• DocumentCode
    2102385
  • Title

    Advanced characterization of microscopic Kidney biopsies utilizing image analysis techniques

  • Author

    Goudas, T. ; Doukas, Charalampos ; Chatziioannou, Aristotelis ; Maglogiannis, Ilias

  • Author_Institution
    Dept. of Comput. Sci. & Biomed. Inf., Univ. of Central Greece, Lamia, Greece
  • fYear
    2012
  • fDate
    Aug. 28 2012-Sept. 1 2012
  • Firstpage
    4414
  • Lastpage
    4417
  • Abstract
    Correct annotation and identification of salient regions in Kidney biopsy images can provide an estimation of pathogenesis in obstructive nephropathy. This paper presents a tool for the automatic or manual segmentation of such regions along with methodology for their characterization in terms of the exhibited pathology. The proposed implementation is based on custom code written in Java and the utilization of open source tools (i.e. RapidMiner, ImageJ). The corresponding implementation details along with the initial evaluation of the proposed integrated system are also presented in the paper.
  • Keywords
    Java; biomedical optical imaging; diseases; estimation theory; image segmentation; kidney; medical image processing; optical microscopy; ImageJ; Java; RapidMiner; automatic segmentation; custom code based implementation; image analysis techniques; integrated system; manual segmentation; microscopic kidney biopsy; obstructive nephropathy; open source tools; pathogenesis estimation; pathology; salient region annotation; salient region identification; Accuracy; Biomedical imaging; Image segmentation; Kidney; Liver; Microscopy; Support vector machines; Algorithms; Artificial Intelligence; Biopsy; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Kidney Diseases; Microscopy; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE
  • Conference_Location
    San Diego, CA
  • ISSN
    1557-170X
  • Print_ISBN
    978-1-4244-4119-8
  • Electronic_ISBN
    1557-170X
  • Type

    conf

  • DOI
    10.1109/EMBC.2012.6346945
  • Filename
    6346945