Classification of Melanoma and Nevus in Digital Images for Diagnosis of Skin Cancer

• Published in: IEEE access Vol. 7; pp. 90132 - 90144
• Main Authors: Khan, Muhammad Qasim, Hussain, Ayyaz, Rehman, Saeed Ur, Khan, Umair, Maqsood, Muazzam, Mehmood, Kashif, Khan, Muazzam A.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Cancer; centroid selection; Clustering; Digital imaging; feature; Feature extraction; Image acquisition; Image classification; Image color analysis; Image processing; Image segmentation; K-means clustering; Lesions; Medical imaging; Melanoma; nevus; Signs and symptoms; Skin; Skin cancer; Support vector machines; Young adults
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2926837

Melanoma is considered a fatal type of skin cancer. However, it is sometimes hard to distinguish it from nevus due to their identical visual appearance and symptoms. The mortality rate because of this disease is higher than all other skin-related consolidated malignancies. The number of cases is growing among young people, but if it is diagnosed at an earlier stage, then the survival rates become very high. The cost and time required for the doctors to diagnose all patients for melanoma are very high. In this paper, we propose an intelligent system to detect and distinguish melanoma from nevus by using the state-of-the-art image processing techniques. At first, the Gaussian filter is used for removing noise from the skin lesion of the acquired images followed by the use of improved K-mean clustering to segment out the lesion. A distinctive hybrid superfeature vector is formed by the extraction of textural and color features from the lesion. Support vector machine (SVM) is utilized for the classification of skin cancer into melanoma and nevus. Our aim is to test the effectiveness of the proposed segmentation technique, extract the most suitable features, and compare the classification results with the other techniques present in the literature. The proposed methodology is tested on the DERMIS dataset having a total number of 397 skin cancer images: 146 are melanoma and 251 are nevus skin lesions. Our proposed methodology archives encouraging results having 96% accuracy.