Texture Classification of Normal Tissues in Computed Tomography

Biomedical imaging is increasingly electronic in terms of image acquisition and display. Image detectors have become so sensitive that the amount of information acquired is greater than can be displayed at any one time without using special purpose hardware. Research in image processing methods is essential to fully exploit the information that has been acquired. Furthermore, the ability to extract quantitative information from images is becoming increasingly important, requiring algorithmic (as opposed to visual) processing. In medical image processing, texture is especially important, because it is difficult to classify human organ tissues using shape or gray level information. Some of the challenges are: 1) the shape of each organ is not consistent through out all slices of a 3D medical image and may change quickly where the inter-slice distance is large, and 2) the gray level intensities overlap considerably for soft tissues. On the other hand, organs are expected to have consistent and homogeneous textures within tissues .