A Newly Hybrid Version of African Vultures Optimization Algorithm and Sine Cosine Algorithm for Mammographic Masses and its Diagnosis

Abstract

From the last few periods, breast cancer is the foremost reason for cancer-related huge death rates in the midst of females. However, the recent study detection and diagnosis of these types of issues can successfully decrease the death rate. Masses are unique indicators of undetectable breast cancer noticeable in mammograms whose identification and judgment is a more complex or stimulating job due to its restrained natural surroundings. The seriousness of this issue is to motivate the scientists of different areas for their solution. With the great inspiration of this learning, in this work we are tried to present a new hybrid algorithm with the integration powerful features of two different algorithms such as African Vultures Optimization Algorithm (AVOA) and Sine Cosine Optimization Algorithm (SCA) and it is called AVSC method for identify the breast cancer. The features of the sine cosine algorithm helps to improve the exploitation and exploration phases of the basic AVOA method. This enhancement has been designed to improve the premature convergence, avoiding the local optima and fast convergence speed and many more. To verify the performance of the proposed scheme have been verified 29-CEC ’2017 test functions. Moreover, the AVSC method has been successfully applied on the two different mini-MIAS and DDSM databases including 68 and 500 mammograms, etc and attained a highest rate of sensitivity and false positives per image for the respective datasets. Hence, the tabulated results give the strong evidence that the AVSC is able to effectively resolve the highly complex tasks that others whole could be more helpful in biomedical sciences.