A Novel Hybrid K-Means and GMM Machine Learning Model for Breast Cancer Detection
P. Esther Jebarani, N. Umadevi, Hien Dang, Marc Pomplun
Abstract
Breast cancer is the second leading cause of death among a large number of women worldwide. It may be challenging for radiologists to diagnose and treat breast cancer. Consequently, primary care improves disease prevention and death. Early detection increases treatment options and saves life, which is the major target of this research. This research indicates the versatility of the methodology by integrating contemporary segmentation approaches with machine learning methods, which are developing areas of research. In the pre-processing process, an adaptive median filter is utilized for noise removal, enhancement of image quality, conservation of edges, and smoothing. This research makes a significant contribution by proposing a new parameter for evaluating K-means and a Gaussian mixture model (GMM) performance. A hybrid combination of segmentation and detection was applied to breast cancer. The proposed technique is significant for classifying benign and malignant tumors. The simulated results are discussed and evaluated to determine the competence of this method for the early diagnosis of breast cancer. This method allows medical experts to recognize breast cancer at a faster rate and provide higher accuracy. An ANOVA test was used to determine the multi-variant analysis and prediction rate for the proposed method.