Research Of Key Techniques Of Breast Mass Detecting And Analyzing

With the breast cancer occurrence still growing, the breast cancer has become the most common form of cancer in the female population. Early detection, early diagnosis and early treatment are the most important methods in diagnosis. Because of a high spatial resolution and sensitivity for the breast mass and calcification, mammography is the first imaging choice. Breast masses are one of the basic, common and important mammographic indicators of malignancy. This paper presented an automatic mass detection algorithm with strong applicability to provide the accurate reference information for the doctor. On the basis of the mass detection, this paper devote to a study of the mass location distribution to provide a tool which reliably analyze the mass location distribution to the doctor.The mass detection algorithms in this article are divided into three parts. Firstly, aiming at the diverse feature of the breast mass, we presented improved dynamic programming segmentation methods with strong robustness of the mass size, mass location and mass density, so we can a precise mass contour. Secondly, aiming at the breast mass with the strong texture feature, we fit the mass contour and obtain the RBST image of the mass. In the RBST image, we extract the texture feature based on the gray level co-occurrence matrix. Because of the RBST image and the gray level co-occurrence matrix can reflect the texture feature, so we can extract the effective mass feature. Finally, to increase the generalization performance of the classification, we used an adaptive SVM to classify and identify the breast mass. For the data set with the inhomogeneity intensity, our introduced method was improved15percent compared to the traditional method.We proposed a faithful analysis tool based on the detection of the mass and the distribution of the breast mass location. The tool contains three parts. The first part is to select a reference image and build a gold standard database of the breast mass. The second part is to get the breast contour combining the method of removing the muscle and nipple and rectify the breast contour using the CPD registration. The last part is analysis the distribution of breast mass based on the large amount of the breast mass database. We come to a conclusion that the outer-upper quadrant is the main distribution area of the breast mass, therefore it can provide the reference information for the diagnosis of the breast cancer.