← Back to all news
arXiv Machine Learning By Siddharth Srivastava, Till Bretschneider

Fast Cross-Strength Multi-Contrast Brain MRI Translation using Latent Bridge Matching

Read the original on arXiv Machine Learning →

The paper presents a unified conditional model for translating brain MRI scans across different field strengths and modalities using conditional latent bridge matching. The single model achieves competitive results on all three tasks of the MRIxFields2026 challenge without task‑specific architectures, and it generates 30 axial slices in under 90 seconds or a full volume in under 70 seconds on a single NVIDIA A5000 GPU. Extensive ablations of the model’s components are also provided.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Computer Vision
Aug 27

MAMA-FLUX.2: Image-to-Image Synthesis of Post-Contrast Breast DCE-MRI for the MAMA-SYNTH Challenge

The paper introduces MAMA-FLUX.2, a conditional latent flow‑matching model built on FLUX.2-Klein-4B, designed to synthesize post‑contrast breast DCE‑MRI from pre‑contrast images for the MAMA‑SYNTH challenge. It encodes the pre‑contrast image as spatial conditioning and predicts the flow field for the post‑contrast latent, adapting the pretrained model with LoRA fine‑tuning and a regional training objective that combines global flow matching, tumor‑region supervision, and stable foreground regularization. Ablation studies show that moderate tumor and stable‑foreground weighting improves the balance between image fidelity and tumor‑region accuracy, with the best configuration achieving a strong trade‑off using LoRA rank 64/64, MHA_max 25, λ_tumor 0.25, and λ_stable 0.1.

By Kamil Kwarciak, Marek Wodzinski
llmsagentsdiffusionfine-tuningbenchmarks
More like this →
Hugging Face Trending Papers
Jun 23

Prob-BBDM: a Probabilistic Brownian Bridge Diffusion Model for MRI sequence image-to-image translation

AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging. Multi-modal image analysis plays a crucial role in optimizing examination quality, yet acquiring multiple imaging modalities in clinical settings remains resource-intensive and time-consuming, especially for 3D imaging.

diffusioncomputer-visionmultimodal
More like this →