Wavelet transform for directional feature extraction in medical imaging

Directional features are extremely important in diagnostic imaging. They can be used either in the searching for important indication of abnormality or for the reference in image alignment. Wavelet transform (WT) as an efficient method for multiresolution representation has been used extensively in medical imaging in past few years. However, from the view point of directional selectivity, they are not so efficient in feature extraction. In this paper, an analysis and comparison on directional selectivity of wavelet transforms with three different frequency decomposition were taken. The WTs with radial-angular decomposition were used for two medical imaging problems: mass detection in digital mammography and lung nodule detection in chest radiography. The results demonstrated its efficiency.