DocumentCode :
867294
Title :
Automatic Tracking of Escherichia Coli in Phase-Contrast Microscopy Video
Author :
Xie, Jun ; Khan, Shahid ; Shah, Mubarak
Author_Institution :
Janelia Farm Res. Campus, Howard Hughes Med. Inst., Ashburn, VA
Volume :
56
Issue :
2
fYear :
2009
Firstpage :
390
Lastpage :
399
Abstract :
In this paper, we present an automatic method for estimating the trajectories of Escherichia coli bacteria from in vivo phase-contrast microscopy. To address the low-contrast boundaries in cellular images, an adaptive kernel-based technique is applied to detect cells in each frame. In addition to intensity features, region homogeneity measure and class uncertainty are also applied in this detection technique. To track cells with complex motion, a novel matching gain measure is introduced to cope with the challenges, particularly the presence of low-contrast boundary, the variations of appearance, and the frequent overlapping and occlusion. For multicell tracking over time, an optimal matching strategy is introduced to improve the handling of cell collision and broken trajectories. The results of successful tracking of Escherichia coli from various phase-contrast sequences are reported and compared with manually determined trajectories, as well as those obtained from existing tracking schemes. The stability of the algorithm with different parameter values is also analyzed and discussed.
Keywords :
biological techniques; cell motility; microorganisms; optical microscopy; adaptive kernel; automatic Escherichia coli tracking; bacteria; cell detection; class uncertainty; multicell tracking; phase-contrast microscopy video; region homogeneity; Gain measurement; Measurement uncertainty; Microorganisms; Microscopy; Motion measurement; Optimal matching; Particle measurements; Phase estimation; Tracking; Trajectory; Escherichia coli; microscopy video processing; tracking; Algorithms; Artificial Intelligence; Chemotaxis; Entropy; Escherichia coli; Image Processing, Computer-Assisted; Microscopy, Phase-Contrast; Microscopy, Video; Pattern Recognition, Automated;
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/TBME.2008.2005956
Filename :
4627431
Link To Document :
بازگشت