Related Experiment Video
Updated: Jun 11, 2026
Live-3D-Cell Immunocytochemistry Assays of Pediatric Diffuse Midline Glioma
Published on: November 11, 2021
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, Washington, District of Columbia, USA.
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, and T2 FLAIR) and manual segmentations from 2 centers: 53 from 1 center formed the internal cohort and 16 from the other center formed the external cohort. We pretrained a deep learning model on a public adult brain tumor data set (BraTS 2021), 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 12-month survival from diagnosis. One model used only data obtained at diagnosis prior to any therapy (baseline study) and the other used data at both diagnosis and post-RT (post-RT study).
Results:
Overall survival prediction accuracy was 77% and 81% for the baseline study, and 85% and 78% for the post-RT study, 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 noninvasively predict which pediatric patients with DMG will survive less than 12 months from the time of diagnosis to provide patient stratification and guide therapy.
Insights
Machine learning using MRI radiomics can predict survival in pediatric diffuse midline gliomas (DMG). This approach aids in identifying patients likely to survive less than 12 months, guiding personalized treatment strategies.
Area of Science:
- Neuro-oncology
- Medical imaging analysis
- Machine learning in medicine
Background:
- Diffuse midline gliomas (DMG) are aggressive pediatric brain tumors.
- MRI is crucial for DMG diagnosis and monitoring.
- Predicting patient survival is essential for guiding treatment.
Purpose of the Study:
- To develop an automatic pipeline for segmenting DMG subregions.
- To identify radiomic features that predict patient overall survival (OS).
- To create machine learning models for predicting 12-month survival in pediatric DMG patients.
Main Methods:
- Acquired multisequence MRI data from two centers (internal and external cohorts).
- Utilized a deep learning model for automatic segmentation of tumor core (TC) and whole tumor (WT) volumes.
- Employed PyRadiomics and sequential feature selection for radiomic feature extraction and selection.
- Trained machine learning models on baseline and post-radiation therapy (RT) data to predict 12-month survival.
Main Results:
- Achieved overall survival prediction accuracies ranging from 77% to 85% across internal and external cohorts.
- Identified homogeneous WT intensity in baseline T2 FLAIR and larger post-RT TC/WT volume ratio as indicators of shorter OS.
- Demonstrated the effectiveness of radiomic features in predicting survival outcomes.
Conclusions:
- Machine learning analysis of MRI radiomics offers a non-invasive method for predicting survival in pediatric DMG.
- This approach can accurately stratify patients likely to survive less than 12 months.
- Findings support the use of radiomics for guiding therapy and improving patient management.
