Advertisement

High Resolution Digital Tissue Image Processing using Texture Image Databases

  • Gábor KissEmail author
  • Orsolya Eszter Cseri
  • Ádám Altsach
  • István Imre Bándi
  • Levente Kovács
  • Miklos Kozlovszky
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 450)

Abstract

Texture based image databases integrated with effective searching algorithms are useful solutions for many scientific and industrial purposes. Medical image processing of high resolution tissue images is one of the areas, where the cell/tissue classification can rely on such solutions. In this paper we are describing the design, development and usage of a specialized medical texture image database. Our primary aim with this texture database is to provide Digital Imaging and Communication in Medicine (DICOM) compatible texture image dataset for cell, gland and epithelium classification in histology. Our solution includes a Picture Archiving and Communication System (PACS) subsystem, which is mainly provide a communication interface (texture image searching and retrieval) and enables image processing algorithms to work more effectively on high resolution tissue slide images. In this paper we describe how our Local Binary Pattern (LBP) based algorithm benefits texture database usage when solving image processing problems in histology and histopathology.

Keywords

PACS DICOM LBP Texture based image database Medical image processing Digital microscopy 

References

  1. 1.
    Visiopharm for digital pathology. Visiopharm (March 2013). http://www.visiopharm.com/pdf/visiomorphdp-factsheet.pdf
  2. 2.
  3. 3.
    Developerxd. Definiers (March 2013). http://www.definiens.com/tissue-diagnostics.html
  4. 4.
    Bickel, E.L.P.: The earth mover‘s distance is the mallows distance: Some insights from statistics. In: ICCV 2001, IEEE 12th International Conference on Computer Vision, pp. 251–256 (2001)Google Scholar
  5. 5.
    Digital imaging and communications in medicine, National Electrical Manufacturers Association (2004). http://dicom.nema.org
  6. 6.
    Reményi, A., Szénási, S., Bándi, I., Vámossy, Z., Valcz, G., Bogdanov, P., Kozlovszky, M., Sergyán, S.: Parallel biomedical image processing with GPGPUs in cancer research. In: 3rd IEEE International Symposium on Logistics and Industrial Informatics, Budapest, Hungary, August 2011, pp. 225–248 (2011)Google Scholar
  7. 7.
    Kozlovszky, M., Szénási, S., Vámossy, Z.: GPGPU-based data parallel region growing algorithm for cell nuclei detection. In: CINTI 2011, 12th IEEE International Symposium on Computational Intelligence and Informatics, pp. 493–499 (2011)Google Scholar
  8. 8.
    Fugal, D.L.: Conceptual wavelets in digital signal processing. Space & Signals Technical (2009)Google Scholar
  9. 9.
    Xiaoyu Wang, S.Y., Han, T.X.: An hog-lbp human detector with partial occlusion handling. In: ICCV 2009, IEEE 12th International Conference on Computer Vision, pp. 1550–5499 (2009)Google Scholar
  10. 10.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slicsuperpixels, Institute of Electrical and Electronics Engineers, Tech. Rep. (2010)Google Scholar
  11. 11.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: Slic superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 2274–2282 (2012)CrossRefGoogle Scholar
  12. 12.
    Yasnoff, J.W.A., Mui, J.K.: Error measures for scene segmentation. Pattern Recognition 9, 217–231 (1977)CrossRefGoogle Scholar
  13. 13.
    ASH ImageBank, hematology imagebank. (Marc 2013). http://imagebank.hematology.org/
  14. 14.
    ImageAfter texture database (March 2013). http://www.imageafter.com/index.php
  15. 15.
    TinEye Reverse Image Search (March 2013). https://www.tineye.com/
  16. 16.
    RevIMG reverse visual search (March 2013). http://www.revimg.net/

Copyright information

© IFIP International Federation for Information Processing 2015

Authors and Affiliations

  • Gábor Kiss
    • 1
    Email author
  • Orsolya Eszter Cseri
    • 1
  • Ádám Altsach
    • 1
  • István Imre Bándi
    • 1
  • Levente Kovács
    • 1
  • Miklos Kozlovszky
    • 1
    • 2
  1. 1.Óbuda University/Biotech Knowledge CenterBudapestHungary
  2. 2.MTA SZTAKI/Laboratory of Parallel and Distributed ComputingBudapestHungary

Personalised recommendations