International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 04 | Apr-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 1147 DETECTION OF SUSPICIOUS LESIONS IN MAMMOGRAM USING ZEBRA MEDICAL VISION ALGORITHM Mrs.LAKSHMI.S 1 , ELAKKIYA.G 2 , SINDHUJA.R 3 , SRINIDHI.U 4 1 Assistant Professor, Dept. of Electronics & Instrumentation Engineering, Panimalar Engineering College, Chennai, Tamil Nadu 2,3,4 Students , Dept. of Electronics & Instrumentation Engineering , Panimalar Engineering College, Chennai, Tamil Nadu ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - The main objective of this project is to detect breast cancer which is the second most deadly type of cancer among women. The existing system is based on the Fuzzy C- means algorithm. In Fuzzy clustering, data elements can belong to more than one cluster, and associated with each element is a set of membership levels. One of the widely used clustering algorithms is Fuzzy C-Means algorithm. The clustering based techniques are the techniques, which segment the image into clusters having pixels with similar characteristics. The existing system i.e., FCM is less accurate. FCM is not that much fast, robust and easier to understand.FCM still needs more computational time. Zebra Medical Vision Algorithm detects the presence of lesions in the Mammogram. Zebra’s mammography algorithm is developed with the aid of thousands of patient studies, aims to optimize BC screening by reducing both false positive results and false negative results. In this project, MATLAB is used as the key tool for identification and classification of the tumor. In the future, this detection technique can be further enhanced by using Artificial Intelligence. By programming the robots with these algorithms the presence of lesions can be detected and removed with the efficiency equal to that of expert radiologists. Our proposed method has achieved greater accuracy than the previous methods. Key Words: Mammogram, Fuzzy, Clustering, Shock filter, Sobel , Masking , Marker Controlled Watershed Segmentation 1. INTRODUCTION The Zebra algorithm provides superior results compared to current tools, reducing misdiagnosis and false alarms. Women over 45 are advised to have a screening mammogram every two years. Approximately 10% of tests are sent for further evaluation due to suspicious findings, and approximately 5 women out of every 1,000 will develop breast cancer. Unfortunately, one of those 5 will be missed, and discovered too late. Furthermore, most women that are sent for biopsy follow ups turn out to be healthy – subjecting them to unnecessary tests and mental anguish. Zebra’s new algorithm helps provide better outcomes in two keys ways by reducing both false negatives and false positives. Less false negatives results in accurately detecting women with cancer and fewer false positives means women will not have to undergo unnecessary tests and stressful procedures. 1.1 Breast Cancer Breast cancer starts in the cells of the breast. A cancerous (Malignant) tumor is a group of cancer cells that can grow into and destroy nearby tissue. It can also spread (metastasize) to other parts of the body. Cells in the breast sometimes change and no longer grow or behave normally. These changes may lead to non-cancerous (Benign) breast conditions such as atypical hyperplasia and cysts. If the cancer is located only in the breast, the 5-year relative survival rate of people with breast cancer is 99%. Sixty-one percent (61%) of cases are diagnosed at this stage. If the cancer has spread to the regional lymph nodes, the 5-year survival rate is 85%. If the cancer has spread to a distant part of the body, the 5-year survival rate is 26%. 1.2 Mammogram A Mammogram is an x-ray picture of the breast. Mammography (also called Mastography)is the process of using low-energy X-rays (usually around 30 kVp) to examine the human breast for diagnosis and screening. The goal of mammography is the early detection of breast cancer. 2. EXISTING SYSTEM The existing system is based on the Fuzzy C-means algorithm. In Fuzzy clustering, data elements can belong to more than one cluster, and associated with each element is a set of membership levels. One of the widely used clustering algorithms is fuzzy C-Means algorithm. The clustering based techniques are the techniques, which segment the image into clusters having pixels with similar characteristics. Data clustering is the method that divides the data elements into clusters such that elements in same cluster are more similar to each other than others. In the threshold based segmentation the image is considered as having only two values either black or white. But the bit map image contains 0 to 255 gray scale values. So sometimes it ignores the tumor cells also. In case of the region growing based segmentation it needs more user interaction for the selection of the seed. Seed is nothing but the center of the tumor cells; it may cause intensity in homogeneity problem. And also it will not provide the acceptable result for all the images.