BRAIN MR IMAGE SEGMENTATION BY MODIFIED ACTIVE CONTOURS AND CONTOURLET TRANSFORM

Multiresolution analysis is often used for image representation and processing because it can represent image at the split resolution and scale space. In this paper, a novel medical image segmentation algorithm is proposed that combines contourlet transform and modified active contour model. This method has a new energy formulation by representing the image with the coefficients of a contourlet transform. This results fast and accurate convergence of the contour towards the object boundary. Medical image segmentation using contourlet transforms has shown significant improvement towards the weak and blurred edges of the Magnetic Resonance Image (MRI). Also, the computational complexity is less compared to using traditional level sets and variational level sets for medical image segmentation. The special property of the contourlet transform is that, the directional information is preserved in each sub-band and is captured by computing its energy. This energy is capable of enhancing weak and complex boundaries in details. Performance of medical image segmentation algorithm using contourlet transform is compared with other deformable models in terms of various performance measures.