Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/3229
Title: | Single-Image Bayesian Restoration and Multi-Image Super-Resolution Restoration for B-Mode Ultrasound Using an Accurate System Model Involving Correlated Nature of the Speckle Noise | Authors: | Özkul, Mine Cüneyitoğlu Mumcuoğlu, Ünal Erkan Sancak, İbrahim Tanzer |
Keywords: | image restoration deconvolution super-resolution speckle reduction correlated noise Bayesian |
Publisher: | SAGE PUBLICATIONS INC | Source: | Cüneyitoğlu Özkul, M., Mumcuoğlu, Ü. E., & Sancak, İ. T. (2019). Single-image Bayesian Restoration and Multi-image Super-resolution Restoration for B-mode Ultrasound Using an Accurate System Model Involving Correlated Nature of the Speckle Noise. Ultrasonic imaging, 0161734619865961. | Abstract: | B-mode ultrasound is an essential part of radiological examinations due to its low cost, safety, and portability, but has the drawbacks of the speckle noise and output of most systems is two-dimensional (2D) cross sections. Image restoration techniques, using mathematical models for image degradation and noise, can be used to boost resolution (deconvolution) as well as to reduce the speckle. In this study, new single-image Bayesian restoration (BR) and multi-image super-resolution restoration (BSRR) methods are proposed for in-plane B-mode ultrasound images. The spatially correlated nature of the speckle was modeled, allowing for examination of two different models for BR and BSRR for uncorrelated Gaussian (BR-UG, BSRR-UG) and correlated Gaussian (BR-CG, BSRR-CG). The performances of these models were compared with common image restoration methods (Wiener filter, bilateral filtering, and anisotropic diffusion). Well-recognized metrics (peak signal-to-noise ratio, contrast-to-noise ratio, and normalized information density) were used for algorithm free-parameter estimation and objective evaluations. The methods were tested using superficial tissue (2D scan data collected from volunteers, tissue-mimicking resolutions, and breast phantoms). Improvement in image quality was assessed by experts using visual grading analysis. In general, BSRR-CG performed better than all other methods. A potential downside of BSRR-CG is increased computation time, which can be addressed by the use of high-performance graphics processing units (GPUs). | URI: | https://journals.sagepub.com/doi/full/10.1177/0161734619865961?url_ver=Z39.88-2003&rfr_id=ori:rid:crossref.org&rfr_dat=cr_pub%3dpubmed https://hdl.handle.net/20.500.11851/3229 |
ISSN: | 0161-7346 |
Appears in Collections: | Dahili Tıp Bilimleri Bölümü / Department of Internal Medical Sciences PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
Show full item record
CORE Recommender
SCOPUSTM
Citations
2
checked on Dec 21, 2024
WEB OF SCIENCETM
Citations
6
checked on Dec 21, 2024
Page view(s)
86
checked on Dec 16, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.