A novel coarse-to-fine adaptation segmentation approach for cellular image analysis

Authors:
Kai Zhang;Hongkai Xiong;Lei Yang;Xiaobo Zhou
Affiliations:
Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, P.R. China;Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, P.R. China;Institute of Image Communication and Information Processing, Shanghai Jiao Tong University, Shanghai, P.R. China;Center for Bioinformatics, Harvard Center for Neurodegeneration and Repair, Harvard Medical School
Venue:
MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Year:
2007

Citing 5
Cited 1

Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations

IEEE Transactions on Pattern Analysis and Machine Intelligence
The watershed transform: definitions, algorithms and parallelization strategies

Fundamenta Informaticae - Special issue on mathematical morphology
Snakes on the Watershed

IEEE Transactions on Pattern Analysis and Machine Intelligence - Graph Algorithms and Computer Vision
Watersnakes: Energy-Driven Watershed Segmentation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Application of Active Contour Models in Medical Image Segmentation

ITCC '04 Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC'04) Volume 2 - Volume 2

Segmentation and cell tracking of breast cancer cells

ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

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.