Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.21213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910062884159488 |
|---|---|
| author | Xia, Tian Sinclair, Matthew Schuh, Andreas Ribeiro, Fabio De Sousa Mehta, Raghav Rasal, Rajat Puyol-Antón, Esther Gerber, Samuel Petersen, Kersten Schaap, Michiel Glocker, Ben |
| author_facet | Xia, Tian Sinclair, Matthew Schuh, Andreas Ribeiro, Fabio De Sousa Mehta, Raghav Rasal, Rajat Puyol-Antón, Esther Gerber, Samuel Petersen, Kersten Schaap, Michiel Glocker, Ben |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21213 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis Xia, Tian Sinclair, Matthew Schuh, Andreas Ribeiro, Fabio De Sousa Mehta, Raghav Rasal, Rajat Puyol-Antón, Esther Gerber, Samuel Petersen, Kersten Schaap, Michiel Glocker, Ben Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Positional Segmentor-Guided Counterfactual Fine-Tuning for Spatially Localized Image Synthesis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2603.21213 |