Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Image Analysis Algorithm for the Corneal Endothelium

  • Kim Young-Yoon (Department of Biomedical Engineering, College of Health Sciences, Yonsei University) ;
  • Kim Beop-Min (Department of Biomedical Engineering, College of Health Sciences, Yonsei University) ;
  • Park Hwa-Joon (Department of Biomedical Engineering, College of Health Sciences, Yonsei University) ;
  • Im Kang-Bin (Department of Biomedical Engineering, College of Health Sciences, Yonsei University) ;
  • Lee Jin-Su (Department of Biomedical Engineering, College of Health Sciences, Yonsei University) ;
  • Kim Dong-Youn (Department of Biomedical Engineering, College of Health Sciences, Yonsei University)
  • Published : 2006.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

The number of the living endothelial cells and the shape of those are very import clinical parameters for the evaluation of the quality of cornea. In this paper, we developed the automated endothelial cell counting and shape analysis algorithm for a confocal microscope. Since, the endothelial images from the confocal microscope has a non-uniform illumination and low contrast between cell boundaries and cell bodies, it is very difficult to segment the cells from the endothelial images. To cope with these difficulties, we proposed the new two stage image processing algorithm. At first stage algorithm, we used a high-pass filter and histogram equalization to compensate the non-uniform brightness pattern and a morphological filter and a watershed method are applied to detect the boundary of cells. From this stage, we could count the number of cells in an endothelial image. At second stage algorithm, we used a Voronoi diagram method to classify the shape of cells. This cell shape analysis and the percent of hexagonal cells are very sensitive in detecting the early endothelium damage. To evaluate the performance of the proposed system, we p개cessed seven endothelial images obtained using a confocal microscope. The proposed system correctly counted 95.5% cells and classified 92.0% of hexagonal cell shapes. This result is better than any others in this research area.

Keywords

References

  1. http://medocs.ucdavis.edu/CHA/402/labsyl/01/18/lm09.htm
  2. L. Mastropasqua, M. Nubile, Cofocal Microscopy of the Cornea, Slack, 2002
  3. M. salerno, F.Sargeni, V.Bonaiuto, P.Amerini, L.Cerulli, and F.Ricci., 'A new CNN based tool for an automated morphometry analysis of the corneal endothelium' in Proc. IEEE Fifth International Workshop, April 1998, pp.169-174
  4. Hirst LW, Auer C, Abbey SC et Al., 'Quantitative analysis of wide-field endothelial specular microphotographs,' Am. J. Ophthalmol, vol. 97, pp. 488, 1894
  5. E.L. Shaw, G.N. Rao, E.J. Arthur et Al., 'The functional reserve of the corneal endotheliurn,' Ophthalmology, vol. 85, pp. 640, 1978 https://doi.org/10.1016/S0161-6420(78)35634-7
  6. R. Nadachi, K. Nunokawa, 'Automated corneal endothelial cell analysis,' in Proc. IEEE Fifth Annual Symposium, June 1992, pp.450-457
  7. M. Foracchia, and A. Ruggeri, 'Estimating cell density in corneal endothelium by means of Fourier analysis,' in Proc. 2nd Joint IEEE-EMBS/BMSE Conference, New York, 2002, pp. 1097-98
  8. L. Ventura, C. A.C. Caetano, S. J.F. Sousa, F. Isaac, C. Chiaradia, R. A. Lotufo, 'A corneal endothelium cell analyzer for slit lamps,' IEEE Engineering in Medicine and Biology, Nov/Dec 2002
  9. Akira Hasegawa, Kazuyoshi Itoh, and Yoshiki Ichioka. 'Generalization of shift invariant neural networks: Image processing of corneal endotheliurn,' Neural Networks, vol. 9, no. 2, pp.345-356, 1996 https://doi.org/10.1016/0893-6080(95)00054-2
  10. Marco Foracchia, and Alfredo Ruggeri, 'Cell countour detection in corneal endothelium in-vivo microscopy,' in Proc. 22nd Annual International Conference of the IEEE, Chicago, July 2000
  11. R.C. Gonzalez, and R.E. Woods, Digital Image Processing 2nd, Prentice Hall, 2002
  12. Jos B.T.M. Roerdink, and A. Meijster, ' The watershed transform: Definitions, algorithms and parallelization strategies,' Fundamenta Informaticae, vol. 41, pp.187-228, 2000
  13. M. Seul, L. O'Gorman, and M.J. Sammon, Practical Algorithms for Image Analysis Description, Examples, and Code, Cambridge, 2000
  14. M. de Berg, M. van Kreveld, M. Overmars, and O. Schwarzkoph, Computational Geometry Algorithms and Application, Springer, 1997
  15. J.R. Parker, Practical Computer Vision using C, Wiley, 1994
  16. N. Y. Morgan, M. Seul, 'Structure of disordered droplet domain patterns in a monomolecular film,' J. Phys. Chem. vol.99, no.7, 1995
  17. S. J. Fortune, 'A sweepline algorithm for voronoi diagram,' Algorithmica, pp. 153-174, 1987
  18. ZEMAX development corporation http://www.zemax.com/zemax/index.html
  19. M.Deberg, M.Vankreveld, M.Overmars, and O.Schwarzkopf, Computational Geometry: Algorithms and Applications 2nd, Springer-Verlag, 2000