Registration of 3D Medical Images using Parallel Affine Transform

Pulak Mondal, Pradyut K. Biswal, and Swapna Banerjee


Biomedical image processing, Computed tomography, Image registration, Affine transform


Image registration is the process of aligning two images. In biomedical imaging systems, the image is acquired using different modalities. To compare the images acquired using different methods, image registration is used. In image registration process, affine transform is one of the important operation. Affine transform is applied iteratively during registration. Also, for the analysis of the interior of an organ is critical to detect eventual diseases or for surgical operations. So, to get a better view of the organs in 3D coordinate system, the affine transform (AT) has to be applied on the acquired volumetric image. The faster implementation of the affine transform will help in real time registration of the images. The affine transform consists of four basic operations viz. rotation, shearing, scaling and translation. In this paper, we have proposed a modified algorithm for applying the transform on 3D images. This algorithm exploits the symmetry of the voxel location to obtain the affine transform of a volumetric image. This helps in reducing the computation in terms of number of matrix multiplication almost by one fourth compared to the conventional algorithm and increases the speed of the execution. The proposed algorithm is simulated using MATLAB. The algorithm is much faster compared to the conventional method without deteriorating the quality of the 3D image.

Important Links:

Go Back