Predicting brain tumour enhancement from non-contrast MR imaging with artificial intelligence

2025-08-19

AI Summary

Gadolinium-based contrast agents (GBCAs) in brain tumor MRI pose risks including nephrotoxicity, allergic reactions, and limitations in pediatric populations. To address these challenges, we propose a contrast-free artificial intelligence framework that predicts contrast-enhanced (CE) lesion appearance solely from non-contrast T1, T2, and T2/FLAIR sequences. This is the first study to validate such a paradigm across a multicenter, age-diverse, and histopathologically heterogeneous brain tumor dataset—challenging the clinical reliance on GBCAs. We employ end-to-end segmentation and CE prediction using nnU-Net, SegResNet, and SwinUNETR; nnU-Net achieves optimal performance: balanced accuracy of 83%, sensitivity of 91.5%, R² = 0.859 for CE volume prediction, and Dice > 0.7 in 50.2% of cases—surpassing radiologist performance. Our work establishes a generalizable, contrast-free MRI methodology for brain tumor assessment, introducing a novel clinical paradigm.

Technology Category

• Computer Vision: Segmentation
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Graph-based Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Brain tumour imaging assessment typically requires both pre- and post-contrast MRI, but gadolinium administration is not always desirable, such as in frequent follow-up, renal impairment, allergy, or paediatric patients. We aimed to develop and validate a deep learning model capable of predicting brain tumour contrast enhancement from non-contrast MRI sequences alone. We assembled 11089 brain MRI studies from 10 international datasets spanning adult and paediatric populations with various neuro-oncological states, including glioma, meningioma, metastases, and post-resection appearances. Deep learning models (nnU-Net, SegResNet, SwinUNETR) were trained to predict and segment enhancing tumour using only non-contrast T1-, T2-, and T2/FLAIR-weighted images. Performance was evaluated on 1109 held-out test patients using patient-level detection metrics and voxel-level segmentation accuracy. Model predictions were compared against 11 expert radiologists who each reviewed 100 randomly selected patients. The best-performing nnU-Net achieved 83% balanced accuracy, 91.5% sensitivity, and 74.4% specificity in detecting enhancing tumour. Enhancement volume predictions strongly correlated with ground truth (R2 0.859). The model outperformed expert radiologists, who achieved 69.8% accuracy, 75.9% sensitivity, and 64.7% specificity. 76.8% of test patients had Dice over 0.3 (acceptable detection), 67.5% had Dice over 0.5 (good detection), and 50.2% had Dice over 0.7 (excellent detection). Deep learning can identify contrast-enhancing brain tumours from non-contrast MRI with clinically relevant performance. These models show promise as screening tools and may reduce gadolinium dependence in neuro-oncology imaging. Future work should evaluate clinical utility alongside radiology experts.

Problem

• Predicting brain tumour enhancement without contrast MRI
• Reducing gadolinium dependence in neuro-oncology imaging
• Developing AI models to segment enhancing tumours noninvasively

Innovation

• Deep learning predicts tumor enhancement from non-contrast MRI
• AI models segment tumors using T1, T2, and FLAIR sequences only
• nnU-Net outperforms radiologists in detecting enhancing brain tumors