Research Of CAD And Microcalcification Detection In Mammography

Breast cancer is one of the most common malignant diseases among women. Clear evidence shows that early discovery, early diagnosis and early treatment of breast cancer can significantly increase the chance of survival for patients. Mammography is the most effective method for the early detection of breast cancer. However normally, viewed mammograms display only a very small part of the total information they contain. It is very hard to find the microcalcifications (MCCs) of early breast cancer in mammograms even for an experienced radiologist. Therefore, any increase in the detection and classification of MCCs will lead to further improvement in its efficacy in the detection of early breast cancer. With the rapid progress of computer technology, computer aided detection and identification of MCCs have been a hot research field since clustered MCCs in mammograms are an important sign for early detection of breast cancer. It is estimated that about 30% to 50% of breast carcinomas detected radiographically demonstrates MCCs in mammograms. So the increase in the detection and classification of MCCs in mammograms has been of interest to many researchers.In this thesis, some key issues of the Computer Aided Diagnosis (CAD) technique of breast cancer MCCs are systematically investigated. Firstly, an algorithm is presented based on the morphological analysis and wavelet transform to segment the MCCs, and this method improve the true positive and reduce the false positive; Secondly, extract features from the original ROIs and the images after the segmentation of MCCs, then use the Probabilistic Neural Network (PNN) to classify the ROIs into with or without MCCs and diagnosis the benign or malignant of the ROIs.Use the above method to analysis the mammography of MIAS, the TP of the detection of the MCCs is 80.2%, the TP of classification of with or without...