# Privacy-Preserving Automated Rosacea Detection Based on Medically Inspired Region of Interest Selection

arXiv: https://arxiv.org/abs/2509.09844 · HTML: https://mlsanity.com/paper/2509.09844/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 11 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Study of Face Obfuscation in ImageNet](https://mlsanity.com/paper/2103.06191/) (2021)
- [Zoom-in-Net: Deep Mining Lesions for Diabetic Retinopathy Detection](https://mlsanity.com/paper/1706.04372/) (2017)
- [Increasing Rosacea Awareness Among Population Using Deep Learning and Statistical Approaches](https://mlsanity.com/paper/2411.07074/) (2024)
- [Interpretable Automatic Rosacea Detection with Whitened Cosine Similarity](https://mlsanity.com/paper/2504.08073/) (2025)

## Abstract (arXiv)

Rosacea is a common but underdiagnosed inflammatory skin condition that primarily affects the central face and presents with subtle redness, pustules, and visible blood vessels. Automated detection remains challenging due to the diffuse nature of symptoms, the scarcity of labeled datasets, and privacy concerns associated with using identifiable facial images. A novel privacy-preserving automated rosacea detection method inspired by clinical priors and trained entirely on synthetic data is presented in this paper. Specifically, the proposed method, which leverages the observation that rosacea manifests predominantly through central facial erythema, first constructs a fixed redness-informed mask by selecting regions with consistently high red channel intensity across facial images. The mask thus is able to focus on diagnostically relevant areas such as the cheeks, nose, and forehead and exclude identity-revealing features. Second, the ResNet-18 deep learning method, which is trained on the masked synthetic images, achieves superior performance over the full-face baselines with notable gains in terms of accuracy, recall and F1 score when evaluated using the real-world test data. The experimental results demonstrate that the synthetic data and clinical priors can jointly enable accurate and ethical dermatological AI systems, especially for privacy sensitive applications in telemedicine and large-scale screening.