Mathematical Model for Segmentation of Medical Images via Hybrid Images Data.

The analysis of medical images requires image segmentation to distinguish the boundaries of irregular regions such as tumors in images. However, segmentation of medical images with intensity inhomogeneity has always been a challenging task in image processing. In this paper, we have proposed a new model for segmentation of medical image having inhomogeneous intensities. In the proposed model, we have used hybrid image data obtained from the product of given image with smooth image and difference of smooth product image from product image. The model uses both local and global information of the image. The proposed model outperforms the existing models qualitatively and quantitatively i.e. in terms of number of iterations and CPU time. For the solution of proposed model we have used some of the numerical schemes such as Explicit and Semi-Implicit schemes. The model is further tested for different type of real medical images. The results showed that the proposed model also performs well in images having intensity inhomogeneity and blurred edges as well. [ABSTRACT FROM AUTHOR]