DIAGNOSIS OF BREAST CANCER USING SEGMENTATION AND CLASSIFICATION TECHNIQUES
Kalyani Ghuge, Vaishnavi Gurram, Gunashree Bhosale · Journal of Critical Reviews · 2020
Nowadays, Breast cancer or Breast Carcinoma is a harmful disease among women. Also, it is the most curable cancer if it is detected early. There are many methods to improve the accuracy of the diagnosis of breast cancer like Machine Learning. The main aim of this paper is to propose ways to automate the mammogram image processing using different pre-processing and segmentation techniques and then classified using Support Vector Machine (SVM) algorithm. The mini-MIAS dataset is used for processing. The techniques for the segmentation of mammograms are K-means(KM) and Fuzzy C-means Clustering (FCM). A comparison between these two techniques will lead to finding the best algorithm for segmentation. SVM used to classify tumors into benign(non-cancerous) and malignant(cancerous) tumors. The algorithms used to detect cancer will help to increase accuracy. Using different segmentation techniques, the tumor part gets extracted and then identifying the tumor types using the SVM classifier. These algorithms are used to improve the accuracy in predicting breast cancer.