Malignancy Determination Breast Cancer Based on Mammogram Image With K-Nearest Neighbor

Breast cancer is the most common cancer in women and for both men and women is the second highest type of cancer in the world. Early diagnosis and treatment is one way to provide appropriate treatment for the presence of breast cancer so that the risk of developing cancer from benign to malignant can be minimized. Before the physical symptoms of cancer appear, mammography is an efficient tool for detecting early breast cancer. In Computer Aided Diagnosis using the detection mammogram images that are either dependent on extraction features and classification methods. In this study, the process of determining features uses first order with six characteristics which will then become the basis for the classification process with KNN. The results obtained were the highest accuracy values found when the value of K = 5 with an accuracy of 91.8% for classification with cross-validation and K = 15 with an accuracy of 91.8% with classification without cross-validation.