Diagnosis of Malignant Melanoma of Skin Cancer Types

TitleDiagnosis of Malignant Melanoma of Skin Cancer Types
Publication TypeJournal Article
Year of Publication2017
AuthorsAlasadi, A. H. H., and B. M. Alsafy
JournalInternational Journal of Interactive Multimedia and Artificial Intelligence
IssueSpecial Issue on 3D Medicine and Artificial Intelligence
Date Published09/2017

Malignant melanoma is a kind of skin cancer that begins in melanocytes. It can influence on the skin only, or it may expand to the bones and organs. It is less common, but more serious and aggressive than other types of skin cancer. Malignant Melanoma can happen anywhere on the skin, but it is widespread in certain locations such as the legs in women, the back and chest in men, the face, the neck, mouth, eyes, and genitals. In this paper, a proposed algorithm is designed for diagnosing malignant melanoma types by using digital image processing techniques. The algorithm consists of four steps: preprocessing, separation, features extraction, and diagnosis. A neural network (NN) used to diagnosis malignant melanoma types. The total accuracy of the neural network was 100% for training and 93% for testing. The evaluation of the algorithm is done by using sensitivity, specificity, and accuracy. The sensitivity of NN in diagnosing malignant melanoma types was 95.6%, while the specificity was 92.2% and the accuracy was 93.9%. The experimental results are acceptable.

KeywordsCancer, Diagnosis, Feature Extraction, Medicine, Melanoma, Segmentation
ijimai20174_5_8.pdf1005.8 KB