Evidence-based detection of spiculated lesions on mammography
MetadataShow full item record
The American Cancer Society estimates that 212,920 women will be diagnosed with breast cancer in the United States in 2006. Another 40,970 women will die of the disease. Early detection of breast cancer increases the survival rate and increases the treatment options. Screening mammography, radiographic imaging of the breast, is currently the most effective tool for early detection of breast cancer. Radiologists visually search mammograms for specific abnormalities. Some of the important signs of breast cancer that radiologists look for are clusters of micro calcifications, masses, and architectural distortions. However, mammography is not perfect. Detection of suspicious abnormalities is a repetitive and fatiguing task. For every thousand cases analyzed by a radiologist, only three to four are cancerous and thus an abnormality may be overlooked. Radiologists fail to detect 10% to 30% of cancers and two thirds of these are evident retrospectively. Thus, computer-aided detection (CADe) systems have been developed to aid radiologists in detecting mammographic lesions that may indicate the presence of breast cancer. However, it is widely known that these systems are more accurate for the detection of micro-calcifications than spiculated lesions. In this dissertation a new evidence-based algorithm is developed for the detection of spiculated lesions on mammography. By evidence based, we mean that we use the statistics of the physical characteristics of these abnormalities to determine the parameters of the detection algorithm. Towards this goal, we have shown that the properties of these lesions can be measured reliably and we have created the first database of the physical properties of these lesions. For the detection algorithm, we have invented a new class of linear filters and filter banks which we call Spiculation Filters and Spiculation Filter banks. These filters were created specifically for the detection of spiculated lesions and are highly specific narrowband filters, which are designed to match the expected structures of these abnormalities. As a part of this algorithm, we have also invented a novel technique to enhance spicules on mammograms. This entails filtering in the Radon domain. All the parameters of the detection algorithm are based on measurements of physical properties of spiculated lesions. The results of the detection algorithm are presented in the form of FROC curves and are competitive with existing algorithms.