ScabAI: A Deep Learning-Based Mobile Application for Scabies Detection from Skin Images

Authors : Hakan Yılmaz, Zeynep Nida Can, Hatice Şevval Baki, Tahsin Çökmez, Mehmet Özdem

Pages : 1371-1383

Doi:10.29109/gujsc.1601385

View : 144 | Download : 400

Publication Date : 2025-12-31

Article Type : Research Paper

Abstract :Scabies, a contagious skin disease caused by the Sarcoptes scabiei mite, remains a significant public health concern globally. This study aims to develop a mobile application, ScabAI, which uses a deep learning model based on Convolutional Neural Networks (CNNs) to detect scabies from skin images. The model was trained using a dataset of 500 images, divided equally between scabies and non-scabies cases, and achieved high performance metrics, including 96.7% accuracy, 96% sensitivity, 97.3% specificity, and a 96.5% F1 score. These results demonstrate the model’s reliability and effectiveness in detecting scabies, outperforming many existing models. The mobile application allows users to capture or upload images of suspected scabies lesions, providing rapid and accurate preliminary diagnoses. ScabAI offers a practical, user-friendly tool that can be beneficial for both healthcare providers and individuals, supporting early detection, timely treatment, and reducing the risk of disease transmission. This study underscores the potential of integrating artificial intelligence with mobile platforms for improved dermatological care, particularly in resource-limited settings. Future research should focus on expanding the dataset to enhance generalization and exploring additional AI techniques to refine detection accuracy. ScabAI not only contributes to AI-assisted dermatology but also serves as a scalable model for developing similar tools targeting other skin conditions. This innovative approach addresses both clinical needs and user accessibility, advancing healthcare outcomes and public health initiatives.
Keywords : Uyuz, derin öğrenme, CNN, mobil arayüz, erken tanı

ORIGINAL ARTICLE URL