Optimum Regularized Joint Registration and Segmentation Method for Medical Brain Images

Mrs. N.Usha Rani, Dr.P.V.Subbaiah, Dr.D.VenkataRao

Abstract


Image registration and segmentation are the two important processes that are frequently used in medical image processing and computer vision applications. In traditional medical image applications both the techniques are applied independently even though the solution to one impacts the solution of the other. Currently medical image segmentation is very complex task due to the lack of sufficient contrast, SNR, and volume averages caused due to the non-uniform magnetic field. The problem is still high with MRI scans rather than other scans due to lack of real boundary. Availability of sophisticated diagnostic methods in the medical domain, demands the fusion of information from different sources for the better analysis. Similarity is enhanced by performing the non-rigid registration, where the local registration highly depends on segmentation of objects. This paper deals with the Atlas-based segmentation technique requires that the given atlas image is to be registered with the target image to find the desired shape segmentation in the target image. This paper discus the joint registration and segmentation process is achieved through highly accurate variational cost effective Distance Regularized Level Set Evolution (DRLSE) method for medical scan images. The key features of this algorithm are, it can accurately converge towards sharp object boundary corners due to forward and backward diffusion and also applied for small and large deformations. It uses less computational cost due to large time steps.

 

Keywords: Medical Image Processing, Image Registration, Segmentation, Joint Registration and Segmentation, Distance Regularized Level Set Evolution, Deformations, Convergence, Computational time.


Full Text:

PDF


DOI: https://doi.org/10.26483/ijarcs.v2i6.887

Refbacks

  • There are currently no refbacks.




Copyright (c) 2016 International Journal of Advanced Research in Computer Science