Related Experiment Video
Updated: Sep 6, 2025
A Protocol for Rapid Post-mortem Cell Culture of Diffuse Intrinsic Pontine Glioma DIPG
Published on: March 7, 2017
Radiomic Features Based on MRI Predict Progression-Free Survival in Pediatric Diffuse Midline Glioma/Diffuse
Matthias W Wagner1,2, Khashayar Namdar1,2, Marc Napoleone1
1Department of Diagnostic Imaging, Division of Neuroradiology, 7979The Hospital for Sick Children, Toronto, Canada.
Abstract:
Purpose: Biopsy-based assessment of H3 K27 M status helps in predicting survival, but biopsy is usually limited to unusual presentations and clinical trials. We aimed to evaluate whether radiomics can serve as prognostic marker to stratify diffuse intrinsic pontine glioma (DIPG) subsets. Methods: In this retrospective study, diagnostic brain MRIs of children with DIPG were analyzed. Radiomic features were extracted from tumor segmentations and data were split into training/testing sets (80:20). A conditional survival forest model was applied to predict progression-free survival (PFS) using training data. The trained model was validated on the test data, and concordances were calculated for PFS. Experiments were repeated 100 times using randomized versions of the respective percentage of the training/test data. Results: A total of 89 patients were identified (48 females, 53.9%). Median age at time of diagnosis was 6.64 years (range: 1-16.9 years) and median PFS was 8 months (range: 1-84 months). Molecular data were available for 26 patients (29.2%) (1 wild type, 3 K27M-H3.1, 22 K27M-H3.3). Radiomic features of FLAIR and nonenhanced T1-weighted sequences were predictive of PFS. The best FLAIR radiomics model yielded a concordance of .87 [95% CI: .86-.88] at 4 months PFS. The best T1-weighted radiomics model yielded a concordance of .82 [95% CI: .8-.84] at 4 months PFS. The best combined FLAIR + T1-weighted radiomics model yielded a concordance of .74 [95% CI: .71-.77] at 3 months PFS. The predominant predictive radiomic feature matrix was gray-level size-zone. Conclusion: MRI-based radiomics may predict progression-free survival in pediatric diffuse midline glioma/diffuse intrinsic pontine glioma.
Insights
Radiomics analysis of MRI scans can predict progression-free survival in pediatric diffuse intrinsic pontine glioma (DIPG). This non-invasive imaging technique offers a promising alternative to biopsies for stratifying DIPG patient subsets.
Area of Science:
- Neuro-oncology
- Medical Imaging
- Radiomics
- Pediatric Oncology
Background:
- H3 K27M mutation status from biopsies predicts survival in diffuse intrinsic pontine glioma (DIPG).
- Biopsies are invasive and typically reserved for rare presentations or clinical trials.
- There is a need for non-invasive prognostic markers to stratify DIPG patients.
Purpose of the Study:
- To evaluate radiomics as a non-invasive prognostic marker for stratifying DIPG subsets.
- To assess the predictive capability of radiomic features for progression-free survival (PFS) in pediatric DIPG.
Main Methods:
- Retrospective analysis of diagnostic brain MRIs from 89 children with DIPG.
- Extraction of radiomic features from tumor segmentations on FLAIR and nonenhanced T1-weighted MRI sequences.
- Application of a conditional survival forest model for PFS prediction, with data split into training (80%) and testing (20%) sets.
Main Results:
- Radiomic features from FLAIR and nonenhanced T1-weighted sequences significantly predicted PFS.
- The best FLAIR radiomics model achieved a concordance of 0.87 at 4 months PFS.
- The best T1-weighted radiomics model achieved a concordance of 0.82 at 4 months PFS; the combined model showed a concordance of 0.74 at 3 months PFS.
Conclusions:
- MRI-based radiomics shows potential as a non-invasive method for predicting PFS in pediatric diffuse midline glioma/DIPG.
- Radiomics can aid in stratifying DIPG patient subsets, potentially guiding treatment decisions.
- Gray-level size-zone matrix was identified as a predominant predictive radiomic feature.
