Patch-based Automatic Rosacea Detection Using the ResNet Deep Learning Framework

2025-09-11

AI Summary

To address the challenge of balancing diagnostic accuracy and patient privacy preservation in early rosacea detection, this paper proposes a ResNet-18–based method utilizing localized facial image patches. Instead of relying on full-face images, the approach systematically extracts multi-scale, multi-location facial patches—such as nasal and malar regions—that correspond to clinically critical areas, enabling enhanced modeling of local visual features and improved sensitivity to pathological manifestations. Its key contributions are threefold: (i) replacing full-face inputs with localized patches significantly mitigates privacy leakage risks; (ii) improving model robustness and interpretability; and (iii) validating efficacy through multi-scale analysis and comparative experiments. Empirical results demonstrate that the proposed method achieves accuracy and sensitivity comparable to or superior to full-image baselines, while ensuring clinical applicability and deployment security.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Search and Optimization: Local Search

Application Category

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

Abstract

Rosacea, which is a chronic inflammatory skin condition that manifests with facial redness, papules, and visible blood vessels, often requirs precise and early detection for significantly improving treatment effectiveness. This paper presents new patch-based automatic rosacea detection strategies using the ResNet-18 deep learning framework. The contributions of the proposed strategies come from the following aspects. First, various image pateches are extracted from the facial images of people in different sizes, shapes, and locations. Second, a number of investigation studies are carried out to evaluate how the localized visual information influences the deep learing model performance. Third, thorough experiments are implemented to reveal that several patch-based automatic rosacea detection strategies achieve competitive or superior accuracy and sensitivity than the full-image based methods. And finally, the proposed patch-based strategies, which use only localized patches, inherently preserve patient privacy by excluding any identifiable facial features from the data. The experimental results indicate that the proposed patch-based strategies guide the deep learning model to focus on clinically relevant regions, enhance robustness and interpretability, and protect patient privacy. As a result, the proposed strategies offer practical insights for improving automated dermatological diagnostics.

Problem

• Automating rosacea detection using patch-based deep learning
• Evaluating localized visual information impact on model performance
• Enhancing accuracy while preserving patient privacy in diagnostics

Innovation

• ResNet-18 deep learning framework
• Localized image patches extraction
• Clinically relevant regions focus