Breast Cancer Detection Using Support Vector Machine Algorithm

Abstract

Abstract: Breast cancer is primary cancer affecting women and ranks second as the leading cause of female mortality. The crucial aspect is identifying the presence of breast cancer and pinpointing the affected area. Medical imaging consistently advances, and early detection of cancer is vital in lowering cancer death rates. The enhancement procedure for mammograms involves filtering and discrete wavelet transforms. Contrast stretching is utilized to boost image contrast. Improved Breast cancer early detection and diagnosis are achieved by segmenting mammogram images. From the segmented breast region, features are retrieved. The proposed system identifies the cancer region and classifies patients as either normal or cancerous. The input mammography image is subjected to pre-processing techniques, and undesirable parts of the image are cropped off. Using morphological techniques, the tumor location is separated from the surrounding tissue and marked on the original mammography image. If the mammogram image is normal, the patient is deemed normal; otherwise, the patient is diagnosed with cancer. The Decision Tree Algorithm is utilized for categorization in this study for reasons of comparison.