Article Figures & Data
Figures
- FIG 1.
Receiver operating characteristic curve with a 4-fold cross-validation scheme to predict BRAF status using radiomics of FLAIR MR images. Std. dev. indicates standard deviation.
- FIG 2.
Receiver operating characteristic curve of the external validation using the optimal hyperparameters obtained by 4-fold cross-validation.
- FIG 3.
Axial FLAIR images of pLGG. A, A 7-year-old boy. Infratentorial, BRAF V600E-mutated JPA. B, A 12-year-old boy. Supratentorial intraventricular, BRAF-fused ganglioma. C, A 7-year-old boy. Left temporal BRAF V600E-mutated dysembryoplastic neuroepithelial tumor. D, An 8-year-old boy. Right temporal BRAF V600E-mutated pleomorphic xanthoastrocytoma.
Tables
Institutional Cohort Toronto Stanford No. of patients 94 21 Age (mean) (yr) 9.4 8.37 Male sex (No.) (%) 45 (48) 12 (57) Histologic diagnosis (No.) JPA 54 12 GG 14 7 LGA 11 PMA 4 2 PXA 5 DNET 2 DA 2 GC 1 ODG 1 Molecular subgroup (No.) (%) BRAF fusion 62 (66) 14 (66) BRAF mutation 32 (34) 7 (34) FLAIR availability (No.) 94 21 Supratentorial (No.) (%) 43 (46) 6 (28) Transtentorial (No.) (%) 0 1 (5) Infratentorial (No.) (%) 51 (54) 14 (67) Note:—GG indicates ganglioglioma; LGA, low-grade astrocytoma; PMA, pilomyxoid astrocytoma; PXA, pleomorphic xanthoastrocytoma; DNET, dysembryoplastic neuroepithelial tumor; DA, diffuse astrocytoma; GC, gangliocytoma; ODG, oligodendroglioma.
No. of Folds No. of Trees AUC (SD) (95% CI) Mean Sensitivity (95% CI) Mean Specificity (95% CI) Mean PPV (95% CI) Mean NPV (95% CI) Top 10 Predictive Features on the External Dataset 4 25 0.75 (SD, 0.12) (0.62–0.89) 0.72 (0.60–0.84) 0.86 (0.76–0.95) 0.73 (0.60–0.87) 0.85 (0.80–0.91) (585, 374, 761, 22, 17, 560, 344, 258, 148, 108) Note:—SD indicates Standard Deviation; PPV, Positive Predictive Value; NPV; Negative Predictive Value.
No. Source Feature Category Feature 585 3D wavelet transform Gray-level difference matrix Small dependence low gray-level emphasis 374 3D wavelet transform Gray-level size zone matrix Zone percentage 761 3D wavelet transform Gray-level difference matrix Dependence entropy 22 Original Gray-level difference matrix Dependence nonuniformity normalized 17 Original Gray-level difference matrix Dependence entropy 560 3D wavelet transform Gray-level size zone matrix Zone percentage 344 3D wavelet transform Histogram Entropy 258 3D wavelet transform Gray-level run-length Gray-level variance 148 3D wavelet transform Histogram Uniformity 108 3D wavelet transform Gray-level difference matrix Gray-level variance ↵a Radiomic features are ranked from top to bottom according to their importance.
Variable P Value Odds Ratio (95% CI) Age .04 1.14 (1.008–1.30) Location <.001 18.80 (4.96–94.6) Sex .96 ↵a Older age and supratentorial location of tumor are significant predictors of BRAF V600E mutation. Sex is not a predictor.
Jump to section
Related Articles
Cited By...
- Imaging Clusters of Pediatric Low-Grade Glioma Are Associated with Distinct Molecular Characteristics
- Segmentation-Free Pretherapeutic Assessment of BRAF-Status in Pediatric Low-Grade Gliomas
- Multiparametric MRI Along with Machine Learning Informs on Molecular Underpinnings, Prognosis, and Treatment Response in Pediatric Low-Grade Glioma
- Imaging Clusters of Pediatric Low-Grade Glioma are Associated with Distinct Molecular Characteristics
- Identification of Multiclass Pediatric Low-Grade Neuroepithelial Tumor Molecular Subtype with ADC MR Imaging and Machine Learning
- Artificial Intelligence in the Future Landscape of Pediatric Neuroradiology: Opportunities and Challenges
- Juvenile pilocytic astrocytoma in a child with a prior normal neonatal brain MRI
- Early prognostication of overall survival for pediatric diffuse midline gliomas using MRI radiomics and machine learning: a two-center study
- Systematic Literature Review of Machine Learning Algorithms Using Pretherapy Radiologic Imaging for Glioma Molecular Subtype Prediction
- Utilizing the Amide Proton Transfer Technique to Characterize Diffuse Gliomas Based on the WHO 2021 Classification of CNS Tumors
- MR Imaging Characteristics and ADC Histogram Metrics for Differentiating Molecular Subgroups of Pediatric Low-Grade Gliomas
- Evolving Role and Translation of Radiomics and Radiogenomics in Adult and Pediatric Neuro-Oncology
- ADC Histogram Analysis of Pediatric Low-Grade Glioma Treated with Selumetinib: A Report from the Pediatric Brain Tumor Consortium