Texture classification of tissues in computed tomogeraphy based on wavelet-based contourlet packet

The research presented in this paper is aimed at the development of an automated imaging system for classification of tissues in medical images obtained from Computed Tomography (CT) scans. The paper focuses on using wavelet-based contourlet packets (WBCP)-based multi-resolution texture analysis. The approach consists of two steps: automatic extraction of the most discriminative texture features of regions of interest and creation of a classifier that automatically identifies the various tissues. The discriminating power of several wavelet-based contourlet packet transform (WBCP)-based texture descriptors are investigated. Tests indicate that Energy, Entropy, Mean and Standard Deviation signatures are the most effective descriptors for wavelet-based contourlet packets (WBCP), yielding accuracy rates in the 96-97% range. A comparison with a similar algorithm based on wavelet and ridgelet texture descriptors clearly shows that using wavelet-based contourlet packet transform (WBCP)-based texture features significantly improves the classification of normal tissues in CT scans.