用分割模型引导生成局部一致的图像反事实，提升医学影像干预效果
Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
- 基于分割模型自动引导，无需人工标注分割图
- 在胸片上实现结构化干预，保持局部一致性且无全局畸变
- 适合医学影像数据增强与疾病建模，尤其适用于病灶区域编辑
反事实图像生成可有效用于数据增强、去偏及疾病建模。现有方法依赖外部分类器或回归器进行个体层面干预（如改变患者年龄），但对于结构特定干预（如改变胸部X光中左肺区域大小），此类方法不足，易引发图像全域的不良影响。以往工作使用像素级标签图作为指导，需用户手动提供假设性分割，耗时且困难。本文提出分割器引导的反事实微调（Seg-CFT），在仅操作结构化标量变量的前提下，生成局部一致且有效的反事实图像。实验验证了其在生成真实胸片方面的性能，并在冠状动脉疾病建模任务中展现良好前景。代码已开源：https://github.com/biomedia-mira/seg-cft。
原文摘要 · Abstract (English)
Counterfactual image generation is a powerful tool for augmenting training data, de-biasing datasets, and modeling disease. Current approaches rely on external classifiers or regressors to increase the effectiveness of subject-level interventions (e.g., changing the patient's age). For structure-specific interventions (e.g., changing the area of the left lung in a chest radiograph), we show that this is insufficient, and can result in undesirable global effects across the image domain. Previous work used pixel-level label maps as guidance, requiring a user to provide hypothetical segmentations which are tedious and difficult to obtain. We propose Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT), which preserves the simplicity of intervening on scalar-valued, structure-specific variables while producing locally coherent and effective counterfactuals. We demonstrate the capability of generating realistic chest radiographs, and we show promising results for modeling coronary artery disease. Code: https://github.com/biomedia-mira/seg-cft.
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。