Open Access Open Access  Restricted Access Subscription Access

Skin-Sense: A Deep Learning-Based Multi-Class Skin Disease Detection System

Akshada Ganesh Jadhav, Avdhoot Vijay Kode, Sakshi Mahesh Gore, Narendra Nandu Ghuge, S.D. Aher

Abstract


Skin diseases have become increasingly common due to environmental changes, lifestyle factors, and limited availability of dermatological services. Early identification of skin disorders is essential to prevent complications and to support timely treatment. This paper presents the implementation of an artificial intelligence-based skin disease detection and management system that analyzes skin images to assist users in identifying possible skin conditions. The system enables users to upload or capture images of affected skin areas and optionally provide visible symptom information to improve prediction reliability. A deep learning–based image classification model is employed to process the input images and generate predicted disease results along with confidence scores. In addition to disease detection, the platform provides preventive guidance, basic care recommendations, automated report generation, and healthcare support features such as chatbot assistance and doctor appointment facilitation. The implemented system aims to improve accessibility to preliminary dermatological assessment, reduce dependence on immediate physical consultations, and promote early awareness and management of skin-related health issues

Full Text:

PDF

References


M. Narendra, “A multimodal approach utilizing Telegram chatbot for text and image analysis in skin disease classification,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3516884.

A. Balasundaram, “Genetic algorithm optimized stacking approach to skin disease detection,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3412791.

L. Riaz, “A comprehensive joint learning system to detect skin cancer,” IEEE Access, 2023, doi: 10.1109/ACCESS.2023.3297644.

Q. Liu, “Enhancing skin disease classification through feature fusion and spatial–channel attention mechanisms,” IEEE Access, 2025, doi: 10.1109/ACCESS.2025.3577740.

S. Mahbod, M. Schaefer, and A. Ecker, “Fusing fine-tuned deep features for skin lesion classification,” Computerized Medical Imaging and Graphics, vol. 101, pp. 1–11, 2022, doi: 10.1016/j.compmedimag.2022.102051.

M. Tschandl, C. Rinner, P. Apalla, et al., “Human–computer collaboration for skin cancer recognition,” Nature Medicine, vol. 26, pp. 1229–1234, 2022, doi: 10.1038/s41591-022-01845-8.

J. Khan, P. Singh, and S. Kumar, “Deep learning-based skin disease detection using convolutional neural networks,” IEEE Transactions on Instrumentation and Measurement, vol. 72, 2023, doi: 10.1109/TIM.2023.3278146.

N. Sharma and R. Tripathi, “A hybrid CNN–SVM approach for early skin disease diagnosis,” IEEE Access, vol. 12, pp. 22147–22156, 2024, doi: 10.1109/ACCESS.2024.3409123


Refbacks

  • There are currently no refbacks.