Early prognostication of overall survival for pediatric diffuse midline gliomas using MRI radiomics and machine
Xinyang Liu1, Zhifan Jiang1, Holger R Roth2
1Sheikh Zayed Institute for Pediatric Surgical Innovation, Children's National Hospital.
Background:
Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors that are diagnosed and monitored through MRI. We developed an automatic pipeline to segment subregions of DMG and select radiomic features that predict patient overall survival (OS).
Methods:
We acquired diagnostic and post-radiation therapy (RT) multisequence MRI (T1, T1ce, T2, T2 FLAIR) and manual segmentations from two centers of 53 (internal cohort) and 16 (external cohort) DMG patients. We pretrained a deep learning model on a public adult brain tumor dataset, and finetuned it to automatically segment tumor core (TC) and whole tumor (WT) volumes. PyRadiomics and sequential feature selection were used for feature extraction and selection based on the segmented volumes. Two machine learning models were trained on our internal cohort to predict patient 1-year survival from diagnosis. One model used only diagnostic tumor features and the other used both diagnostic and post-RT features.
Results:
For segmentation, Dice score (mean [median]±SD) was 0.91 (0.94)±0.12 and 0.74 (0.83)±0.32 for TC, and 0.88 (0.91)±0.07 and 0.86 (0.89)±0.06 for WT for internal and external cohorts, respectively. For OS prediction, accuracy was 77% and 81% at time of diagnosis, and 85% and 78% post-RT for internal and external cohorts, respectively. Homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio indicate shorter OS.
Conclusions:
Machine learning analysis of MRI radiomics has potential to accurately and non-invasively predict which pediatric patients with DMG will survive less than one year from the time of diagnosis to provide patient stratification and guide therapy.
Insights
Machine learning models analyzing MRI radiomics can predict overall survival in pediatric diffuse midline gliomas (DMG). This approach aids in patient stratification and therapy guidance for these aggressive brain tumors.
Area of Science:
- Oncology
- Radiology
- Artificial Intelligence
Background:
- Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors requiring accurate diagnostic and prognostic tools.
- Current diagnosis and monitoring rely on Magnetic Resonance Imaging (MRI).
- Predicting patient overall survival (OS) is crucial for guiding treatment strategies.
Approach:
- Developed an automatic pipeline for segmenting DMG subregions (tumor core [TC] and whole tumor [WT]) using deep learning on multisequence MRI.
- Extracted and selected radiomic features from segmented tumor volumes using PyRadiomics and sequential feature selection.
- Trained machine learning models on radiomic features from diagnostic and post-radiation therapy (RT) MRI to predict 1-year patient survival.
Key Points:
- Achieved high segmentation accuracy with Dice scores of 0.91 for TC and 0.88 for WT on the internal cohort.
- OS prediction models demonstrated accuracies of 77% (diagnostic) and 85% (post-RT) for the internal cohort.
- Identified homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio as indicators of shorter OS.
Conclusions:
- Machine learning analysis of MRI radiomics offers a non-invasive method for predicting survival in pediatric DMG patients.
- The findings support using radiomic features for early patient stratification and personalized therapy guidance.
- This approach has the potential to significantly improve outcomes for children diagnosed with diffuse midline gliomas.
