Affine Registration of the Magnitude and Phase Reconstructed MR Image


Author (s):

  1. A M. Kothari, Atmiya inst of science and technology, Rajkot, Gujarat, INDIA
  2. Poorvi H. Patel, Atmiya Institute of Tech. and Science, Rajkot, Gujarat, INDIA, phpatel@aits.edu.in
  3. Vandip J. Patel, Takshashila College of Engineering & Technology, Rajkot, Gujarat, INDIA

Abstract:

The two parameters which plays important role in MRI (magnetic resonance imaging), acquired by various imaging modalities are feature extraction and object recognition. These operations will become difficult if the images are corrupted with noise. Denoising is a challenging problem in MRI (acquired as a complex signal ) as the magnitude and phase error both are to be corrected having a signal dependent random noise distribution changing each pixel value in MR image and it is very important for the diagnosis and recognition of cancer, tumor, and tissue properties. After getting denoised MRI, we are registering the multiple MR Images resulting from the unintentional movement or misalignments between consecutive sequences of image. In this paper, we are representing an algorithm for MRI denoising in which we are using non-linear adaptive gradient smoothing for amplitude reconstruction and used FFT and non-linear anisotropic diffusion for phase reconstruction and Affine transformation for registering the MR images. We are using the PSNR (Peak signal to noise ration), MSE (Mean square error) and RMSE (Root mean square error) as performance matrices to measure the quality of denoised MRI .The final result shows that this method is effectively removing the noise while preserving the edge and fine information in the images and by collaging the images through affine registration gives accurate diagnosis results.

No of downloads: 16