MRI denoising using BM3D equipped with noise invalidation denoising technique and VST for improved contrast

Abstract

Denoising of medical scanned images such as X-ray, MRI etc. is important stage in the medical use. To remove the noise from “magnetic resonance images” (MRI) is the attention of researchers to generate the MR images with high “signal-to-noise ratio” as well as with high spatial resolution. In this denoising technique, block-matching and 3-dimensional filtering (BM3D) method is used to denoise the MR images. Main steps used in BM3D are grouping, 3-dimensional discrete wavelet transformation and wavelet shrinkage. In the proposed method, noise invalidation denoising technique (NIDe) is used rather than hard thresholding. NIDe gives the threshold value automatically based on the data and noise characteristics and threshold value changes according to the characteristics of data i.e. wavelet coefficient of image. Before denoising MR images, variance stabilization transform (VST) discard the noise variance dependency of the MRI intensities. Combining block-matching and 3-dimensional filtering technique and VST make able the use of the BM3D technique for Magnetic Resonance Image denoising. After BM3D i.e. final denoised MR image, “contrast limited adaptive histogram equalization” technique is applied to increase the contrast of MR images which are denoised. Performance metrics such as “Peak Signal to Noise ratio”, “Root Mean Square Error”, “Mutual Information”, “Edge Entropy” and “Structural Similarity Index Method” are found out for “T1 weighted”, “T2 weighted” and “PD weighted” magnetic resonance images.