Enhancement Without Contrast: Stability-Aware Multicenter Machine Learning for Glioma MRI Imaging

2025-09-12

AI Summary

This study addresses safety concerns, high costs, and limited accessibility associated with gadolinium-based contrast agents (GBCAs) in glioma MRI diagnosis, as well as the poor generalizability of existing predictive models across multi-center settings. We propose a stability-aware machine learning framework that systematically identifies a robust radiomic workflow: PyRadiomics (adhering to IBSI standards) extracts 108 non-contrast MRI features; these are combined with 48 dimensionality reduction methods and 25 classifiers, evaluated via rotating validation for multi-center training and assessment. The optimal pipeline—MI-ETr—achieves cross-validated accuracy of 0.91–0.96, and external validation yields mean accuracy of 0.93 and F1-scores of 0.87–0.96. This workflow significantly enhances cross-platform stability and clinical applicability, establishing a reproducible, highly robust paradigm for contrast-free prediction of glioma enhancement.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Safety and Robustness

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

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.

Problem

• Predicting glioma MRI contrast enhancement without gadolinium agents
• Addressing scanner and cohort variability in multicenter ML models
• Identifying stable ML pipelines for reproducible enhancement prediction

Innovation

• Stability-aware framework for multicenter ML
• Rotational validation across four TCIA datasets
• MI with ETr pipeline for reliable prediction