A Novel Coarse-to-Fine Adaptation Segmentation Approach for Cellular Image Analysis
Lists
Only you see this
Abstract
Cellular image content analysis is one of the most important aspects of the cellular research and often requires collecting a great amount of statistical information and phenomena. Automated segmentation of time-lapse images gradually becomes the key problem in cellular image analysis. To address fuzzy, irregular, and ruffling cell boundaries in time-lapse cellular images, this paper introduces a hierarchical coarse-to-fine approach which is composed of iteration-dependent adaptation procedures with high-level interpretation: initial segmentation, adaptive processing, and refined segmentation. The iteration-dependent adaptation lies in that the adaptive processing and the refined segmentation be deliberately designed without a fixed order and a uniform associated iteration number, to connect coarse segmentation and refined segmentation for locally progressive approximation. The initial segmentation could avoid over-segmentation from watershed transform and converge to some features using a priori information. Experimental results on cellular images with spurious branches, arbitrary gaps, low contrast boundaries and low signal-to-noise ratio, show that the proposed approach provides a close matching to the manual cognition and overcomes several common drawbacks from other existing methods applied on cell migration. The procedure configuration of the proposed approach has a certain potential to serve as a biomedical image content analysis tool.
BibTeX
@inproceedings{zhang2007novel,
author = {Kai Zhang and Hongkai Xiong and Lei Yang and Xiaobo Zhou},
title = {{A Novel Coarse-to-Fine Adaptation Segmentation Approach for Cellular Image Analysis}},
booktitle = {MMM},
year = {2007},
doi = {10.1007/978-3-540-69423-6\_74},
}Loading related content...