Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis
This work addresses the need for finer spatial control in counterfactual image generation for applications like disease modeling, representing an incremental improvement over existing methods.
The paper tackled the problem of generating spatially localized counterfactual images without user-defined masks, proposing a method that subdivides structures into regional segments for independent measurements, resulting in realistic, region-specific modifications in coronary CT angiography experiments.
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.