Tag: Radiomics

Posted on

Predictive models for assessing the risk of brain aneurysm rupture

J Neurosurg 143:607–614, 2025

This study evaluated predictive models for brain aneurysm rupture risk using clinical, morphological, and advanced MRI radiomics data. Models combining these factors, especially radiomics, significantly improved accuracy in identifying symptomatic aneurysms, supporting a comprehensive, personalized approach for aneurysm risk stratification and treatment decisions.

• The study evaluated predictive models for assessing the risk of brain aneurysm rupture using high-resolution MRI, clinical, morphological, and radiomic data.

• 129 intracranial aneurysms were analyzed; 26% were symptomatic (ruptured or with warning symptoms).

• The PHASES score alone had low predictive ability (AUC 0.61–0.62) for symptomatic aneurysms.

• Adding morphological metrics (especially size ratio) and smoking status improved prediction (AUC up to 0.79).

• Incorporating aneurysm wall enhancement (AWE) metrics further increased model performance (AUC 0.82).

• The best model included age and radiomics features, achieving the highest predictive accuracy (AUC 0.87, 88% sensitivity).

• Younger age, current smoking, larger size ratio, and higher wall enhancement were associated with symptomatic aneurysms.

• A comprehensive approach using clinical, morphological, and advanced imaging/radiomics data improves aneurysm risk stratification.

Posted on

Machine Learning for the Prediction of Molecular Markers in Glioma on Magnetic Resonance Imaging: A Systematic Review and Meta-Analysis

Neurosurgery 89:31–44, 2021

Molecular characterization of glioma has implications for prognosis, treatment planning, and prediction of treatment response. Current histopathology is limited by intratumoral heterogeneity and variability in detection methods. Advances in computational techniques have led to interest in mining quantitative imaging features to noninvasively detect genetic mutations.

OBJECTIVE: To evaluate the diagnostic accuracy of machine learning (ML) models in molecular subtyping gliomas on preoperative magnetic resonance imaging (MRI).

METHODS: A systematic search was performed following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) guidelines to identify studies up to April 1, 2020. Methodological quality of studies was assessed using the Quality Assessment for Diagnostic Accuracy Studies (QUADAS)-2. Diagnostic performance estimates were obtained using a bivariate model and heterogeneity was explored using metaregression.

RESULTS: Forty-four original articles were included. The pooled sensitivity and specificity for predicting isocitrate dehydrogenase (IDH) mutation in training datasets were 0.88 (95% CI 0.83-0.91) and 0.86 (95% CI 0.79-0.91), respectively, and 0.83 to 0.85 in validation sets. Use of data augmentation and MRI sequence type were weakly associated with heterogeneity. Both O6-methylguanine-DNA methyltransferase (MGMT) gene promoter methylation and 1p/19q codeletion could be predicted with a pooled sensitivity and specificity between 0.76 and 0.83 in training datasets.

CONCLUSION: ML application to preoperative MRI demonstrated promising results for predicting IDHmutation, MGMT methylation, and 1p/19q codeletion in glioma. Optimized ML models could lead to a noninvasive, objective tool that captures molecular information important for clinical decisionmaking. Future studies should use multicenter data, external validation and investigate clinical feasibility of ML models.

Proudly powered by WordPress