Multi Scale Region based Advance Scheme for Breast Cancer Detection and Classification Alkaben Prajapati CE Department, L.J. Institute of Engineering and Technology, Ahmedabad Dr. A.C. Suthar CE Department, L.J. Institute of Engineering and Technology, Ahmedabad ABSTRACT BREAST cancer diagnosis is usually performed by doctors based on Digital Mammography (DM) or on Medical Images (MI). In order to assist doctors to process big amount of images for different patients, Breast Cancer Computer Aided Diagnosis (BC- CAD) is becoming, nowadays, an appealing area of research Using image processing techniques for computer-aided diagnosis that involves the feature extraction for cancer detection, so as to help doctors towards making optimal decisions quickly and accurately. Features play an important role in detecting the cancer in the digital mammogram and feature extraction stage is the most vital and difficult stage. In this research, an enhanced feature extraction method named Multi-scale Surrounding Region Method (MSRM) is proposed to be effective in classifying the mammogram images into normal or benign or malignant. This proposed system is based on a four-step procedure: Regions of Interest specification, segmentation base on edge and thresholding, and multi-scale surrounding region dependence matrix computation and feature extraction. After that we apply machine learning mechanism for classify breast cancer on early stage as soon as possible and we also use segmentation approach for that. after Implement Proposed Algorithm achieve more than 93% Accuracy for detect and Classify Breast Cancer with Benign and Malignant type tumors. Keywords: Breast Cancer, Classification, Segmentation, Feature Extraction 1. INTRODUCTION Breast cancer is one of the frequent diagnosis diseases among women. It tends to be distinguished by clinical breast examination, yet the discovery rate suffers to be extremely low. Also, the unusual abnormal areas that can't be felt can be very testing to check utilizing traditional methods however can be effectively observed on a conventional mammogram or with ultrasound. Mammography is as of now the best technique for identifying breast cancer at its beginning time. The issue with mammography pictures is they are intricate. Subsequently, picture processing and features extraction methods are utilized to help radiologist for recognizing tumor. Highlights extricated from suspicious locales in mammography pictures can help specialists to find the presence of the tumor at continuous in this way accelerating treatment process. Recognizing breast cancer can be a significant testing work. Specially, as cancer is certifiably not a solitary illness however is an accumulation of numerous infections. Therefore, every malignant growth is not the same as each other disease that exist. Likewise, a similar medication may have diverse response on comparable kind of malignant growth. Subsequently, disease change from individual to individual. Contingent upon just a single strategy or one calculation to identify breast cancer may not give us the most ideal outcome. As one malignancy contrast from another, comparably every bosom shows up uniquely in contrast to another. The mammography image can likewise be undermined if the patient has experienced some breast medical procedure [11] Mukt Shabd Journal Volume IX, Issue VI, JUNE/2020 ISSN NO : 2347-3150 Page No : 3391