A REVIEW PAPER ON DENOISING MULTI - CHANNEL IMAGES IN PARALLEL MRI BY LOW RANK MATRIX DECOMPOSITION AND BACTERIAL FORAGING ALGORITHM
Journal: International Journal of Engineering Sciences & Research Technology (IJESRT) (Vol.4, No. 12)Publication Date: 2015-12-30
Authors : Tulika Saggar; R.C. Gangwar; IITR;
Page : 563-567
Keywords : enoising; Low rank matrix decomposition; Multi - channel coil; parallel MRI (pMRI); Bac terial Foraging Algorithm (BFA);
Abstract
Parallel magnetic resonance imaging has emerged as an effective means for high - speed imaging in various applications. The reconstruction of parallel magnetic resonance imaging (pMRI) [1] data can be a computationally demanding task. Signal - to - noise ratio is also a concern, especially in high - resolution imaging. We present a patch - wise Denoising method for pM RI by exploiting the rank deficiency of multichannel images. For each processed patch and pixel, similar patches are searched with pixel in spatial domain and throughout all coil elements, and arranged in appropriate matrix forms. Then, noise and aliasing artifacts are removed from the structured matrix by applying sparse and low rank matrix decomposition method with Bacterial Foraging Algorithm (BFA). The proposed method validates using both phantom and in vivo brain data sets, producing encouraging result s. Specifically, the method can effectively remove both noise and residual aliasing artifact from pMRI reconstructed noisy images, and produce higher peak signal noise rate (PSNR) and structural similarity index matrix (SSIM) than other state - of - the - art De noising methods [3].The Denoising of pMRI is implemented using Image Processing Toolbox. This work test and found suitable for its purpose. For the implementation of this proposed work we use the Matlab software.
Other Latest Articles
- A REVIEW PAPER ON ON THE DESIGN OPTIMIZATION FOR ENHANCED FACE RECOGNITION
- SIMULATION STUDIES ON SOLAR PHOTOVOLTAIC MODULE FOR DIFFERENT TEMPERATURE AND WAVE LENGTH
- EFFECTIVE RADAR TRACKING USING ADAPTIVE KALMAN FILTER
- A CROSSLAYER PROTOCOL DESIGN APPROACH BETWEEN PHY AND MAC LAYER FOR COGNITIVE RADIO NETWORKS
- REVIEW ON METHODS TO REDUCE DELAMINATION IN COMPOSITE LAMINATE
Last modified: 2015-12-18 21:34:06