Contrast-enhanced MRI images generated from non-contrast scans improve tumor detection
Mixture of Multi-Sequence Feature Difference for Contrast-Enhanced MRI Synthesis
Computer Vision and Pattern Recognition
Summary
Getting detailed MRI images with contrast agents can be expensive and carries some health risks. The authors developed a way to create these contrast-enhanced MRI images using regular MRI scans without injecting agents. Their method mixes information from different scan types in a smart way to better reconstruct tumor areas. Tests showed their images are close in quality to real contrast-enhanced images and help with accurate tumor identification.
What this means in practice
- •For radiology teams: Create contrast-enhanced MRI images from standard MRI sequences to avoid contrast agent usage and maintain diagnostic quality.
- •For medical image software developers: Incorporate adaptive multi-sequence feature fusion techniques to improve synthetic MRI image generation for tumor segmentation workflows.
Authors
Jonghun Kim, Junmo Kwon, Hyunjin Park
Abstract
Contrast-enhanced magnetic resonance imaging (CE-MRI) is crucial for accurately diagnosing and segmenting brain tumors. However, the acquisition of CE-MRI requires injecting contrast agents, which poses potential health risks and increases scan costs. Here, we propose a CE-MRI synthesis method from non-contrast sequences, reducing both risk and cost. Unlike existing methods that rely on channel-wise concatenation to fuse multi-sequence information for synthesis, we introduce a Mixture of Feature Difference (MoFD) module. The proposed module uses a dynamic weighting strategy to adaptively select and aggregate informative features from both individual source sequences and explicit differences among them. Quantitative and qualitative evaluations demonstrate that our proposed method outperforms baselines in terms of image fidelity and perceptual quality on the UCSF-PDGM and UPenn-GBM datasets. Our method successfully reconstructs tumor regions and achieves segmentation performance comparable to that obtained with real CE-MRI. Our ablation studies show that although adversarial learning improves perceptual quality, a regression-based variant of our method achieves higher structural fidelity.