MAMMOGRAM ANALYSIS BASED ON MACHINE LEARNING ALGORITHMS: A COMPARATIVE STUDY

Breast cancer is one of the leading causes of death in women. Several experiments have been performed to identify and track breast cancer using different imaging and classification techniques. However, the illness is one of the deadliest illnesses. Because the cause of breast cancer is unknown, diagnosis is difficult. Thus, early diagnosis of breast cancer is the best way to treat breast cancer. To help detect breast cancer in children, mass and microcalcification clusters are significant early indicators of possible breast cancer. The reasoning for spectral clustering implementation is very simple, it can be easily solved by modern methods of linear algebra, and it extends conventional clustering algorithms such as the algorithm of K-means. Spectral clustering is used to group N data points in I-dimensional space into multiple clusters and mammograms are segmented using K Means, Fuzzy C-Means, DBSCAN and Spectral Clustering, where the tumor is detected in the breast and the exact location of the tumor is identified. The efficiency of Fuzzy C-Means plays a major role compared to other algorithms