Ultrasound image despeckling using low rank matrix approximation approach. (September 2017)

• Record Type: Journal Article
• Authors: Mohd Sagheer, Sameera V.; George, Sudhish N.
• Is Part Of: Biomedical signal processing and control. Volume 38(2017)
• Page Start: 236
• Page End: 249
• Publication Date: 2017-09
• Subjects: Ultrasound image -- Speckle noise -- Low-rank recovery -- Denoising; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2017.06.011
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A new despeckling method based on low rank recovery techniques is proposed. The statistical properties of the ultrasound images have been incorporated to enhance the performance of the proposed algorithm. The experiments explain the applicability of proposed method for real medical ultrasound images. The proposed algorithm is shown to have superior performance compared to the state-of-art works existing in the literature. Abstract: The nuclear norm minimization has attracted a great deal of research interest in contemporary years. This paper proposes a low-rank approximation based approach for despeckling of ultrasound images using weighted nuclear norm minimization (WNNM). Two methods are proposed to recover the despeckled image from the speckled data. In the first approach, the homomorphic technique is applied to the speckled ultrasound image followed by low-rank minimisation technique to despeckle the ultrasound image. In the second method, in order to enhance the despeckling capacity, a pre-processing stage is incorporated taking into consideration of the statistical properties of an ultrasound video data. Experimental results on simulated and real ultrasound data prove that the proposed methods outperform the state-of-art works.