A Comprehensive Approach to Classify the Skin Cancer Disease Using Latest CNN Model (YOLOv8)

Skin cancer is a pressing global health issue, necessitating accurate and timely diagnosis for effective treatment. This document introduces a comprehensive and innovative paradigm for skin cancer classification using state-of-the-art object detection and classification model YOLOv8. The YOLOv8 image classification model is designed to detect 1000 pre-defined classes in images in real-time. The methodology encompasses data collection, preprocessing, and balancing to mitigate class imbalance. The model is trained on a diverse dataset comprising various skin lesion types, including actinic keratoses and intraepithelial carcinoma, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevi and vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhage). Leveraging transfer learning and fine-tuning techniques, the CNN model achieves tremendous performance metrics, including accuracy, sensitivity and specificity. By applying the power of deep learning, our model insights are fine-tuned with a wide dataset (10,000), ensuring exceptional accuracy in disease classification.