Finding Orientated Line Patterns in Digital Mammographic Images

In mammography the presence of subtle abnormalities such as stellate patterns and architectual distortions indicates possible malignancy. Radiologists do not always detect these abnormalities in screening mammograms; this has led to interest in computer–aided mammographic interpretation where the radiologist is presented with computer–generated ’prompts’ for abnormalities. A first step in this process is the detection of the “orientation”, “scale” and “strength” of linear structures in the mammograms. We discuss several generic methods for extracting this information from images and compare their performance using synthetic images intended to simulate the appearance of mammograms. We show significant differences in performance between the different methods. We also show results obtained for real mammograms.