DEEP CNN MODEL FOR MULTI-CLASS CLASSIFICATION OF SKIN CANCER FROM DERMOSCOPIC IMAGES

Abstract

Skin cancer, one of the most common and potentially fatal cancers, necessitates early and accurate diagnosis. Traditional diagnostic methods, although effective, are often slow, costly, and prone to human error. This project leverages advanced machine learning techniques to address these issues.Specifically, it uses the InceptionResNetV2 model for feature extraction and the Extra Trees Classifier(ETC) for multi-class classification of skin cancer, aiming to create an automated and efficient diagnostic tool for dermatologists. Traditional diagnosis of skin cancer involves a dermatologist's visual examination, followed by a biopsy and histopathological analysis