• DocumentCode
    2034875
  • Title

    Detecting immature precursor cells in pathological images of bone marrow based on morphology

  • Author

    Li, Ling ; Cao, Guitao ; Shi, Jun ; Wu, Heng ; Zhang, Xianxia

  • Author_Institution
    Software Eng. Inst., East China Normal Univ., Shanghai, China
  • Volume
    5
  • fYear
    2010
  • fDate
    10-12 Aug. 2010
  • Firstpage
    2190
  • Lastpage
    2194
  • Abstract
    It is an effective means for the early diagnosis of leukemia to study immature precursor cells in marrow pathological images by computer image processing technology. This paper proposed a new method about localization of immature precursor cells in Pathological images of bone marrow. Firstly, we use modified OSTU method to binarize the image; then we process the image with morphological operations, combined with their own characteristics and the sizes of cells; finally we obtain the right results of cellular localization. Experimental results show that the method proposed in this paper has a better performance on immature precursor cells identification, which addresses the problem unsolved in specific situation with general image segmentation methods. This lays a foundation for the future study in the area of distribution of cells.
  • Keywords
    biology computing; bone; diseases; image segmentation; medical image processing; bone marrow; cellular localization; computer image processing; image segmentation; immature precursor cell identification; leukemia diagnosis; marrow pathological image; morphological operation; morphology; Bones; Image edge detection; Image segmentation; Morphology; Optimization; Pathology; Pixel; cell localization; immature precursor cells; marrow pathological image; morphology;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Fuzzy Systems and Knowledge Discovery (FSKD), 2010 Seventh International Conference on
  • Conference_Location
    Yantai, Shandong
  • Print_ISBN
    978-1-4244-5931-5
  • Type

    conf

  • DOI
    10.1109/FSKD.2010.5569552
  • Filename
    5569552