PROJECT TITLE :

One Class Classification Of Mammograms Using Trace Transform Functionals - 2014

ABSTRACT:

Mammography is one in all the first diagnostic tests to prescreen breast cancer. Early detection of breast cancer has been known to enhance recovery rates to a great extent. In most medical centers, experienced radiologists are given the responsibility of analyzing mammograms. But, there is continually a risk of human error. Errors can frequently occur as a results of fatigue of the observer, ensuing in interobserver and intraobserver variations. The sensitivity of mammographic screening also varies with image quality. To offset completely different types of variability and to standardize diagnostic procedures, efforts are being made to develop automated techniques for diagnosis and grading of breast cancer images. This paper presents a 1-category classification pipeline for the classification of breast cancer images into benign and malignant categories. As a result of of the sparse distribution of abnormal mammograms, the two-class classification downside is reduced to a 1-class outlier identification problem. Trace rework, which may be a generalization of the Radon rework, has been used to extract the features. Many new functionals specific to mammographic image analysis are developed and implemented to yield clinically important options. Classifiers like the linear discriminant classifier, quadratic discriminant classifier, nearest mean classifier, support vector machine, and therefore the Gaussian mixture model (GMM) were used. For automated diagnosis, the classification pipeline was tested on a set of 313 mammograms provided by the Singapore Anti-Tuberculosis Association CommHealth. A most accuracy rate of ninety two.forty eight% has been obtained using GMMs.