Peer-reviewed article
IMG-14. DEVELOPING A PREDICTIVE GRADING MODEL FOR CHILDREN WITH GLIOMAS BASED ON DIFFUSION KURTOSIS IMAGING METRICS: ACCURACY AND CLINICAL CORRELATIONS WITH SURVIVAL
Voicu I, Napolitano A, Carboni A, Lattavo L, Carai A et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This is a medical imaging study that develops a computational model to grade brain tumors (gliomas) in children using diffusion kurtosis imaging metrics. The model was tested on 59 children and achieved high accuracy in distinguishing low-grade from high-grade tumors. While the research involves children as subjects, it is a diagnostic imaging study focused on tumor classification and survival prediction rather than child well-being, health outcomes, or interventions to improve children's lives.
Key points
- A predictive model using diffusion kurtosis imaging achieved 94.6% accuracy in grading pediatric gliomas
- The model's predictions correlated significantly with progression-free survival outcomes
- Study included 59 children: 46 with low-grade gliomas and 13 with high-grade gliomas
Limitations
This is a retrospective diagnostic imaging study that develops a grading tool rather than testing an intervention to improve child health or well-being. It does not evaluate whether any treatment or support program improves outcomes for children with gliomas.
Abstract
Abstract PURPOSE To develop a predictive grading model based on diffusion kurtosis imaging (DKI) metrics in children affected by gliomas, and to investigate the clinical impact of the model via correlations with overall survival and progression-free survival. MATERIALS AND METHODS We retrospectively studied 59 children (33M, 26F, median age 7.2 years) affected by gliomas on a 3T magnet. Patients with tumor locations other than infratentorial midline were included. Conventional and DKI sequences were obtained. Mean kurtosis (MK), axial kurtosis (AK), radial kurtosis (RK), fractional anisotropy (FA) and apparent diffusion coefficient (ADC) maps were obtained. Whole tumor volumes (VOIs) were segmented semiautomatically. Mean DKI values were calculated for each metric. The quantitative values from DKI-derived metrics were used to develop a predictive grading model with penalized logistic regression (glmnet package, R). Elasticnet regularization was used to avoid model overfitting. Fitted model coefficients from each metric were used to develop a probability prediction of a high-grade glioma (HGG). Grading accuracy of the resulting probabilities was tested with ROC analysis. Finally, model predictions were correlated to progression-free survival (PFS) with a Kaplan-Meier analysis. RESULTS The cohort included 46 patients with low-grade gliomas (LGG) and 13 patients with HGG. The developed model predictions yielded an AUC of 0.946 (95%CI: 0.890–1). Model predictions were significantly correlated with PFS (23.1 months for HGG vs 34.7 months for LGG, p<0.004). CONCLUSION In our cohort, a DKI-based predictive model was highly accurate for pediatric glioma grading. DKI-based model predictions were significantly correlated with progression-free survival.