Medical Images Segmentation Using WGAC Technique: A Fast Geodesic Active Contour Model Using Prior Analysis and Wavelets

Image Segmentation is an image processing technique which is used to subdivide an image into regions in which each one contains components having similar properties or characteristics. Its goal is to "simplify and/or change the representation of an image into something that is more meaningful and easier to analyze". This approach has many applications. One of its most important applications is the extraction of tumor areas from medical images as a first step in the therapy planning of cancer patients. This objective can be achieved by many image segmentation approaches. One of these successful techniques is the active contour (Snake); its idea is based on a flexible curve (or surface) which is dynamically adapted to required edges or objects in an image. In this work an improvement over a current active contour model is proposed. The new model was tested using real CT images and has given promising results.

Sharif M. S. Al-Sharif, Palestinian. He Received his Master degree in Systems Engineering from KFUPM, KSA in 2010. His Master Thesis scope was Medical Image Processing. Mohammed Deriche, Algerian. Associate Professor in Electrical Engineering. KFUPM, KSA. Nabil Maalej, Tunisian. Associate Professor in Medical Physics. KFUPM, KSA.