Tumor Analysis Using Breast Elastography

• Main Authors: Juliwati Joe, 尤溫柔
• Other Authors: Ruey-Feng Chang
• Format: Others
• Language: en_US
• Published: 2007
• Online Access: http://ndltd.ncl.edu.tw/handle/96215736435230642060

碩士 === 國立中正大學 === 資訊工程所 === 95 === In recent years, the breast cancer is globally the main causes of death for women. If a cancer can be found out earlier, the curability of the breast cancer will increase greatly; therefore American Cancer Society suggests that women more than twenty years old should take breast examination annually. Clinically, the computer-aided analysis can help radiologists to differentiate the benign and malignant tumors. If computer-aided analysis provides higher accuracy, the demand of the breast biopsy can be reduced. In this paper, the color elastographic breast images are used to diagnose the breast tumors, on which the blue region represents the harder tissues, while the green to red region represents the softer tissues. We propose an analysis method using several features for differentiating tumor malignancy of breast elastography. The malignant and benign tumors have different elasticity characteristic. Generally, the malignant tumor is harder, while the benign tumor is softer, so we make use of this characteristic to apply in our analysis method. The tumor contours of the input images in our experiment were drawn by physician in advance, and then we applied our analysis method to the images to classify the malignancy of them. Other than elastographic features, we also applied BI-RADS standard features to analyze the malignancy of the tumor. In our experiments, 181 pathology-proven cases are used to test the accuracy of our proposed computer aided system; among them, there includes 113 benign and 68 malignant breast tumors. The accuracy rate of proposed computer aided analysis method towards elastography features can achieve 86.19% on breast elastography, on B-mode features can achieve 82.32%, and on both features can achieve 90.61%.