用少量参考图对医学图像生成进行分布对齐，提升分割模型性能
Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation
- 通过可微奖励微调实现生成图像与目标分布对齐
- 在少样本下仍保持性能，mDice提升3.5-4.0%，mIoU提升3.5-5.6%
- 结合流匹配生成多样化掩码，适合医疗图像数据稀缺场景
数据异质性阻碍了医学图像分析模型的临床应用，生成式数据增强有助于缓解此问题。然而，现有基于扩散的方法在合成图像-掩码对时往往忽略不同场景间生成图像与真实图像的分布偏移，这种不匹配会显著降低下游性能。为此，我们提出AlignFlow，一种通过可微奖励微调对齐目标参考图像分布的流匹配模型，在仅提供少量参考图像时仍有效。具体地，将流匹配训练分为两阶段：第一阶段拟合训练数据生成合理图像；第二阶段引入分布对齐机制，利用可微奖励引导生成图像趋向目标域样本分布。此外，为增强掩码多样性，还设计基于流匹配的掩码生成方法，补充感兴趣区域的多样性。大量实验表明，该方法在多种数据集和场景下均有效，mDice提升3.5-4.0%，mIoU提升3.5-5.6%。
原文摘要 · Abstract (English)
Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution shifts between generated and real images across scenarios, and such mismatches can markedly degrade downstream performance. To address this issue, we propose AlignFlow, a flow matching model that aligns with the target reference image distribution via differentiable reward fine-tuning, and remains effective even when only a small number of reference images are provided. Specifically, we divide the training of the flow matching model into two stages: in the first stage, the model fits the training data to generate plausible images; Then, we introduce a distribution alignment mechanism and employ differentiable reward to steer the generated images toward the distribution of the given samples from the target domain. In addition, to enhance the diversity of generated masks, we also design a flow matching based mask generation to complement the diversity in regions of interest. Extensive experiments demonstrate the effectiveness of our approach, i.e., performance improvement by 3.5-4.0% in mDice and 3.5-5.6% in mIoU across a variety of datasets and scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。