Cell Phase Identification Using Fuzzy Gaussian Mixture Models

Dat Tran, T Pham, Xiaobo Zhou

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    2 Citations (Scopus)

    Abstract

    Fuzzy Gaussian mixture modeling method is proposed in this paper for the computerized classification of cell nuclei in different mitotic phases. A mixture of Gaussian distributions was used to represent the cell data in multi-dimensional cell feature space. Gaussian parameters were estimated using fuzzy c-means estimation. The method was tested with the data set containing 379519 cells in 5 phases extracted from real image sequences recorded at every fifteen minutes with a time-lapse fluorescence microscopy. Experimental results have shown that the proposed method is more effective than the Gaussian mixture modeling method
    Original languageEnglish
    Title of host publicationProceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems
    EditorsK.N Ngan, W.C Siu
    Place of PublicationHong Kong
    PublisherIEEE
    Pages465-468
    Number of pages4
    ISBN (Print)0780392663
    DOIs
    Publication statusPublished - 2005
    EventInternational Symposium on Intelligent Signal Processing and Communication Systems - , Hong Kong
    Duration: 13 Dec 200516 Dec 2005

    Conference

    ConferenceInternational Symposium on Intelligent Signal Processing and Communication Systems
    CountryHong Kong
    Period13/12/0516/12/05

    Fingerprint

    Identification (control systems)
    Fluorescence microscopy
    Gaussian distribution
    Cells

    Cite this

    Tran, D., Pham, T., & Zhou, X. (2005). Cell Phase Identification Using Fuzzy Gaussian Mixture Models. In K. N. Ngan, & W. C. Siu (Eds.), Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems (pp. 465-468). Hong Kong: IEEE. https://doi.org/10.1109/ISPACS.2005.1595447
    Tran, Dat ; Pham, T ; Zhou, Xiaobo. / Cell Phase Identification Using Fuzzy Gaussian Mixture Models. Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems. editor / K.N Ngan ; W.C Siu. Hong Kong : IEEE, 2005. pp. 465-468
    @inproceedings{3b0b3ef1f5d641e1aad18c809fd4cb84,
    title = "Cell Phase Identification Using Fuzzy Gaussian Mixture Models",
    abstract = "Fuzzy Gaussian mixture modeling method is proposed in this paper for the computerized classification of cell nuclei in different mitotic phases. A mixture of Gaussian distributions was used to represent the cell data in multi-dimensional cell feature space. Gaussian parameters were estimated using fuzzy c-means estimation. The method was tested with the data set containing 379519 cells in 5 phases extracted from real image sequences recorded at every fifteen minutes with a time-lapse fluorescence microscopy. Experimental results have shown that the proposed method is more effective than the Gaussian mixture modeling method",
    author = "Dat Tran and T Pham and Xiaobo Zhou",
    year = "2005",
    doi = "10.1109/ISPACS.2005.1595447",
    language = "English",
    isbn = "0780392663",
    pages = "465--468",
    editor = "K.N Ngan and W.C Siu",
    booktitle = "Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems",
    publisher = "IEEE",

    }

    Tran, D, Pham, T & Zhou, X 2005, Cell Phase Identification Using Fuzzy Gaussian Mixture Models. in KN Ngan & WC Siu (eds), Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems. IEEE, Hong Kong, pp. 465-468, International Symposium on Intelligent Signal Processing and Communication Systems, Hong Kong, 13/12/05. https://doi.org/10.1109/ISPACS.2005.1595447

    Cell Phase Identification Using Fuzzy Gaussian Mixture Models. / Tran, Dat; Pham, T; Zhou, Xiaobo.

    Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems. ed. / K.N Ngan; W.C Siu. Hong Kong : IEEE, 2005. p. 465-468.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - Cell Phase Identification Using Fuzzy Gaussian Mixture Models

    AU - Tran, Dat

    AU - Pham, T

    AU - Zhou, Xiaobo

    PY - 2005

    Y1 - 2005

    N2 - Fuzzy Gaussian mixture modeling method is proposed in this paper for the computerized classification of cell nuclei in different mitotic phases. A mixture of Gaussian distributions was used to represent the cell data in multi-dimensional cell feature space. Gaussian parameters were estimated using fuzzy c-means estimation. The method was tested with the data set containing 379519 cells in 5 phases extracted from real image sequences recorded at every fifteen minutes with a time-lapse fluorescence microscopy. Experimental results have shown that the proposed method is more effective than the Gaussian mixture modeling method

    AB - Fuzzy Gaussian mixture modeling method is proposed in this paper for the computerized classification of cell nuclei in different mitotic phases. A mixture of Gaussian distributions was used to represent the cell data in multi-dimensional cell feature space. Gaussian parameters were estimated using fuzzy c-means estimation. The method was tested with the data set containing 379519 cells in 5 phases extracted from real image sequences recorded at every fifteen minutes with a time-lapse fluorescence microscopy. Experimental results have shown that the proposed method is more effective than the Gaussian mixture modeling method

    U2 - 10.1109/ISPACS.2005.1595447

    DO - 10.1109/ISPACS.2005.1595447

    M3 - Conference contribution

    SN - 0780392663

    SP - 465

    EP - 468

    BT - Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems

    A2 - Ngan, K.N

    A2 - Siu, W.C

    PB - IEEE

    CY - Hong Kong

    ER -

    Tran D, Pham T, Zhou X. Cell Phase Identification Using Fuzzy Gaussian Mixture Models. In Ngan KN, Siu WC, editors, Proceedings of 2005 International Symposium on Intelligent Signal Processing and Communication Systems. Hong Kong: IEEE. 2005. p. 465-468 https://doi.org/10.1109/ISPACS.2005.1595447