Optimum Regularized Joint Registration and Segmentation Method for Medical Brain Images
Main Article Content
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.
Â
Keywords: Medical Image Processing, Image Registration, Segmentation, Joint Registration and Segmentation, Distance Regularized Level Set Evolution, Deformations, Convergence, Computational time.
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.