MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Jianhao, Zhang, Ziang, Weng, Zhenyu, Zhu, Yuesheng, Luo, Guibo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918076800303104
author Xie, Jianhao
Zhang, Ziang
Weng, Zhenyu
Zhu, Yuesheng
Luo, Guibo
author_facet Xie, Jianhao
Zhang, Ziang
Weng, Zhenyu
Zhu, Yuesheng
Luo, Guibo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_00377
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
Xie, Jianhao
Zhang, Ziang
Weng, Zhenyu
Zhu, Yuesheng
Luo, Guibo
Computer Vision and Pattern Recognition
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.
title MedDiff-FT: Data-Efficient Diffusion Model Fine-tuning with Structural Guidance for Controllable Medical Image Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.00377