基于位置分割器的反事实微调用于空间局部化图像合成
Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis
AI总结：
本文提出Positional Seg-CFT，通过将每个结构细分为区域并独立测量每个区域，实现空间局部化的反事实生成，提升冠状动脉CT血管造影中疾病建模的精细空间控制。
摘要：
反事实图像生成能够实现受控的数据增强、偏见缓解和疾病建模。然而，现有方法受限于主体级因素（如年龄）且无法生成局部结构变化，常导致全局伪影。像素级指导使用分割掩膜已被探索，但需要用户定义的反事实掩膜，操作繁琐且不实用。Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT) 通过分割衍生的测量来监督结构特定变量，但受限于全局干预。本文提出Positional Seg-CFT，将每个结构细分为区域并为每个区域推导独立测量，实现空间局部化且解剖学一致的反事实生成。在冠状动脉CT血管造影实验中，Pos-Seg-CFT生成真实、区域特定的修改，为疾病进展建模提供更精细的空间控制。
英文摘要：
Counterfactual image generation enables controlled data augmentation, bias mitigation, and disease modeling. However, existing methods guided by external classifiers or regressors are limited to subject-level factors (e.g., age) and fail to produce localized structural changes, often resulting in global artifacts. Pixel-level guidance using segmentation masks has been explored, but requires user-defined counterfactual masks, which are tedious and impractical. Segmentor-guided Counterfactual Fine-Tuning (Seg-CFT) addressed this by using segmentation-derived measurements to supervise structure-specific variables, yet it remains restricted to global interventions. We propose Positional Seg-CFT, which subdivides each structure into regional segments and derives independent measurements per region, enabling spatially localized and anatomically coherent counterfactuals. Experiments on coronary CT angiography show that Pos-Seg-CFT generates realistic, region-specific modifications, providing finer spatial control for modeling disease progression.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
