Breast cancer detection through image processing techniques

Breast cancer has become the leading cause of cancer deaths among women in developed and developing countries. Recent statistics show that breast cancer affects one of every 10women in Europe and one of every eight in the United States and one in every seven in Egypt (American Cancer Society ACS, 2009). Early diagnosis and early treatment are the best ways toreduce deaths due to breast cancer. Early diagnosis requires an accurate and reliable diagnosticprocedure that allows. physicians to distinguish benign from malignant breast microcaicifications (MCs), and finding such a’ procedure is an important goal. The key tosurviving breast cancer is early detection and treatment. According to the ACS, when breastcancer is confined to ~hebreast, the five-year survival rate is almost 100%. Breast cancer screening has been shown to reduce breast cancer mortality (Society, 2004). Currently, 63% ofbreast cancers are diagnosed at a localized stage.for which the five-year su~vival rate is 97%.Mammography has been one of the most reliable ’methods for. early detection of breastabnormalities. X-ray mammography is currently considered as standard procedure for breastcancer diagnosis. Radiologists find abnormalities in mammograms, and classify them as benignand malignant-usually-by-further, biopsy-tests. -However=studies have shown that-radiologistscan miss the detection of a’ significant proportion of abnormalities in addition to having highrates of false positives. The estimated sensitivity of radiologists in breast cancer screening isonly about’75% (Moayedi et al., 2007). Double reading has been suggested to be an effectiveapproach to improve the -sensitivity. But it becomes costly because it requires twice as manyradiologists’ reading time.I Therefore, it would be valuable to develop a computer aided method for MCs classificationI based on extracted features from the region of interests (ROI) in mammograms. This wouldI reduce the number of unnecessarv biopsies in patients wi’th benign disease and thus avoidIpatients’ physical and mental suffering, with an added bonus of reducing healthcare costs.Digital mammography brought the possibility of developing and using computer aided diagnosis .’(CAD) system for the classification of benign and malignant patterns. The idea of using computer help in the analysis of radiographic’ images is not new. Already in 1964 Meyers et.prOposed.-a”System~~to. automatically-’-determine the ”cardio-thoraclc .ratlo on chest radiographs. In 1967, Winsberg et al. developed a system for automated analysis of