Computational & Technology Resources
an online resource for computational,
engineering & technology publications
PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON PARALLEL, DISTRIBUTED, GPU AND CLOUD COMPUTING FOR ENGINEERING
Edited by: P. Iványi and B.H.V. Topping
Parallel hybrid algorithm for speckle noise reduction in ultrasound images
J. Arnal and I. Mayzel
Department of Computer Science and Artificial Intelligence, University of Alicante, Spain
J. Arnal, I. Mayzel, "Parallel hybrid algorithm for speckle noise reduction in ultrasound images", in P. Iványi, B.H.V. Topping, (Editors), "Proceedings of the Sixth International Conference on Parallel, Distributed, GPU and Cloud Computing for Engineering", Civil-Comp Press, Stirlingshire, UK, Paper 27, 2019. doi:10.4203/ccp.112.27
Keywords: parallel processing, OpenMP, MPI, digital image processing, speckle noise, ultrasound imaging.
Speckle noise appears as a granular pattern in ultrasound images due to the coherent constructive and destructive interferences of scattering echoes reflected by the microscopic dispersion of the tissue. Therefore, despeckling through digital image processing should improve the quality of the image and possibly the diagnostic potential of medical ultrasound images. In this paper, we propose a novel parallel hybrid despeckling algorithm by combining in an efficient manner the advantages of several denoising filters using local and non-local information. The parallel algorithm is implemented on multicore platforms using OpenMP. The parallel implementation is compared to the sequential one, obtaining significative values of speed-up.
purchase the full-text of this paper (price £22)