{"ID":2899438,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.00377","arxiv_id":"2507.00377","title":"MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis","abstract":"Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solution by generating synthetic images, their effectiveness in medical imaging remains constrained due to their reliance on large-scale medical datasets and the need for higher image quality. To address these challenges, we present MedDiff-FT, a controllable medical image generation method that fine-tunes a diffusion foundation model to produce medical images with structural dependency and domain specificity in a data-efficient manner. During inference, a dynamic adaptive guiding mask enforces spatial constraints to ensure anatomically coherent synthesis, while a lightweight stochastic mask generator enhances diversity through hierarchical randomness injection. Additionally, an automated quality assessment protocol filters suboptimal outputs using feature-space metrics, followed by mask corrosion to refine fidelity. Evaluated on five medical segmentation datasets,MedDiff-FT's synthetic image-mask pairs improve SOTA method's segmentation performance by an average of 1% in Dice score. The framework effectively balances generation quality, diversity, and computational efficiency, offering a practical solution for medical data augmentation. The code is available at https://github.com/JianhaoXie1/MedDiff-FT.","short_abstract":"Recent advancements in deep learning for medical image segmentation are often limited by the scarcity of high-quality training data.While diffusion models provide a potential solution by generating synthetic images, their effectiveness in medical imaging remains constrained due to their reliance on large-scale medical...","url_abs":"https://arxiv.org/abs/2507.00377","url_pdf":"https://arxiv.org/pdf/2507.00377v1","authors":"[\"Jianhao Xie\",\"Ziang Zhang\",\"Zhenyu Weng\",\"Yuesheng Zhu\",\"Guibo Luo\"]","published":"2025-07-01T02:22:32Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":612477,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2899438,"paper_url":"https://arxiv.org/abs/2507.00377","paper_title":"MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis","repo_url":"https://github.com/JianhaoXie1/MedDiff-FT","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}