workers’ Hospital from January 2015 to December 2024. Pseudoprogression was adjudicated before modeling through multidisciplinary review; 13 pseudoprogression cases had histopathological confirmation, and non-histologically confirmed cases required at least 6 months of stable or improved follow-up imaging. The complete two-reader radiomics matrix was analyzed using a strict split-first workflow. Dataset partitioning preceded ICC filtering, Z-score normalization, and LASSO modeling. Results A total of 3,404 radiomic features were analyzed. After reproducibility filtering and LASSO selection, 17 radiomic features were retained to construct the locked RadScore. In the held-out validation cohort, the integrated model combining RadScore, rCBV, ADC, NLR, MGMT promoter methylation, and TMZ treatment achieved an AUC of 0.811 (95% CI: 0.696-0.925). The clinical-imaging model without RadScore achieved a validation AUC of 0.744 (95% CI: 0.614-0.873), whereas RadScore alone achieved an AUC of 0.771 (95% CI: 0.648-0.894). Conclusion The integrated model showed acceptable internal validation performance and provided a clinically interpretable framework for individualized PsP risk estimation by combining radiomic, perfusion-diffusion, inflammatory, molecular, and treatment-related information. External validation with standardized imaging protocols is warranted.
Jiang Zhou, Danmeng Zhang, Y. Hui et al.· Frontiers in Oncology· 0 citations
The identification of quantitative non-invasive imaging biomarkers, including radiomics, may complement molecular characterization and thereby improve clinical management of neuro-oncological patients. We aimed to identify imaging predictors with improved performance over clinical parameters to stratify patients with brain metastases into high and low-risk groups for overall survival (OS). 422 patients recruited by two neuro-oncological centers were included with first diagnosis of brain metastases from different primary tumors. From each patient, 15 clinical parameters and a total of 321 radiomic features extracted from cerebral MRI were employed in prediction models to classify patients into low- and high-risk groups for OS. The best performing model was a bootstrap aggregating model including only clinical features (test set: macro F-1 = 0.62, accuracy = 0.72), while the combined and radiomic datasets led to poorer results (test set: macro F-1 = 0.60, accuracy = 0.67; test set: macro F-1 = 0.62, accuracy = 0.52, respectively). However, in the subgroup of melanoma patients (n = 54), the radiomic dataset showed better predictive power over clinical and combined dataset (test set: macro F-1 score = 0.71, accuracy = 0.77). 80% and 67% of melanoma patients were correctly classified into the low- and the high-risk group for OS, respectively. Clinical features remained the strongest predictors of risk across patients with brain metastases from different primary tumors. Although, in melanoma patients, radiomic features provided better prediction of the survival outcome compared to clinical parameters alone.
J. Heugenhauser, Sabrina Herbst, T. Drucks et al.· Clinical and Experimental Me...· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduAug 17, 2026
A USAF cadet and a Lincoln Laboratory researcher found AI chatbots can help nontechnical service members produce viable software applications for their unique problems.
