Please use this identifier to cite or link to this item: http://hdl.handle.net/10603/284816
Title: A Novel Approach for Classification and Early Detection of Breast Cancer using Image Enhancement Image egmentation and Feature Extraction on Mammograms
Researcher: PARAMKUSHAM SPANDANA
Guide(s): B.V.V.S.N.Prabhakar Rao
Keywords: Engineering and Technology,Engineering,Engineering Biomedical
University: Birla Institute of Technology and Science
Completed Date: 2018
Abstract: Breast cancer is the most common cancer in women in India and world over the last decade. It is the second most leading cause of cancers death among women. Breast cancer accounts for 25% to 31% of all cancers in women in India. Incidence rate has been increased from 22.2% in 2008 to 27.05% in 2012 in India. According to WHO for the year 2012, an estimated 70,218 women died in India due to breast cancer, more than any other country in the world. According to the reports of Indian Council for Medical Research in 2016 the breast cancer cases expected to rise by about 14.5 lakhs and this may increase to 17.3 lakhs in 2020. Digital mammography plays a vital role in the early detection of breast cancer. It helps to avoid wrong diagnosis, unwanted examinations, and inadequate surgeries, which directly affects the outcome and longevity of the patient. However, due to low contrast and high noise in the mammograms, it is challenging task to detect the abnormalities. Thus, for early detection and diagnosis of breast cancer in mammograms, there is a significant need of computer aided system (CAD). CAD system uses image processing and computerized techniques to pinpoint the abnormalities and classify mammogram into several classes namely normal or abnormal, benign or malignant etc. newlineIn this thesis, the contributions include the development of new algorithms for image enhancement, segmentation and feature extraction for early detection of breast cancer using mammograms. In addition to that, an automatic CAD system has been developed for the detection and analysis of abnormalities without user intervention. In this context, we have developed algorithms for image enhancement, image segmentation and different feature extraction schemes based on both shape and gray level characteristics of abnormality in mammograms. These relevant features extracted are submitted to classifier for further analysis. newlinevi newlineThe analysis includes classification of breast regions into normal-abnormal and benign-malignant. These schemes developed for CAD sy
Pagination: 142p.
URI: http://hdl.handle.net/10603/284816
Appears in Departments:Electrical & Electronics Engineering

Files in This Item:
File Description SizeFormat 
thesis_spandana.pdfAttached File5.76 MBAdobe PDFView/Open


Items in Shodhganga are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetric Badge: