<![CDATA[Skin cancer is a prevalent and potentially life-threatening condition that requires accurate and timely diagnosis. This study explores the application of Convolutional Neural Networks (CNNs) for the detection and classification of skin cancer types, including mole, dermatofibroma, melanoma, and nevus, based on visual characteristics extracted from digital images. The research focuses on preserving color information in original images during preprocessing to enhance the model's ability to differentiate between these conditions. A dataset comprising a variety of skin condition images was utilized to train and evaluate the CNN model, which was designed with convolutional and dense layers for effective feature extraction and classification. The model achieved a test accuracy of 63.83%, indicating its potential as a tool for supporting dermatological diagnosis. This work contributes to advancing machine learning applications in dermatology, aiming to improve diagnostic accuracy and patient care outcomes in the detection of skin cancer.]]>
Copyrights © 2025
