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

2025-09-11

AI Summary

Rosacea diagnosis faces challenges due to diffuse symptom presentation, scarcity of annotated clinical data, and privacy risks associated with using real facial images. Method: We propose a medically inspired, privacy-preserving detection framework. Leveraging clinical priors, we design a fixed erythema mask that explicitly focuses on diagnostically relevant regions (e.g., mid-facial erythematous zones) while excluding identity-discriminative facial features. A ResNet-18 backbone is trained end-to-end exclusively on synthetic facial images, eliminating reliance on real human faces. Contribution/Results: To our knowledge, this is the first work to encode clinical erythema distribution priors into a lightweight, interpretable region-of-interest (ROI) masking mechanism. The synthetic-data-driven approach achieves high generalization across real-world scenarios. In empirical evaluation, our method significantly outperforms full-face baseline models in accuracy, recall, and F1-score—demonstrating the efficacy of medical prior guidance and privacy-by-design principles.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

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.

Problem

• Automated detection of rosacea using facial images
• Addressing privacy concerns with synthetic data training
• Focusing on diagnostically relevant facial regions

Innovation

• Redness-informed mask for privacy
• ResNet-18 trained on synthetic data
• Focuses on cheeks nose forehead