AUTOMATIC ANALYSIS OF MAMMOGRAPHY IMAGES: CLASSIFICATION OF BREAST DENSITY
Rita Filipa, Santos Teixeira · 2013
Breast cancer is the most common malignancy of women and is the second most common and leading cause of cancer deaths among them. At present, there are no effective ways to prevent breast cancer, because its cause is not yet fully known. Early detection is an effective way to diagnose and manage breast cancer can give a better chance of full recovery. Therefore, early detection of breast cancer can play an important role in reducing the associated morbidity and mortality rates. Mammography has proven to be the most effective tool for detecting breast cancer in its earliest and most treatable stage, so it continues to be the primary imaging modality for breast cancer screening and diagnosis. Furthermore, this exam allows the detection of other pathologies and may suggest the nature such as normal, benign or malignant. The introduction of digital mammography is considered the most important improvement in breast imaging. Computer-aided detection/diagnosis (CAD) has been shown to be a helpful tool in the early detection of breast cancer by marking suspicious regions on a screening mammogram, allowing thus to reduce the death rate among women with this disease. These systems use computer technologies to detect abnormalities in mammograms and the use of these results by radiologists for diagnosis play an important role, once characterize lesions through automatic image analysis. The CAD performance can vary because some lesions are more difficult to detect than others, this is because they have similar characteristics to normal mammary tissue. However, it is important to continue working in order to decrease the number of failures. The pectoral muscle represents a predominant dense region in medio-lateral oblique views of mammograms. Its segmentation has been considered an important factor for an adequate performance of automatic cancer detection methods. Mammograms images are hard to interpret because of the complex tissue morphology of the breast and the number of imaging parameters that affect mammogram acquisition. Classification of breast density is important for epidemiological studies investigate the relationship between mammogram density and the occurrence of cancer. For these reason, there is an increasing interest in using measurements of mammographic density patterns in computer aided-detection.