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

arXiv:2608.25648v1 Announce Type: new Abstract: Dynamic contrast-enhanced breast MRI is central to cancer diagnosis and monitoring, but requires gadolinium-based contrast agents. In this work, we address pre-to-post contrast breast MRI synthesis for the MAMA-SYNTH challenge. We propose MAMA-FLUX.2, a conditional latent flow-matching approach based on FLUX.2-Klein-4B. The pre-contrast image is encoded as spatial conditioning, while the model predicts the flow field associated with the post-contrast target latent. To adapt the pretrained model efficiently, we use LoRA fine-tuning and introduce a regional training objective combining global flow matching, tumor-region supervision, and stable foreground regularization. We further investigate LoRA rank, intensity windowing, and regional loss weights on axial slices, prioritizing clinically relevant tumor-focused metrics. Our ablation study shows that moderate tumor and stable-foreground weighting improves the trade-off between image fidelity and tumor-region accuracy. The final model achieves the best overall balance with LoRA rank/alpha=64/64, MHA_{max}=25, lambda_{tumor}=0.25, and lambda_{stable}=0.1. These results demonstrate that compact pretrained rectified-flow transformers can be adapted for contrast-enhanced MRI synthesis using parameter-efficient fine-tuning and task-aware regional losses.

Related

• Contrast-X: A Multi-Modal Contrast Image Synthesis Benchmark and Universal Modality Flow Matching
• Pre- to Post-Contrast Synthesis of Breast DCE-MRI using Latent Bridge Matching
• Spatio-Temporal Mixture-of-Modality-Experts Diffusion for Quantitative DCE-MRI Synthesis from Incomplete MR Sequences
• Predictive Enhancement Calibration for Latent Breast MRI Virtual Contrast Enhancement

Source: arXiv cs.CV | 2026-08-27