Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears

Roopa B. Hegde, Keerthana Prasad, Harishchandra Hebbar, Brij Mohan Kumar Singh

    Research output: Contribution to journalArticle

    Abstract

    Peripheral blood smear analysis is a gold-standard method used in laboratories to diagnose many hematological disorders. Leukocyte analysis helps in monitoring and identifying health status of a person. Segmentation is an important step in the process of automation of analysis which would reduce the burden on hematologists and make the process simpler. The segmentation of leukocytes is a challenging task due to variations in appearance of cells across the slide. In the proposed study, an automated method to detect nuclei and to extract leukocytes from peripheral blood smear images with color and illumination variations is presented. Arithmetic and morphological operations are used for nuclei detection and active contours method is for leukocyte detection. The results demonstrate that the proposed method detects nuclei and leukocytes with Dice score of 0.97 and 0.96 respectively. The overall sensitivity of the method is around 96%.

    Original languageEnglish
    Article number114
    JournalJournal of Medical Systems
    Volume43
    Issue number5
    DOIs
    Publication statusPublished - 01-05-2019

    Fingerprint

    Image processing
    Leukocytes
    Blood
    Automation
    Lighting
    Gold
    Health
    Color
    Monitoring
    Clinical Laboratory Techniques
    Health Status

    All Science Journal Classification (ASJC) codes

    • Medicine (miscellaneous)
    • Information Systems
    • Health Informatics
    • Health Information Management

    Cite this

    Hegde, Roopa B. ; Prasad, Keerthana ; Hebbar, Harishchandra ; Singh, Brij Mohan Kumar. / Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears. In: Journal of Medical Systems. 2019 ; Vol. 43, No. 5.
    @article{1e2712a737a44efd8f3e9f1e5d8439f0,
    title = "Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears",
    abstract = "Peripheral blood smear analysis is a gold-standard method used in laboratories to diagnose many hematological disorders. Leukocyte analysis helps in monitoring and identifying health status of a person. Segmentation is an important step in the process of automation of analysis which would reduce the burden on hematologists and make the process simpler. The segmentation of leukocytes is a challenging task due to variations in appearance of cells across the slide. In the proposed study, an automated method to detect nuclei and to extract leukocytes from peripheral blood smear images with color and illumination variations is presented. Arithmetic and morphological operations are used for nuclei detection and active contours method is for leukocyte detection. The results demonstrate that the proposed method detects nuclei and leukocytes with Dice score of 0.97 and 0.96 respectively. The overall sensitivity of the method is around 96{\%}.",
    author = "Hegde, {Roopa B.} and Keerthana Prasad and Harishchandra Hebbar and Singh, {Brij Mohan Kumar}",
    year = "2019",
    month = "5",
    day = "1",
    doi = "10.1007/s10916-019-1219-3",
    language = "English",
    volume = "43",
    journal = "Journal of Medical Systems",
    issn = "0148-5598",
    publisher = "Springer New York",
    number = "5",

    }

    Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears. / Hegde, Roopa B.; Prasad, Keerthana; Hebbar, Harishchandra; Singh, Brij Mohan Kumar.

    In: Journal of Medical Systems, Vol. 43, No. 5, 114, 01.05.2019.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears

    AU - Hegde, Roopa B.

    AU - Prasad, Keerthana

    AU - Hebbar, Harishchandra

    AU - Singh, Brij Mohan Kumar

    PY - 2019/5/1

    Y1 - 2019/5/1

    N2 - Peripheral blood smear analysis is a gold-standard method used in laboratories to diagnose many hematological disorders. Leukocyte analysis helps in monitoring and identifying health status of a person. Segmentation is an important step in the process of automation of analysis which would reduce the burden on hematologists and make the process simpler. The segmentation of leukocytes is a challenging task due to variations in appearance of cells across the slide. In the proposed study, an automated method to detect nuclei and to extract leukocytes from peripheral blood smear images with color and illumination variations is presented. Arithmetic and morphological operations are used for nuclei detection and active contours method is for leukocyte detection. The results demonstrate that the proposed method detects nuclei and leukocytes with Dice score of 0.97 and 0.96 respectively. The overall sensitivity of the method is around 96%.

    AB - Peripheral blood smear analysis is a gold-standard method used in laboratories to diagnose many hematological disorders. Leukocyte analysis helps in monitoring and identifying health status of a person. Segmentation is an important step in the process of automation of analysis which would reduce the burden on hematologists and make the process simpler. The segmentation of leukocytes is a challenging task due to variations in appearance of cells across the slide. In the proposed study, an automated method to detect nuclei and to extract leukocytes from peripheral blood smear images with color and illumination variations is presented. Arithmetic and morphological operations are used for nuclei detection and active contours method is for leukocyte detection. The results demonstrate that the proposed method detects nuclei and leukocytes with Dice score of 0.97 and 0.96 respectively. The overall sensitivity of the method is around 96%.

    UR - http://www.scopus.com/inward/record.url?scp=85063321122&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85063321122&partnerID=8YFLogxK

    U2 - 10.1007/s10916-019-1219-3

    DO - 10.1007/s10916-019-1219-3

    M3 - Article

    AN - SCOPUS:85063321122

    VL - 43

    JO - Journal of Medical Systems

    JF - Journal of Medical Systems

    SN - 0148-5598

    IS - 5

    M1 - 114

    ER -