%0 Conference Proceedings
%T Structure-Preserving Smoothing of Biomedical Images
%A Debora Gil
%A Aura Hernandez-Sabate
%A Mireia Burnat
%A Steven Jansen
%A Jordi Martinez-Vilalta
%B 13th International Conference on Computer Analysis of Images and Patterns
%D 2009
%V 5702
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-03766-5
%F Debora Gil2009
%O IAM
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=1527), last updated on Thu, 22 May 2014 17:27:49 +0200
%X Smoothing of biomedical images should preserve gray-level transitions between adjacent tissues, while restoring contours consistent with anatomical structures. Anisotropic diffusion operators are based on image appearance discontinuities (either local or contextual) and might fail at weak inter-tissue transitions. Meanwhile, the output of block-wise and morphological operations is prone to present a block structure due to the shape and size of the considered pixel neighborhood. In this contribution, we use differential geometry concepts to define a diffusion operator that restricts to image consistent level-sets. In this manner, the final state is a non-uniform intensity image presenting homogeneous inter-tissue transitions along anatomical structures, while smoothing intra-structure texture. Experiments on different types of medical images (magnetic resonance, computerized tomography) illustrate its benefit on a further process (such as segmentation) of images.
%K non-linear smoothing
%K differential geometry
%K anatomical structures segmentation
%K cardiac magnetic resonance
%K computerized tomography.
%U http://refbase.cvc.uab.es/files/GHB2009.pdf
%U http://dx.doi.org/10.1007/978-3-642-03767-2_52
%P 427-434