Author : Vidyashree 1
Date of Publication :24th May 2018
Abstract: Magnetic Resonance Imaging (MRI) is a medical imaging technology that is used for diagnostic imaging of a wide range of diseases. Image reconstruction is much concentrated with the contrast of possibly the same value as the original. This paper presents the comparison of KarhunenLoeve Transform (KLT) and Walsh Hadamard Transform (WHT) for MR Image reconstruction. The MR image used is grayscale. The original image is reconstructed using Inverse Transform. The performance of each transform is measured by evaluating Peak Signal to Noise Ratio (PSNR), Structural Similarity Index(SSIM) and Mean Square Error(MSE) for the reconstructed gray scale of pixel size 256× 256. The quality measurement for these two transforms is measured in terms of MSE, PSNR and SSIM values. The comparison of PSNR, SSIM, MSE values between the two transforms proves that the reconstructed image using WHT transform has better quality than the KLT transform
Reference :
-
- Baker, Christopher Adams, "Investigation of Sparsifying Transforms in Compressed Sensing for Magnetic Resonance Imaging with Fasttestcs “The University of Wisconsin-Milwaukee Thesis and Dissertations, 2016.
- Prof. W.S. Besbas, Prof. M.A. Artemi, R.M. Suliman, M.M. AL_Rjebi,” Content Based Face Image Retrieval in Walsh Hadamard Transform (WHT) Domain vol. 86, 2008, pp.32-50.
- Mahmood Qureshi, Muhammad Kaleem and Hammad Omer,” Journey through k-space”, Biomedical Research vol. 28, 2017, pp.1618-1623.
- Alain hore and Djemel Ziou,”Image quality metrics:PSNR vs.SSIM”,international conference on Pattern Recognition, 2010,pp.2366-2369
- Kai Tobias and Mainz, “Advanced Methods for Radial Data Sampling in Magnetic Resonance Imaging”, ISMRM Workshop on Non-Cartesian MRI Sedona vol. 17, 2008, pp. 234-246.
- Yanchun Zhu “K-Space Trajectory Development”, IEEE International Conference on Medical Imaging Physics and Engineering vol. 9, 2013, pp. 356-360