Performance analyses of non invasive breast cancer detection based on certain feature level fusion techniques

Abstract

Breast cancer remains the main cause of cancer deaths among women newlinein the world. As per the statistics, it is the most common killer disease of the newlinenew era. Since 2008, breast cancer incidence has increased by more than newline20%, while mortality has increased by 14%. The statistics of breast cancer newlineincidences as per GLOBOCAN project for the years 2008 and 2012 show an newlineincrease from 22.2% to 27% globally. In India alone, breast cancer accounts newlinefor 25% to 31% of all cancers in women.Accurate detection of breast cancer at the earliest stage is very much essential to reduce mortality. Currently, Computer Aided Diagnosis (CAD) is newlinecarried out with the aid of the two major imaging modalities - Mammography newlineand Sonography. Usually radiologists use Cranio Caudal (CC) and Medio newlineLateral Oblique (MLO) mammographic views of each breast to locate the newlinebreast tumours by observing the gray scale morphology and compare relevant newlineareas in double views to verify the diagnostic results. Hence, to mimic the newlineradiologists perception, information derived from both mammographic views newlineis used in CAD system to obtain better performance newline newline