Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 38 references that are in the map. First posted on arXiv 29 Sep 2025.
Builds on
27 of 38 references.
References · 27
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2022Generative Adversarial Networkscited by 5,603
- 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
- 2019PadChest: A large chest x-ray image dataset with multi-label annotated reportscited by 308
- 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
- 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
- 2021TorchXRayVision: A library of chest X-ray datasets and modelscited by 131
- 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
- 2022Deep End-to-end Causal Inferencecited by 93
- 2022Diffusion Models for Causal Discovery via Topological Orderingcited by 64
15 more
- 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 54
- 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
- 2024Enhancing Spatiotemporal Disease Progression Models via Latent Diffusion and Prior Knowledgecited by 35
- 2023Measuring axiomatic soundness of counterfactual image modelscited by 34
- 2023RadEdit: stress-testing biomedical vision models via diffusion image editingcited by 28
- 2024Counterfactual Image Editingcited by 20
- 2024Diffusion-based Iterative Counterfactual Explanations for Fetal Ultrasound Image Quality Assessmentcited by 13
- 2023Debiasing Counterfactuals In the Presence of Spurious Correlationscited by 12
- 2024Mitigating attribute amplification in counterfactual image generationcited by 12
- 2024Robust image representations with counterfactual contrastive learningcited by 12
- 2024Counterfactual contrastive learning: robust representations via causal image synthesiscited by 11
- 2017Implicit Causal Models for Genome-wide Association Studiescited by 10
- 2024MedEdit: Counterfactual Diffusion-based Image Editing on Brain MRIcited by 8
- 2022Optimising Chest X-Rays for Image Analysis by Identifying and Removing Confounding Factorscited by 6
- 2024Semi-Supervised Learning for Deep Causal Generative Modelscited by 6
Built on by
Citing papers per year: 2026: 2.
2 papers.