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 single-layer 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, i.e., 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.

Highlights

  • M EDICAL imaging (MI) attributes to procedures and methods employed to generate images of different sections of the human body for symptomatic and treatment objectives within digital health

  • wireless capsule endoscopy (WCE) or colonoscopy procedures examine the gastrointestinal tract of the human body and takes 8 hours for the whole examination generating more than 55,000 images

  • The result of layer analysis, sparsity averaging model, reweighted analysis, and resolutions effect are presented to show the analysis of RGB-sparsity averaging reweighted analysis (SARA) performances

Read more

Summary

INTRODUCTION

M EDICAL imaging (MI) attributes to procedures and methods employed to generate images of different sections of the human body for symptomatic and treatment objectives within digital health. Medical data such as WCE images are taken at a specific frame rate followed by the transmission to a receiver connected to a human body This process is hectic and time-consuming and can suffer JPEG compression and channel noises while transmission. MI techniques such as WCE and colonoscopy process where a huge number of images are produced under variant spatial positions within the human body having different illuminations leading to data handling harder and time-consuming. An extensive study was performed for WCE and colonoscopy data, in which the combination of an average sparsity model, BPDN reconstruction method, and improve version of BPDN with reweighted analysis [3]. The proposed RGB-SARA for WCE images is based on the spread spectrum sampling method, sparsity averaging, basis pursuit denoise reconstruction method, and reweighted analysis. Performance analysis of RGB-SARA in colored medical images with performance metrics, i.e., signal to noise ratio (SNR), average SNR (ASNR), structural similarity index (SSIM), and processing time

PROPOSED RGB-SARA
CS BY SPREAD SPECTRUM
RESULTS
CONCLUSION
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call