Artifact removal and lesion segmentation for melanoma detection in skin lesion images

• Main Authors: Salido, Julie Ann A., Ruiz, Conrado, Marcos, Nelson
• Format: text
• Published: Animo Repository 2018
• Subjects: Hair—Removal > Automation; Skin tests > Automation; Melanoma—Diagnosis; Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/1870
• Institution: De La Salle University

Melanoma is a severe form of skin cancer characterized by the rapid multiplication of pigment-producing cells. There are new techniques for automated analysis of skin lesions for classification of melanoma using images from digital cameras and smart phones. A problem on analysis of these images are interesting because of the existence of artifacts and noise such as hair, veins, water residue, illuminations and light reflections. An important step in the diagnosis of melanoma is the removal of artifacts and reduction of noise that can inhibit the examination to accurately segment the skin lesion from the surrounding skin area. In this paper, a new method for extraction of skin lesion is implemented based on image enhancement and morphological operators. The experimental results show that artifact removal and lesion segmentation in skin lesion images can perform a true detection rate of 95.37% for melanoma skin lesion segmentation. © 2018.