2014 | OriginalPaper | Chapter
Fast Anisotropic Speckle Filter for Ultrasound Medical Images
Authors : G. Ramos-Llordén, G. Vegas-Sánchez-Ferrero, S. Aja-Fernández, M. Martín-Fernández, C. Alberola-López
Published in: XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013
Publisher: Springer International Publishing
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Low contrast in ultrasound images caused by the granular pattern (speckle) makes difficult computational analysis and diagnosis. Thus, speckle filtering is a common step before computed automatic analysis. However, speckle depends on the inner echo-morphology of tissue and it should be removed without over-filtering relevant details for diagnostic purposes. Some methods were proposed to preserve important details by means of anisotropic diffusion schemes. However, they require to solve an evolutionary partial differential equation, which needs considerable computation time thatmakes this kind of filters impractical for real-time scenarios. Additionally, there is no rational criteria to select the optimal stop criteria. Some other detail preserving filters are based in the Non-Local means philosophy, however they involves an even higher computational cost.
In this work we propose a fast anisotropic speckle filter which makes use of speckle statistics to preserve the tissue echomorphology while the speckle is properly removed from regions without clinical relevant features, such as blood in heart cavities. The implementation is based on an anisotropic and spatially variant Gaussian kernel whose covariance depends on structural information of tissues. The proposed implementation is computationally efficient, where no stop criterion is needed. Results confirmed the low computation cost compared to diffusion and Non-Local means based filters.Quantitative evaluation with synthetic data also confirmed the better performance of the filter compared to other state of the art methods.