Leveraging Deep Learning for Accurate Classification of Skin Disease Images
Year: 2025
Type: article
Abstract: This paper leverages deep learning techniques to address the complex task of classifying ten distinct types of skin diseases. A comprehensive dataset comprising 27,200 images was utilized to train and evaluate a convolutional neural network (CNN) model based on the ResNet50 architecture. To ensure a rigorous assessment, the dataset was split into training (80%), validation (10%), and testing (10%) subsets. The ResNet50-based CNN was trained extensively and achieved a classification accuracy of 92% on the test set, demonstrating strong predictive performance. These results highlight the potential of deep learning to support healthcare professionals by enabling automated and accurate skin disease classification. This paper contributes to the growing field of intelligent diagnostic systems aimed at improving early detection and treatment planning in dermatology.
Authors: HAZEM NOORI, Ahmed, Aya, Goh
Language: English
Subfield: Oncology
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W4409595688