# When the Edit Changes the Patient: Measuring Identity Preservation in Counterfactual Retinal Images

arXiv: https://arxiv.org/abs/2608.23024 · HTML: https://mlsanity.com/paper/2608.23024/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 36 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 28 of 28)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [DiffEdit: Diffusion-based semantic image editing with mask guidance](https://mlsanity.com/paper/2210.11427/) (2022)
- [Diffusion Visual Counterfactual Explanations](https://mlsanity.com/paper/2210.11841/) (2022)
- [Diffusion Models for Counterfactual Explanations](https://mlsanity.com/paper/2203.15636/) (2022)
- [SADM: Sequence-Aware Diffusion Model for Longitudinal Medical Image Generation](https://mlsanity.com/paper/2212.08228/) (2022)
- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)
- [Learning to synthesise the ageing brain without longitudinal data](https://mlsanity.com/paper/1912.02620/) (2019)
- [Deep Learning-based Patient Re-identification Is able to Exploit the Biometric Nature of Medical Chest X-ray Data](https://mlsanity.com/paper/2103.08562/) (2021)
- [Measuring axiomatic soundness of counterfactual image models](https://mlsanity.com/paper/2303.01274/) (2023)
- [Sparse Visual Counterfactual Explanations in Image Space](https://mlsanity.com/paper/2205.07972/) (2022)
- [Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images](https://mlsanity.com/paper/2308.02062/) (2023)
- [CounteRGAN: Generating Realistic Counterfactuals with Residual Generative Adversarial Nets](https://mlsanity.com/paper/2009.05199/) (2020)
- [BiomedJourney: Counterfactual Biomedical Image Generation by Instruction-Learning from Multimodal Patient Journeys](https://mlsanity.com/paper/2310.10765/) (2023)
- [RadEdit: stress-testing biomedical vision models via diffusion image editing](https://mlsanity.com/paper/2312.12865/) (2023)
- [Benchmarking Counterfactual Image Generation](https://mlsanity.com/paper/2403.20287/) (2024)
- [BioLORD: Learning Ontological Representations from Definitions (for Biomedical Concepts and their Textual Descriptions)](https://mlsanity.com/paper/2210.11892/) (2022)
- [PRISM: High-Resolution & Precise Counterfactual Medical Image Generation using Language-guided Stable Diffusion](https://mlsanity.com/paper/2503.00196/) (2025)
- [Latent Drifting in Diffusion Models for Counterfactual Medical Image Synthesis](https://mlsanity.com/paper/2412.20651/) (2024)
- [Mitigating attribute amplification in counterfactual image generation](https://mlsanity.com/paper/2403.09422/) (2024)
- [A Generalist Model for Diverse Text-Guided Medical Image Synthesis](https://mlsanity.com/paper/2405.09806/) (2024)
- [Specialized curricula for training vision-language models in retinal image analysis](https://mlsanity.com/paper/2407.08410/) (2024)
- [IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age Transformation](https://mlsanity.com/paper/2410.16945/) (2024)

## Built on by (most cited first, 1 of 1)

- [What Makes a Good Medical Image Tokenizer? Rethinking Reconstruction and Generation in Medical Image Tokenization](https://mlsanity.com/paper/2609.24691/) (2026)

## Abstract (arXiv)

Counterfactual medical image generation aims to modify an existing image to reflect a hypothetical scenario in which certain characteristics of the imaged subject are altered, while keeping their identity fixed. Most existing works repurpose established image editing methods, which do not directly supervise identity preservation. Instead, they assume that identity is implicitly preserved by anchoring generation to the source image. This assumption is rarely tested and may fail in domains where biometric cues are subtle, such as retinal optical coherence tomography (OCT). In this work, we explicitly measure identity preservation for three groups of text-conditioned editing methods - source-anchored, structured-prompt, and paired-training - using referee classifiers, embedding alignment scores, and a blind reader study. We find that all methods produce high-quality OCT images with comparable editing success, yet their identity preservation differs markedly. Source-anchored editing frequently alters the depicted subject, while paired-training preserves it best. We argue that future work on medical counterfactual generation must explicitly measure and report identity preservation alongside image realism and editing success.