Detection and Diagnosis of Breast Tumors using Digital Mammogram Images: A Fuzzy Approach

Breast cancer is one of the major causes of death among women. Tiny clusters of micro calcifications appear as collection of white spots on mammograms show an early warning of breast cancer. Primary prevention seems impossible because the causes of this disease are still remaining unknown. An improvement of early diagnostic techniques is important for womens quality of life. Mammography is the key test use for screening and pre-diagnosis. Early detection performed on X-ray mammography is the key to improve breast cancer prognosis. In order to increase radiologists diagnostic performance, several computer-aided diagnosis (CAD) methods have been developed to advance the detection of primary signatures of this disease masses and micro calcifications. Masses are space-occupying lesions, described by their shapes, structure, boundaries, and denseness properties. A benign neoplasm is smoothly marginated having regular shape, whereas a malignancy is characterized by an indistinct and irregular border that becomes more speculated with time. Because of the slight differences in X-ray attenuation between masses and benign glandular tissue, they appear with low contrast and often very blurred. Micro calcifications are small deposits of calcium that appear as small bright spots in the mammogram. This paper presents a staging approach on mammography images using gradient magnitude Sobel filter for cancer tumor mass segmentation. After Enhancement, the first step of the cancer signs detection should be a segmentation procedure can distinguish masses and micro calcifications from background tissue followed by fuzzy classifier. The proposed technique shows good results.