The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2607. 19137v1 Announce Type: cross Abstract: Inferring contrast enhancement from one pre-contrast breast MRI slice is underdetermined: post-contrast appearance contains physiological information that is not uniquely encoded in baseline anatomy.
arXiv:2607. 29394v1 Announce Type: cross Abstract: Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is essential for breast cancer management, but reliance on gadolinium-based contrast agents (GBCAs) restricts use in contraindicated populations, prolongs scan protocols, and presents environmental toxicity concerns.
Inferring contrast enhancement from one pre-contrast breast MRI slice is underdetermined: post-contrast appearance contains physiological information that is not uniquely encoded in baseline anatomy. Optimizing only paired pixel fidelity can suppress uncertain lesion enhancement, whereas adversarial or stochastic generative objectives can favor realistic post-contrast appearance without guaranteeing patient-specific lesion fidelity.
The study presents an anatomy-aware deep learning framework that generates post-contrast breast MRI from pre-contrast images, focusing on tumor and background parenchymal enhancement regions. Using a dataset of 649 patients and 6,251 image pairs, the model incorporates breast mask consistency, lesion-region supervision, and BPE-region supervision within an image-to-image translation architecture. Quantitative metrics, a radiologist reader study, and Ki‑67 classification experiments demonstrate that the proposed method surpasses Pix2Pix, Pix2PixHD, diffusion-based synthesis, and mask-supervised baselines, while Ki‑67 performance remains comparable between real and synthetic images.
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.
arXiv:2606. 24313v1 Announce Type: new Abstract: AI-driven image-to-image synthesis is rapidly advancing, with growing applications in medical imaging.