Open AccessDenoising of 3D magnetic resonance images using non-local PCA and Transform-Domain Filter
Author(s) -
Laraib Kanwal
Publication year - 2017
Publication title -
lahore garrison university research journal of computer science and information technology
Language(s) - English
Resource type - Journals
eISSN - 2521-0122
pISSN - 2519-7991
DOI - 10.54692/lgurjcsit.2017.01018
Subject(s) - noise reduction , wiener filter , principal component analysis , artificial intelligence , filter (signal processing) , thresholding , pattern recognition (psychology) , matlab , noise (video) , computer science , non local means , computer vision , mathematics , image (mathematics) , image denoising , operating system
The Magnetic Resonance Imaging (MRI) technologyused in clinical diagnosis demands high Peak Signal-to-Noise ratio(PSNR) and improved resolution for accurate analysis and treatmentmonitoring. However, MRI data is often corrupted by random noisewhich degrades the quality of Magnetic Resonance (MR) images.Denoising is a paramount challenge as removing noise causesreduction in the fine details of MRI images. We have developed anovel algorithm which employs Principal Component Analysis(PCA) decomposition and Wiener filtering. We have proposed a twostage approach. In first stage, non-local PCA thresholding is appliedon noisy image and second stage uses Wiener filter over this filteredimage. Our algorithm is implemented using MATLAB andperformance is measured via PSNR. The proposed approach hasalso been compared with related state-of-art methods. Moreover, wepresent both qualitative and quantitative results which prove thatproposed algorithm gives superior denoising performance.