Computer-Based Identification of Breast Cancer Using Digitized Mammograms |
| |
| Authors: | Rajendra Acharya U E Y K Ng Y H Chang J Yang G J L Kaw |
| |
| Institution: | (1) Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore, Singapore;(2) School of Mechanical and Aerospace Engg., Nanyang Technological University, Singapore, Singapore;(3) Adjunct NUH Scientist, Office of Biomedical Research, National University Hospital of Singapore, Singapore, Singapore;(4) Senior Radiologist, Dept of Diagnostic Radiology, Tan Tock Seng Hospital, Singapore, Singapore |
| |
| Abstract: | High-quality mammography is the most effective technology presently available for breast cancer screening. Efforts to improve
mammography focus on refining the technology and improving how it is administered and X-ray films are interpreted. Computer-based
intelligent system for identification of the breast cancer can be very useful in diagnosis and its management. This paper
presents a comparative approach for classification of three kinds of mammogram namely normal, benign and cancer. The features are extracted from the raw images using the image processing techniques and fed to the two classifiers namely:
the feedforward architecture neural network classifier, and Gaussian mixture model (GMM) for comparison.. Our protocol uses,
360 subjects consisting of normal, benign and cancer breast conditions. We demonstrate a sensitivity and specificity of more
than 90% for these classifiers. |
| |
| Keywords: | Digitized mammogram Breast Benign Cancer Sensitivity Specificity |
| 本文献已被 SpringerLink 等数据库收录！ |
|
