A Metaheuristic based Clustering Approach for Breast Cancer Identification for Earlier Diagnosis

Breast cancer is the most common type of cancer among women and is an imminent danger to their life. China now has the highest global mortality rate for breast cancer, and this rate is rising. Research teams and organizations are working round-the-clock to create the optimal diagnostic procedure and course of action because of the significant harm that breast cancer does to the well-being and health of an individual. Because of developments in computer technology and learning algorithms, artificially intelligent algorithms have been given the ability to replace human behavior and judgement in some fields. In order to identify breast cancer using the conventional way, medical personnel must constantly evaluate patient data. In this case, the algorithm is used to quickly deliver clinicians an incredibly plausible reference outcome, which is very important to increase the accuracy of the diagnosis and minimize the burden on medical professionals. In order to improve the precision of cancer recognition, this research establishes and puts into practice a method based on the particle swarm optimization (PSO) algorithm to continuously change the most important variables of the spatially constrained adaptively regularized kernel based fuzzy c means (ScARKFCM) clustering. The outcomes of the developed PSO-ScARKFCM algorithm were validated using the MIAS dataset. The findings assist doctors in obtaining a quicker diagnosis of the condition by detecting and extracting the tumor from the unprocessed medical images.