Abstract Views :168 |
PDF Views:3
Authors
Affiliations
1 Computer Science and Engineering Department, Dr. Sivanthi Aditanar College of Engineering, Tiruchendur, IN
Source
Artificial Intelligent Systems and Machine Learning, Vol 3, No 6 (2011), Pagination: 376-380
Abstract
To aid radiologist in early detection of breast cancer a retrospective study of mammograms was conducted. In this pioneer study screening mammograms that were normal and malignant mass categories were analyzed. For each of the mammographic projection of normal and abnormal breast, one region was marked: 1) Region one which is corresponded to the normal mammogram report. 2) Region two, which corresponded to the site where the malignant mass developed. All the regions were marked as Circle with specified radius. The texture and photometric image features were then calculated for all of the marked areas. The resulting feature values for the two groups of normal regions and abnormal regions then form the input to Stepwise discriminant analysis for dimension reduction. This analysis examines all the features and determines the ones that can best distinguish between the two groups of normal and abnormal regions. Then also creates the support vector machine, the best linear classification, which can be used to classify new cases. At its current stage, the system can be used by a radiologist to examine any pattern in a mammogram. The regions which are flagged by the system have a 72% chance of developing a malignant mass by the time of the next screening. Therefore, further evaluation of these patients (e.g., a screening examination sooner than the normal one year interval) could result in earlier detection of breast cancer. The ultimate goal is to run the system automatically over the whole mammogram and flag any suspicious region. The study is validated using the mammograms obtained from the online Mammographic Image Analysis Society (MIAS) Digital Mammogram database.
Keywords
Breast Cancer, Computer-Assisted Diagnosis (CAD), Digital Mammography.