# Anonymizing medical case-based explanations through disentanglement

arXiv: https://arxiv.org/abs/2311.04833 · HTML: https://mlsanity.com/paper/2311.04833/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Diffusion Models for Medical Image Analysis: A Comprehensive Survey](https://mlsanity.com/paper/2211.07804/) (2022)
- [A Survey on Homomorphic Encryption Schemes: Theory and Implementation](https://mlsanity.com/paper/1704.03578/) (2017)
- [Unsupervised Learning of Disentangled Representations from Video](https://mlsanity.com/paper/1705.10915/) (2017)
- [DeepPrivacy: A Generative Adversarial Network for Face Anonymization](https://mlsanity.com/paper/1909.04538/) (2019)
- [CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks](https://mlsanity.com/paper/2005.09544/) (2020)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [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)
- [IdentityDP: Differential Private Identification Protection for Face Images](https://mlsanity.com/paper/2103.01745/) (2021)
- [Assessment of iris recognition reliability for eyes affected by ocular pathologies](https://mlsanity.com/paper/1809.00206/) (2018)
- [VGAN-Based Image Representation Learning for Privacy-Preserving Facial Expression Recognition](https://mlsanity.com/paper/1803.07100/) (2018)
- [Privacy-Net: An Adversarial Approach for Identity-Obfuscated Segmentation of Medical Images](https://mlsanity.com/paper/1909.04087/) (2019)
- [Learning Invariant Feature Representation to Improve Generalization across Chest X-ray Datasets](https://mlsanity.com/paper/2008.04152/) (2020)
- [Siamese Generative Adversarial Privatizer for Biometric Data](https://mlsanity.com/paper/1804.08757/) (2018)
- [Deep Learning-based Anonymization of Chest Radiographs: A Utility-preserving Measure for Patient Privacy](https://mlsanity.com/paper/2209.11531/) (2022)
- [Implications of Ocular Pathologies for Iris Recognition Reliability](https://mlsanity.com/paper/1809.00168/) (2018)
- [Towards Privacy-preserving Explanations in Medical Image Analysis](https://mlsanity.com/paper/2107.09652/) (2021)

## Built on by (most cited first, 5 of 5)

- [Causal Disentanglement for Robust Long-tail Medical Image Generation](https://mlsanity.com/paper/2504.14450/) (2025)
- [SafeTriage: Facial Video De-identification for Privacy-Preserving Stroke Triage](https://mlsanity.com/paper/2506.16578/) (2025)
- [Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: A Scoping Review](https://mlsanity.com/paper/2505.02828/) (2025)
- [Towards integration of Privacy Enhancing Technologies in Explainable Artificial Intelligence](https://mlsanity.com/paper/2507.04528/) (2025)
- [Disentanglement and Assessment of Shortcuts in Ophthalmological Retinal Imaging Exams](https://mlsanity.com/paper/2507.09640/) (2025)

## Abstract (arXiv)

Case-based explanations are an intuitive method to gain insight into the decision-making process of deep learning models in clinical contexts. However, medical images cannot be shared as explanations due to privacy concerns. To address this problem, we propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved, obtaining independent feature vectors that encode the images' identity and medical characteristics. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image's identity and achieve anonymization. The models are applied to medical and biometric datasets, demonstrating their capacity to generate realistic-looking anonymized images that preserve their original medical content. Additionally, the experiments show the network's inherent capacity to generate counterfactual images through the replacement of medical features.