Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study introduces MAMA-FLUX.2, a conditional latent flow-matching approach designed for synthesizing post-contrast breast DCE-MRI images from pre-contrast data, addressing challenges in cancer diagnosis and monitoring. By employing LoRA fine-tuning and a novel regional training objective, the model effectively balances image fidelity and tumor-region accuracy, achieving optimal performance metrics. The findings indicate that specific weighting strategies for tumor and stable foreground regions significantly enhance the synthesis quality, demonstrating the potential of compact pretrained transformers in medical imaging tasks.
Achieving a superior balance between image fidelity and tumor accuracy, MAMA-FLUX.2 redefines post-contrast MRI synthesis with a novel regional training approach.
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/$\alpha=64/64$, $\mathrm{MHA}_{\max}=25$, $\lambda_{\mathrm{tumor}}=0.25$, and $\lambda_{\mathrm{stable}}=0.1$. 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.