Abstract

One of today's motivating medical image processing problem is registration. Medical images acquired from different modalities give rise to a practical problem in image registration. For many years, mutual information has been utilized as a similarity criterion for registration. Therefore, it is believed to be the state-of-the-art in this field. Nonetheless, it is understood to be non-convex and possess many local maxima. To overcome this problem, we introduce a novel evolutionary rigid body docking (ERBD) algorithm for medical image registration. Here, the ligand is taken as the non-aligned (target) image (to be registered) and protein as the reference image. The alignment of the target image is changed as per the optimal configuration. This paper introduces a firsthand objective (fitness) function for finding optimal configurations. Genetic algorithm (GA) is used to optimize the fitness function. The proposed method is useful for recovery of rotation and translation parameters. Different image data formats like magnetic resonance image (MRI), computed tomography (CT) and positron emission tomography (PET) images from Retrospective Image Registration Evaluation (RIRE) project are used to demonstrate the effectiveness of our proposed method. Experimental results are presented to reveal the fact that our approach seems to be efficient.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.