P Narasimhaiah¹* and C Nagaraju²

¹Research Scholar, Department of Computer Science and Engineering, YSR Engineering College of YVU, Yogivemana University-Kadapa, India
²Professor, Department of Computer Science and Engineering, YSR Engineering College of YVU, Yogivemana University-Kadapa, India

*Corresponding Author: P Narasimhaiah, Research Scholar, Department of Computer Science and Engineering, YSR Engineering College of YVU, Yogivemana University-Kadapa, India.

Received: March 04, 2022; Published: July 18, 2022

Abstract

Breast cancer is one of the most prominent diseases and the second foremost source of death among middle-aged women in the world. An early finding is the underpinning of breast cancer deterrence. Removing of breast tumor by using a surgical treatment and chemotherapy could work excellently if it can be identified as a primary tumor or at an early stage of transmutation. The quick development of machine learning techniques continues to burn the medical tomography enthusiasm in implementing these to improve the accurateness of tumor findings. In the area of mammographic applications to capture, analyse and store breast mammograms automatically machine learning plays a key role. Breast cancer detection using screening mammograms early reduces women's mortality and provides better treatment and increases the survival rate. To identify breast cancer in the area of machine learning lots of attempts were made, but these techniques are not too accurate. In the proposed method advanced CAD techniques and machine learning tools are used to remove a label, pectoral muscles, noise, and identification of cancer. For database construction, GLCM features are used and a confusion matrix is used to estimate accuracy. The experimental results are computed and it is inspected, the proposed method shows preferable accuracy to the existing method.

Keywords: Canny; Mammogram; GLCM, and MLRM