Automatic Extraction of Shape Features for Classification of Leukocytes

Ermai Xie, TM McGinnity, Qingxiang Wu

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    6 Citations (Scopus)

    Abstract

    Microscope-based white blood cell classification plays an important role in diagnosing disease. The number of segments of nucleus and the shape of segments of nucleus are regarded as important features. Since it is difficult to automatically extract these features from a blood smeared image, they have not been used in the current automatic classifiers based on smeared images. In this paper, an approach based on the Poisson equation is proposed to extract the number of segments of nucleus in a more straightforward manner, and inner distances are used to represent the shape features of the nucleus segments. The experimental results show that the proposed approaches can extract the features efficiently. These important features can be added to the input feature set of neural networks or other classifiers to improve classification results of leukocytes in a blood smeared image.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Place of PublicationUSA
    Pages220-224
    Number of pages5
    DOIs
    Publication statusPublished - 23 Oct 2010
    EventThe 2010 International Conference on Artificial Intelligence and Computational Intelligence (AICI'10) -
    Duration: 23 Oct 2010 → …

    Conference

    ConferenceThe 2010 International Conference on Artificial Intelligence and Computational Intelligence (AICI'10)
    Period23/10/10 → …

    Fingerprint

    Blood
    Classifiers
    Poisson equation
    Microscopes
    Cells
    Neural networks

    Cite this

    Xie, Ermai ; McGinnity, TM ; Wu, Qingxiang. / Automatic Extraction of Shape Features for Classification of Leukocytes. Unknown Host Publication. USA, 2010. pp. 220-224
    @inproceedings{03f85a20146f471aac2da97f750da057,
    title = "Automatic Extraction of Shape Features for Classification of Leukocytes",
    abstract = "Microscope-based white blood cell classification plays an important role in diagnosing disease. The number of segments of nucleus and the shape of segments of nucleus are regarded as important features. Since it is difficult to automatically extract these features from a blood smeared image, they have not been used in the current automatic classifiers based on smeared images. In this paper, an approach based on the Poisson equation is proposed to extract the number of segments of nucleus in a more straightforward manner, and inner distances are used to represent the shape features of the nucleus segments. The experimental results show that the proposed approaches can extract the features efficiently. These important features can be added to the input feature set of neural networks or other classifiers to improve classification results of leukocytes in a blood smeared image.",
    author = "Ermai Xie and TM McGinnity and Qingxiang Wu",
    year = "2010",
    month = "10",
    day = "23",
    doi = "10.1109/AICI.2010.168",
    language = "English",
    isbn = "978-1-4244-8432-4",
    pages = "220--224",
    booktitle = "Unknown Host Publication",

    }

    Xie, E, McGinnity, TM & Wu, Q 2010, Automatic Extraction of Shape Features for Classification of Leukocytes. in Unknown Host Publication. USA, pp. 220-224, The 2010 International Conference on Artificial Intelligence and Computational Intelligence (AICI'10), 23/10/10. https://doi.org/10.1109/AICI.2010.168

    Automatic Extraction of Shape Features for Classification of Leukocytes. / Xie, Ermai; McGinnity, TM; Wu, Qingxiang.

    Unknown Host Publication. USA, 2010. p. 220-224.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    TY - GEN

    T1 - Automatic Extraction of Shape Features for Classification of Leukocytes

    AU - Xie, Ermai

    AU - McGinnity, TM

    AU - Wu, Qingxiang

    PY - 2010/10/23

    Y1 - 2010/10/23

    N2 - Microscope-based white blood cell classification plays an important role in diagnosing disease. The number of segments of nucleus and the shape of segments of nucleus are regarded as important features. Since it is difficult to automatically extract these features from a blood smeared image, they have not been used in the current automatic classifiers based on smeared images. In this paper, an approach based on the Poisson equation is proposed to extract the number of segments of nucleus in a more straightforward manner, and inner distances are used to represent the shape features of the nucleus segments. The experimental results show that the proposed approaches can extract the features efficiently. These important features can be added to the input feature set of neural networks or other classifiers to improve classification results of leukocytes in a blood smeared image.

    AB - Microscope-based white blood cell classification plays an important role in diagnosing disease. The number of segments of nucleus and the shape of segments of nucleus are regarded as important features. Since it is difficult to automatically extract these features from a blood smeared image, they have not been used in the current automatic classifiers based on smeared images. In this paper, an approach based on the Poisson equation is proposed to extract the number of segments of nucleus in a more straightforward manner, and inner distances are used to represent the shape features of the nucleus segments. The experimental results show that the proposed approaches can extract the features efficiently. These important features can be added to the input feature set of neural networks or other classifiers to improve classification results of leukocytes in a blood smeared image.

    U2 - 10.1109/AICI.2010.168

    DO - 10.1109/AICI.2010.168

    M3 - Conference contribution

    SN - 978-1-4244-8432-4

    SP - 220

    EP - 224

    BT - Unknown Host Publication

    CY - USA

    ER -