RGB-Based Compressed Medical Imaging Using Sparsity Averaging Reweighted Analysis for Wireless Capsule Endoscopy Images

Abstract

Compressed medical imaging (CMI) is a medical image sampling process with several samples lower than the Nyquist-Shannon sampling theorem for efficient image sampling; therefore, speeds up the processing time of medical applications. In comparison to previous approaches focusing on singlelayer images analysis, this paper proposes CMI using RGB-based sparsity averaging with reweighted analysis (RGB-SARA). The proposed RGB-SARA method is based on the spread spectrum (SS) sampling method, sparsity averaging (SA), basis pursuit denoise (BPDN) reconstruction method, and reweighted analysis (RA). The CS-based SS sampling method compresses each sample in the specific RGB layer followed by SA and BPDN with RA as a sparsity basis and to enhance the performance of CMI reconstruction, respectively. A detailed results analysis is presented in terms of signal-to-noise ratio (SNR), average SNR (ASNR), structural similarity index (SSIM), and processing time demonstrating the efficacy of the proposed RGB-SARA over conventional CMI (Haar, Daubechies 8 (Db8), and curvelet). A successful demonstration is presented proving that the proposed RGB-SARA is a potential of a new compression method for medical images with high visual quality and less processing time.INDEX TERMS Compressed imaging, RGB-based, reweighted analysis, sparsity averaging, wireless capsule endoscopy.

Compressive Sampling of Color Retinal Image Using Spread Spectrum Fourier Sampling and Total Variant

“…1 shows and example of medical imaging where colonoscopy, endoscopy and iris/retinal image are considered as color medical imaging. An initial CMI framework in color medical images that considers RGB format was proposed using sparsity averaging (SA) reweighted analysis (RA) and referred to as RGB-SARA [33]. In addition, the CMI of color iris/retinal images using basis pursuit (BP) with SA (RGB-BPSA) [34] was proposed.…”

“…Throughout this paper, novel TV-based reconstruction method for RGB color retinal images (RGB-TV) is proposed. Different from RGB-SARA [33] and M-BRA [31], RA is not considered in this paper because RA process requires long processing time. This paper aims both processing time and visual quality improvement of the CMI.…”