Fast Cross-Strength Multi-Contrast Brain MRI Translation
Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching
This research provides a faster and more efficient method for translating brain MRI images, which is crucial for medical analysis and research.
A new model called Latent Bridge Matching achieves fast synthesis of multi-contrast brain MRI images across different field strengths. It solves a key challenge in medical imaging by creating comparable images from different acquisition settings. The model was tested on the MRIxFields2026 challenge and can generate 30 slices in under 90 seconds on a single GPU.
Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching
Magnetic Resonance Imaging (MRI) acquired at different field strengths exhibits pronounced variation in noise, resolution, homogeneity, and contrast, which limits comparability across acquisition settings and complicates downstream analysis. We address this with a unified conditional model for controllable field-to-field synthesis, built on the framework of conditional latent bridge matching. Our single model achieves highly competitive results across the validation phase for all three tasks of the MRIxFields2026 challenge without task-specific architectures or training. We achieve fast generation with only a single inference step, producing all modality and field-strength combinations for $30$ axial slices in under $90$ seconds, as well as cross-modality-strength translation for a full volume in under $70$ seconds, on a single NVIDIA A5000 GPU. We further provide extensive ablations regarding different components of our solution. Code: https://gitlab.com/siddharthsrivastava/mrixfields-2026