Breast Cancer Prediction and Trail Using Machine Learning and Image Processing

Abstract

As per WHO, there are more than 2.09 million cases furthermore 627,000 deaths globally women are diagnosed with breast cancer worldwide annually. It is one of the common cancer in women in India, occurring at any age however in India rise in the early thirties and peak at 50−64 years of age. Only small number of accurate prognostic and predictive factors is used clinically for managing patients with breast cancer. Early detection of this fatal disease is very important which helps in decreasing the morality rate and increasing the survival period of breast cancer patients. This work exploits Mammography for screening and premature identification, analysis as well as processing are solution to improving breast cancer prognosis. To detect breast cancer with mammogram, segmentation of image is performed with the help of Fuzzy C-Means (FCM) technique. As the regions are segmented the required features are extracted, and trained. Finally trained images are classified by the efficient classifier of different classes in mammogram. Texture features are extracted using a feature extraction technique like Gray-Level Co-occurrence Matrix (GLCM), Multi-level Discrete Wavelet Transform and Principal Component Analysis (PCA). Morphological operators are used to make a distinction of micro-calcifications and masses from background tissue also for classification KNN algorithm are exercised. The boundaries of tumor affected region in mammogram are marked and displayed to the doctor, along with area of tumor.