An improved segementation approach for skin lesion classification

Abstract

Skin cancer is one of the most common types of cancer, its incidence reached epidemic proportions and caused many deaths. Skin cancer can be categorize into three main types; Actinic Keratoses, Basal cell carcinoma and Melanoma. The melanoma skin cancer is the most aggressive and the deadliest form of skin cancer compared to the others. Early Melanoma detection and diagnosis often allows for more treatment option and decreases significantly the number of deaths. Many researchers proposed to use image processing for skin lesion detection. The process can be divided into three main stages: lesion identification based on image segmentation, features extraction and lesion classification. Segmentation and features extraction are the key-steps and significantly influence the outcome of the classification results. In this paper, a new approach for automatic segmentation and classification for skin lesion has been proposed. The proposed approach consists on a preprocessing based on multiscale decomposition that’s separate the input image into two components. The geometrical component will be used in the segmentation stage and the texture component in features extraction. The classification performed using the Support Vector Machine (SVM) classifier. The efficiency and the performance of the proposed approach has been evaluated in comparison with recent and robust dermoscopic approaches from literature.