Skin Cancer Detection using Neutrosophic c-means and Fuzzy c-means Clustering Algorithms

Ahmed Abdelhafeez^*1, Hoda K Mohamed ²

¹ Faculty of Information Systems and Computer Science, October 6th University, Cairo, 12585, Egypt;

² Faculty of Engineering, Ain shams University, Cairo, 11566, Egypt;

Emails: aahafeez.scis@o6u.edu.eg; Hoda.korashy@eng.asu.edu.eg

Abstract

Melanoma is the kind of skin cancer that poses the greatest risk to one's life and has the maximum mortality rate within the group of skin cancer disorders. Even so, the automated placement and classification of skin lesions at initial phases remains a complicated task due to the lack of contrast melanoma molarity and skin fraction and a greater level of color similarity among melanoma-affected and -nonaffected areas. Contemporary technological improvements and research methods enabled it to recognize and distinguish this type of skin cancer more successfully. A clustering technique called neutrosophic c-means clustering (NCMC) is presented in this research to group ambiguous data in the detection of skin cancer. This algorithm takes its cues from both fuzzy c-means and the neutrosophic set structure. To arrive at such a structure, an appropriate objective function must first be created and then minimized. The clustering issue must then be stated as a restricted minimization problem, the solution of which is determined by the objective function. This paper made a comparison between NCMC and fuzzy c-means clustering (FCMC). The results show that the NCMC is more suitable than the FCMC.

Keywords: Skin cancer; Neutrosophic set; Clustering; Neutrosophic c-means clustering; Fuzzy c-means clustering