Related Experiment Video
Updated: Jun 12, 2025
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
Machine learning-based nomogram for distinguishing between supratentorial extraventricular ependymoma and
Ling Chen1, Weijiao Chen1, Chuyun Tang2
1Department of Radiology, Liuzhou Worker's Hospital, Liuzhou, Guangxi, China.
Objective:
To develop a machine learning-based nomogram for distinguishing between supratentorial extraventricular ependymoma (STEE) and supratentorial glioblastoma (GBM).
Methods:
We conducted a retrospective analysis on MRI datasets obtained from 140 patients who were diagnosed with STEE (n=48) and GBM (n=92) from two institutions. Initially, we compared seven different machine learning algorithms to determine the most suitable signature (rad-score). Subsequently, univariate and multivariate logistic regression analyses were performed to identify significant clinical predictors that can differentiate between STEE and GBM. Finally, we developed a nomogram by visualizing the rad-score and clinical features for clinical evaluation.
Results:
The TreeBagger (TB) outperformed the other six algorithms, yielding the best diagnostic efficacy in differentiating STEE from GBM, with area under the curve (AUC) values of 0.735 (95% CI: 0.625-0.845) and 0.796 (95% CI: 0.644-0.949) in the training set and test set. Furthermore, the nomogram incorporating both the rad-score and clinical variables demonstrated a robust predictive performance with an accuracy of 0.787 in the training set and 0.832 in the test set.
Conclusion:
The nomogram could serve as a valuable tool for non-invasively discriminating between STEE and GBM.
Insights
A machine learning nomogram effectively distinguishes supratentorial extraventricular ependymoma (STEE) from glioblastoma (GBM). This AI tool aids in non-invasive diagnosis, improving patient management for these brain tumors.
Area of Science:
- Neuro-oncology
- Radiology
- Machine Learning in Medicine
Background:
- Supratentorial extraventricular ependymoma (STEE) and supratentorial glioblastoma (GBM) are distinct brain tumors requiring accurate differentiation for appropriate treatment.
- Distinguishing between STEE and GBM based solely on imaging can be challenging, necessitating advanced diagnostic tools.
Purpose of the Study:
- To develop and validate a machine learning-based nomogram for the non-invasive differentiation of STEE and GBM.
- To identify key clinical and imaging features that predict tumor type.
Main Methods:
- Retrospective analysis of MRI data from 140 patients (48 STEE, 92 GBM) across two institutions.
- Comparison of seven machine learning algorithms to identify the optimal radiomic signature (rad-score).
- Development of a nomogram integrating the rad-score and significant clinical predictors identified through logistic regression.
Main Results:
- The TreeBagger algorithm demonstrated superior performance in differentiating STEE from GBM, achieving an AUC of 0.796 in the test set.
- The developed nomogram, incorporating rad-score and clinical variables, showed strong predictive accuracy (0.832 in the test set).
Conclusions:
- The machine learning-based nomogram is a promising tool for the non-invasive discrimination between STEE and GBM.
- This approach can aid clinicians in making more accurate diagnoses and tailoring treatment strategies for patients with these brain tumors.
