Multiclass Radiomics-Based Prediction of BRAF Mutation Status in Pediatric Low-Grade Gliomas Using Multisequence MRI

Pediatric low-grade gliomas (pLGGs) are the most common brain tumors in children and frequently harbor BRAF alterations, most commonly KIAA1549-BRAF fusions and BRAF V600E mutations, which have distinct therapeutic implications. The aim of our study was to assess multiclass radiomics-based prediction of BRAF mutation status in children with pLGGs using multisequence MRI. This study follows TRIPOD+AI guidelines.

This retrospective bi-institutional study included pediatric patients with pLGGs and known BRAF mutation status who underwent presurgical MRI between January 2009 and January 2023. Tumors were manually segmented, and radiomics features were extracted using PyRadiomics. Random forest classifiers were trained for 3-class classification (BRAF fusion vs BRAF V600E vs non-BRAF) using clinical-only, radiomics-only, and combined models. Performance was evaluated with leave-one-out cross-validation, and results were compared across single-sequence and multisequence approaches. Single-sequence models were trained using all available patients for each MRI sequence, whereas multisequence models were restricted to the subset of 180 patients with all 4 sequences available.

Five hundred eleven children were included (mean age 8.5 ± 5.1 years; 45% girls). Molecular subtypes included BRAF fusion (223/511; 44.6%), BRAF V600E (105/511; 21.0%), and non-BRAF tumors (172/511; 34.4%). FLAIR sequences were available for 495, T2WI for 454, contrast-enhanced T1WI (CE-T1WI) for 285, and ADC maps for 252 children. All sequences were available for 180 children. FLAIR was the best-performing single sequence (area under the curve [AUC] 0.82), followed by T2WI (0.80), ADC (0.77), and CE-T1WI (0.75). Reported AUC values represent macro-average one-vs-rest performance across the 3 molecular classes. Combined clinical-radiomics models consistently outperformed single-source models. In the 180-patient multisequence cohort, radiomics feature concatenation (macro-AUC 0.79) and ensemble modeling (macro-AUC 0.79) both outperformed single-sequence approaches (P < .001). Feature analysis showed FLAIR-derived features dominated, but adding T2, ADC, and CE-T1WI improved balanced classification across subtypes.

MRI-based machine learning models may support noninvasive prediction of BRAF mutation status in pLGGs. FLAIR is the best-predicting single sequence, but multisequence integration was associated with improved and more balanced performance. These findings support multisequence radiomics as a promising tool to guide precision treatment in pLGGs, particularly when tissue sampling is not feasible.