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

    4 Citations (Scopus)

    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

    All Science Journal Classification (ASJC) codes

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

    Fingerprint Dive into the research topics of 'Image Processing Approach for Detection of Leukocytes in Peripheral Blood Smears'. Together they form a unique fingerprint.

  • Cite this