RT info:eu-repo/semantics/article T1 Anisotropic Diffusion Filter with Memory based on Speckle Statistics for Ultrasound Images A1 Ramos Llordén, Gabriel A1 Vegas Sánchez-Ferrero, Gonzalo A1 Martín Fernández, Marcos Antonio A1 Alberola López, Carlos A1 Aja Fernández, Santiago K1 Ultrasound Imaging K1 Speckle Filter K1 Anisotropic Diffusion K1 Memory Equations K1 Volterra Equations AB Ultrasound imaging exhibits considerable difficulties for medical visual inspection and for the development of automaticanalysis methods due to speckle, which negatively affects the perception of tissue boundaries and the performance of automaticsegmentation methods. With the aim of alleviating the effect of speckle, many filtering techniques are usually considered as apreprocessing step prior to automatic analysis methods or visual inspection. Most of the state-of-the-art filters try to reduce thespeckle effect without considering its relevance for the characterization of tissue nature. However, the speckle phenomenon is theinherent response of echo signals in tissues and can provide important features for clinical purposes. This loss of informationis even magnified due to the iterative process of some speckle filters, e.g., diffusion filters, which tend to produce over-filteringbecause of the progressive loss of relevant information for diagnostic purposes during the diffusion process. In this work, wepropose an anisotropic diffusion filter with a probabilistic-driven memory mechanism to overcome the over-filtering problem byfollowing a tissue selective philosophy. Specifically, we formulate the memory mechanism as a delay differential equation forthe diffusion tensor whose behavior depends on the statistics of the tissues, by accelerating the diffusion process in meaninglessregions and including the memory effect in regions where relevant details should be preserved. Results both in synthetic and realUS images support the inclusion of the probabilistic memory mechanism for maintaining clinical relevant structures, which areremoved by the state-of-the-art filters. YR 2015 FD 2015 LK http://uvadoc.uva.es/handle/10324/15167 UL http://uvadoc.uva.es/handle/10324/15167 LA spa NO IEEE Trans. on Image Processing, Vol. 24, No. 1, Enero 2015 DS UVaDOC RD 29-mar-2024