MAMMOGRAM IMAGE TO DETECT BREAST CANCER USING K-MEANS CLUSTERING ALGORITHM

Author (s) : S.Soniya & M.Sivaranjani, M.Brindha, A.Saritha

---

Abstract :
Breast Cancer is the uncontrolled multiplication of group of cells in breasts and is the second largest disease leading to the death of women in the world. The disease can be cured if it is detected in early stages. A lot of research has been done to find out the tumor correctly but a 100% accurate method has not been found. Research on breast cancer detection using digital image processing is not new but many new approaches in this field is being considered to accurately predict the tumor region. The present approach is to detect the tumor region visually as well as to figure out in which region the tumor is mostly concentrated. Mammography screening images two views CC and MLO are widely used in diagnosis process. This project presents the method to detect cancer region and classify normal and cancerous patient. Pre-processing operations are performed on the input Mammogram image and undesirable parts are removed from the image. Tumor regions are segmented from the image using morphological operation and are highlighted on original mammogram image. If mammogram image is normal then it shows that patient is healthy. This work majorly focuses on finding out the best algorithms to detect the tumors present in the breast. In the proposed work, a variety of algorithms has been applied but the best one suited for cancer detection is the combination of K-Means clustering algorithm. Classification accuracy of K-Means is 95% accurate output will be predicted.

Keywords : Mammography, K-Means clustering algorithm, breast cancer

Conference Date : 30/08/2019

Pages : 310

Paper ID : 19301