{"ID":6537438,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.11655","arxiv_id":"2607.11655","title":"Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis","abstract":"Conditional diffusion models can generate anatomically plausible medical ultrasound (US) images, but anatomical plausibility alone does not ensure realistic B-mode appearance. Most US pipelines adapt standard generative architectures and condition them on anatomical masks, or use guidance mechanisms that reinforce the same anatomical signal. However, B-mode US images are shaped by acquisition-dependent properties such as speckle texture, tissue contrast, and attenuation. Using a frozen US foundation model, we show that standard conditional diffusion baselines remain separated from real images in representation space. In this work, we propose Feature-Space Candidate Guidance (FSCG), a training-free sampling strategy to reduce this gap. At sampling time, FSCG applies local k-NN feature correction and selects the best of multiple stochastic candidates according to their feature-space energy. In this way, the mask defines the anatomy, while FSCG steers samples toward the real US domain. Across three different datasets, FSCG reduces average FID64 by 56\\%, FID192 by 57\\%, and nearest-neighbour feature distance by 47\\% over standard conditional diffusion sampling, outperforming alternative inference-time guidance baselines. The results suggest that domain-aware feature representations can reveal and reduce realism gaps in medical diffusion synthesis without retraining the generator. Our code is available at https://github.com/marinadominguez/FSCG.","short_abstract":"Conditional diffusion models can generate anatomically plausible medical ultrasound (US) images, but anatomical plausibility alone does not ensure realistic B-mode appearance. Most US pipelines adapt standard generative architectures and condition them on anatomical masks, or use guidance mechanisms that reinforce the...","url_abs":"https://arxiv.org/abs/2607.11655","url_pdf":"https://arxiv.org/pdf/2607.11655v1","authors":"[\"Marina Domínguez\",\"Nélida Mirabet-Herranz\",\"Valery Naranjo\"]","published":"2026-07-13T15:05:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":614201,"CreatedAt":"2026-07-14T02:54:43.516908796Z","UpdatedAt":"2026-07-14T02:54:43.516908796Z","DeletedAt":null,"paper_id":6537438,"paper_url":"https://arxiv.org/abs/2607.11655","paper_title":"Feature-Space Guided Diffusion for Realistic Ultrasound Image Synthesis","repo_url":"https://github.com/marinadominguez/FSCG","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}