Comparative Study of Algorithms used for Predicting Invasive Ductal Carcinoma (IDC)

Breast cancer is a disease which we hear about a lot nowadays. It is one of the most widespread diseases. It affects both men and women all around the world. Research says that every year around 2000+ new cases of breast cancer for men and about 2,30,000 new cases for women. Diagnosis of this disease is crucial and its demand the faster treatment for the recover. Correct and early diagnosis of these disease can save the patient. Breast cancer detection is done with the help of mammograms, which are basically X-rays of the breasts. Detection is not easy due to different kinds of uncertainties identified in these mammograms. Machine Learning (ML) techniques can help for the early detection of breast cancer. This paper consists of these techniques which can help doctors for early detection and diagnosis of breast cancer which could greatly enhance the survival rate of patients. In this paper, Support Vector Machine (SVM) and Convolution Neural Network (CNN) model applied for the data set which contains both benign and malignant breast cancer images and generated confusion matrix for validating the result. We also performed a comparative analysis of Logistic regression, SVM, Naive Bays, Neural Networks, Decision tree, Adaboost and Random Forest.