The Nonlinear Tensor Diffusion in Segmentation of Meaningful Biological Structures from Image Sequences of Zebrafish Embryogenesis

Authors:
Olga Drblíková;Karol Mikula;Nadine Peyriéras
Affiliations:
Slovak University of Technology, Bratislava, Slovakia 813 68;Slovak University of Technology, Bratislava, Slovakia 813 68;Institut de Neurobiologie Alfred Fessard, CNRS-DEPSN, Gif sur Yvette, France 91198
Venue:
SSVM '09 Proceedings of the Second International Conference on Scale Space and Variational Methods in Computer Vision
Year:
2009

Citing 3
Cited 1

Coherence-Enhancing Diffusion Filtering

International Journal of Computer Vision
Semi-Implicit Covolume Method in 3D Image Segmentation

SIAM Journal on Scientific Computing
Convergence Analysis of Finite Volume Scheme for Nonlinear Tensor Anisotropic Diffusion in Image Processing

SIAM Journal on Numerical Analysis

Segmentation of 3D cell membrane images by PDE methods and its applications

Computers in Biology and Medicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this contribution we develop a strategy for segmentation of evolving biological structures in image sequences. Our approach is based on combination of nonlinear tensor diffusion image smoothing and subjective surface based image segmentation. Since the fine cell structure would restrain the evolving segmentation function to achieve a shape of meaningful biological structures, we have to smooth properly the images in the sequence. To that goal we apply the nonlinear tensor diffusion which enhances the connectivity of bordering structure lines and smoothes their inner parts. For the numerical implementations we use semi-implicit diamond-cell finite volume methods both for filtering and segmentation. We show application of the method in image segmentation of early stages of zebrafish embryogenesis.