Microscopic cell segmentation by parallel detection and fusion algorithm

Automatic cell segmentation and tracking in optical microscope images plays a very important role in the study the behaviour of lymphocytes. The variable image contrasts, and especially variable cell densities are major factors to affect the successful cell detection rates. In this paper, two inner and outer cell contours edge detection based cell segmentation algorithms are proposed and used in parallel. Then a detection fusion algorithm is proposed to combine the two detection results and increase the probability of cell detection. Experimental results are used to demonstrate that these algorithms are robust to variations in both image contrast and cell densities. We show that the proposed fusion algorithm can increase cell detection rate significantly to above 90% with the false detection rate about 5%.

[1]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[2]  Scott T. Acton,et al.  Rolling Leukocyte Detection based on Teardrop Shape and the Gradient Inverse Coefficient of Variation , 2006, International Conference on Medical Information Visualisation - BioMedical Visualisation (MedVis'06).

[3]  John F Markham,et al.  Measuring lymphocyte proliferation, survival and differentiation using CFSE time-series data , 2007, Nature Protocols.

[4]  Alina N. Moga,et al.  An efficient watershed algorithm based on connected components , 2000, Pattern Recognit..

[5]  Jaclyn Nascimento,et al.  Real‐time automated tracking and trapping system for sperm , 2006, Microscopy research and technique.

[6]  Scott E Fraser,et al.  Time‐lapse tracing of mitotic cell divisions in the early Xenopus embryo using microscopic MRI , 2006, Developmental dynamics : an official publication of the American Association of Anatomists.

[7]  Robin Callard,et al.  Modeling T‐ and B‐cell growth and differentiation , 2007, Immunological reviews.

[8]  Andrzej Ciereszko,et al.  Polymorphism of transferrin of carp seminal plasma: relationship to blood transferrin and sperm motility characteristics. , 2007, Comparative biochemistry and physiology. Part B, Biochemistry & molecular biology.

[9]  P. Hodgkin,et al.  A model of immune regulation as a consequence of randomized lymphocyte division and death times , 2007, Proceedings of the National Academy of Sciences.

[10]  Hong Yan,et al.  Recognition of broken and noisy handwritten characters using statistical methods based on a broken-character-mending algorithm , 1997 .

[11]  Mohamed Cheriet,et al.  Automatic segmentation of cells from microscopic imagery using ellipse detection , 2007 .

[12]  Xiaobo Zhou,et al.  Automated segmentation, classification, and tracking of cancer cell nuclei in time-lapse microscopy , 2006, IEEE Transactions on Biomedical Engineering.

[13]  Scott E Fraser,et al.  New tools for visualization and analysis of morphogenesis in spherical embryos , 2005, Developmental dynamics : an official publication of the American Association of Anatomists.

[14]  Scott T. Acton,et al.  Active contours for cell tracking , 2002, Proceedings Fifth IEEE Southwest Symposium on Image Analysis and Interpretation.

[15]  Scott T. Acton,et al.  Data acceptance for automated leukocyte tracking through segmentation of spatiotemporal images , 2005, IEEE Transactions on Biomedical Engineering.

[16]  R. Wollman,et al.  High throughput microscopy: from raw images to discoveries , 2007, Journal of Cell Science.

[17]  Gunilla Borgefors,et al.  Distance transformations in digital images , 1986, Comput. Vis. Graph. Image Process..

[18]  Gang Dong,et al.  Automated leukocyte detection in VIVO , 2004, Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004..

[19]  Xiaobo Zhou,et al.  Informatics challenges of high-throughput microscopy , 2006, IEEE Signal Processing Magazine.