Enhancement Without Contrast: Stability-Aware Multicenter Machine Learning for Glioma MRI Imaging
Preprint
Abstract
Gadolinium-based contrast agents (GBCAs) are central to glioma imaging but raise safety, cost, and accessibility concerns. Predicting contrast enhancement from non-contrast MRI using machine learning (ML) offers a safer alternative, as enhancement reflects tumor aggressiveness and informs treatment planning. Yet scanner and cohort variability hinder robust model selection. We propose a stability-aware framework to identify reproducible ML pipelines for multicenter prediction of glioma MRI contrast enhancement. We analyzed 1,446 glioma cases from four TCIA datasets (UCSF-PDGM, UPENN-GB, BRATS-Africa, BRATS-TCGA-LGG). Non-contrast T1WI served as input, with enhancement derived from paired post-contrast T1WI. Using PyRadiomics under IBSI standards, 108 features were extracted and combined with 48 dimensionality reduction methods and 25 classifiers, yielding 1,200 pipelines. Rotational validation was trained on three datasets and tested on the fourth. Cross-validation prediction accuracies ranged from 0.91 to 0.96, with external testing achieving 0.87 (UCSF-PDGM), 0.98 (UPENN-GB), and 0.95 (BRATS-Africa), with an average of 0.93. F1, precision, and recall were stable (0.87 to 0.96), while ROC-AUC varied more widely (0.50 to 0.82), reflecting cohort heterogeneity. The MI linked with ETr pipeline consistently ranked highest, balancing accuracy and stability. This framework demonstrates that stability-aware model selection enables reliable prediction of contrast enhancement from non-contrast glioma MRI, reducing reliance on GBCAs and improving generalizability across centers. It provides a scalable template for reproducible ML in neuro-oncology and beyond.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Radiological and Biological Dictionary of Radiomics Features: Addressing Understandable AI Issues in Personalized Prostate Cancer, Dictionary Version PM1.0Journal of Imaging Informatics in Medicine, 2025
- Prediction of Parkinson’s disease pathogenic variants using hybrid Machine learning systems and radiomic featuresPhysica Medica, 2023
- The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomicsScientific Data, 2022
- Brain tumor image generation using an aggregation of GAN models with style transferScientific Reports, 2022
- Machine learning for medical imaging: methodological failures and recommendations for the futurenpj Digital Medicine, 2022
- Federated learning for multi-center imaging diagnostics: a simulation study in cardiovascular diseaseScientific Reports, 2022
- Feature selection and machine learning methods for optimal identification and prediction of subtypes in Parkinson's diseaseComputer Methods and Programs in Biomedicine, 2021
- Robust identification of Parkinson's disease subtypes using radiomics and hybrid machine learningComputers in Biology and Medicine, 2021
- MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variabilityScientific Reports, 2020
- Brain tissue gadolinium retention in pediatric patients after contrast-enhanced magnetic resonance exams: pathological confirmationPediatric Radiology, 2020