MAMMOGRAPHIC IMAGE DENOISING AND CONTRAST ENHANCEMENT

Abstract

Breast cancer is one of the most common malignant diseases among women, it is important to give patients early diagnose and treatment. Mammography has become the most effective way for detection of breast cancer, and it is sensitive to clustered microcalcification which is the main characteristic of early breast tumors. Mammography is a specific type of imaging that uses a low-dose X-ray system for examination of the breasts. Area of thesis is mammographic image denoising and contrast enhancement on the basis of diagnostic feature information extracted from mammograms. Thesis work proposed an efficient enhancement algorithm for contrast enhancement and detection of microcalcifications in digital mammograms based on wavelet analysis and mathematical morphology. In this proposed thesis work, we adopt mathematical morphology and wavelet-based level dependent thresholding algorithm to increase the contrast in mammograms. For the evaluation of the performance of the enhancement algorithm, contrast improvement index is used. After enhancement, algorithm for segmentation of microcalcification based on edge detection is implemented. After segmentation of each microcalcification from mammogram, diagnostic features are calculated. First order histogram based features and texture based GLCM features are extracted. Total ten features are calculated. Feature set extracted is used for classification of microcalcification between malignant and benign and normal case. The feature set is divided into three groups, such that a single group is used for testing the model that has been developed from the remaining two groups. The evaluation statistics for each method is then assessed as an average of three groups