Detection of architectural distortion in mammogram image using wavelet transform

In this paper, we present methods for the detection of sites of architectural distortion in prior mammograms of interval-cancer cases. We observed that screening mammograms obtained prior to the detection of cancer could contain subtle signs of early stages of breast cancer, in particular, architectural distortion. This method uses wavelet transform to improve the accuracy of detection. Before using wavelet transform the image is preprocessed by Otsu threshold method, followed by filtering using morphological filtering. Analysis made using phase portrait analysis, angular spread of power analysis. Further fractal analysis, Laws' texture energy measures derived from geometrically transformed regions of interest (ROIs), and Haralick's texture features are determined. The architectural distorted areas are viewed in marked curved lines which are obtained by diluting image and maximizing the size of the image, if it get vanished it comes under noise category and it is filtered out by morphological filter, if it remains, it comes under architectural distorted region. The accuracy of detection is improved by applying wavelet transform.