Open AccessSVM BASED APPROACH OF DETECTION AND CLASSIFICATION OF TUMORS IN MAMMOGRAPHY
Author(s) -
M. Lakshmitha,
A. Abdul Hayum
Publication year - 2020
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2020.v05i01.075
Subject(s) - mammography , support vector machine , artificial intelligence , pattern recognition (psychology) , computer science , medicine , cancer , breast cancer
One of the most lethal cancer threating women all over the world is the breast cancer. It is medically defined as abnormal cell growth in the breasts. It is estimated that by the end of 2020 about 17 lakh women will be diagnosed to have breast cancer. After detected with carcinoma out of 100 women in US only 89 women can survive for at least 5 years. The diagnosis of carcinoma has different procedures evolved from various technologies. But the diagnosis results are not exact all the time and the major drawback reported to be is false-positives. The advancement of image processing and artificial intelligence had led to diagnosis results of cancer masses more accurate and in short time. This project provides a solution for early detection by processing the mammogram images to locate the carcinoma and to specify the stage of cancer. It employs the machine learning approaches to perform the classification after the identification of the location of cancer masses. To classify the cancer stages the unsupervised learning technique named as support vector machines is implemented.