Computer aided Breast lesions classification system using digitized fine needle aspirate images

According to the WHO, the cases of Breast Cancer are now a global issue as the cases are increasing day by day globally. Hence the early detection of malignant tumor is utmost important to prevent patient’s early demise due to patient’s ignorance. If patient comes to doctor and their application detects the tumor is non cancerous or it is just a benign tumor but actually it is malignant tumor then early detection alone can not play such an important role for cancer prevention. So, It is equally important to use best Machine Learning model, which surely detects malignant as malignant tumor and benign as benign tumor. Such accurate model is also highly required along with early detection of Breast Cancer disease. Our work is dedicated in this direction that our suggested model predicts malignant tumor as malignant and benign as benign tumor with high accuracy than existing model is providing. This paper suggests an architecture which produces high accuracy of the model when applied on Wisconsin Diagnostic Breast Cancer (WDBC) dataset obtained by digitized fine needle aspirate images. Our suggested model is the modified version of SVM. It is providing 63% accuracy when data points are not scaled, 98% when date is correctly scaled and 99% when the data points are correctly scaled with appropriate regularization and K fold validation techniques are applied on Support Vector Machine (SVM) instead of simply using default SVM with default parameters. Evidently, our suggested SVM provides 99% accuracy for detecting tumor as benign or malignant over WDBC dataset obtained by digitized fine needle aspirate images.