Skip to main content

Advertisement

SpringerLink
Log in

An automatic approach for cell detection and segmentation of corneal endothelium in specular microscope

  • Cornea
  • Published:
Graefe's Archive for Clinical and Experimental Ophthalmology Aims and scope Submit manuscript

A Correction to this article was published on 29 November 2021

This article has been updated

Abstract

Purpose

Specular microscopy is an indispensable tool for clinicians seeking to monitor the corneal endothelium. Automated methods of determining endothelial cell density (ECD) are limited in their ability to analyze images of poor quality. We describe and assess an image processing algorithm to analyze corneal endothelial images.

Methods

A set of corneal endothelial images acquired with a Konan CellChek specular microscope was analyzed using three methods: flex-center, Konan Auto Tracer, and the proposed method. In this technique, the algorithm determines the region of interest, filters the image to differentiate cell boundaries from their interiors, and utilizes stochastic watershed segmentation to draw cell boundaries and assess ECD based on the masked region. We compared ECD measured by the algorithm with manual and automated results from the specular microscope.

Results

We analyzed a total of 303 images manually, using the Auto Tracer, and with the proposed image processing method. Relative to manual analysis across all images, the mean error was 0.04% in the proposed method (p = 0.23 for difference) whereas Auto Tracer demonstrated a bias towards overestimation, with a mean error of 5.7% (p = 2.06× 10-8). The relative mean absolute errors were 6.9% and 7.9%, respectively, for the proposed and Auto Tracer. The average time for analysis of each image using the proposed method was 2.5 s.

Conclusion

We demonstrate a computationally efficient algorithm to analyze corneal endothelial cell density that can be implemented on devices for clinical and research use.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

The specific images used in the research cannot be shared in public due to the patient consent; however, the images were captured using Konan specular microscope and authors believe the algorithm should work with similar accuracy with any images taken using the similar device.

Code availability

Authors implemented their own code on MATLAB.

Change history

References

  1. McCarey BE (1979) Noncontact specular microscopy: a macrophotography technique and some endothelial cell findings. Ophthalmology 86(10):1848–1860

    Article  CAS  Google Scholar 

  2. Bourne WM, Nelson LR, Hodge DO (1997) Central corneal endothelial cell changes over a ten-year period. Invest Ophthalmol Vis Sci 38(3):779–782

    CAS  PubMed  Google Scholar 

  3. Laing RA, Sandstrom MM, Berrospi AR et al (1976) Changes in the corneal endothelium as a function of age. Exp Eye Res 22(6):587–594

    Article  CAS  Google Scholar 

  4. Mohammad-Salih P (2011) Corneal endothelial cell density and morphology in normal Malay eyes. Med J Malaysia 66(4):300–303

    CAS  PubMed  Google Scholar 

  5. Rao SK, Sen PR, Fogla R et al (000) Corneal endothelial cell density and morphology in normal Indian eyes. Cornea 19(6):820–823

  6. Maurice D (1968) Cellular membrane activity in the corneal endothelium of the intact eye. Cell Mol Life Sci 24(11):1094–1095

    Article  CAS  Google Scholar 

  7. Laing RA, Sandstrom MM, Leibowitz HM (1975) Vivo photomicrography of the corneal endothelium. Arch Ophthalmol 93(2):143–145

    Article  CAS  Google Scholar 

  8. Bourne WM, Kaufman HE (1976) Specular microscopy of human corneal endothelium in vivo. Am J Ophthalmol 81(3):319–323

    Article  CAS  Google Scholar 

  9. Jalbert I, Stapleton F, Papas E et al (2003) In vivo confocal microscopy of the human cornea. Br J Ophthalmol 87(2):225–236

    Article  CAS  Google Scholar 

  10. Huang J, Maram J, Tepelus TC et al (2018) Comparison of noncontact specular and confocal microscopy for evaluation of corneal endothelium. Eye Contact Lens 44:144–150

    Article  Google Scholar 

  11. Huang J, Maram J, Modak C et al (2014) Comparison of non-contact specular and confocal microscopy for the evaluation of the corneal endothelium. Invest Ophthalmol Vis Sci 55(13):999–999

    Google Scholar 

  12. Hara M, Morishige N, Chikama T et al (2003) Comparison of confocal biomicroscopy and noncontact specular microscopy for evaluation of the corneal endothelium. Cornea 22(6):512–515

    Article  Google Scholar 

  13. Price MO, Fairchild KM, Price FW Jr (2013) Comparison of manual and automated endothelial cell density analysis in normal eyes and dsek eyes. Cornea 32(5):567–573

    Article  Google Scholar 

  14. Miyagi H, Stanley AA, Chokshi TJ et al (2020) Comparison of automated vs manual analysis of corneal endothelial cell density and morphology in normal and corneal endothelial dystrophy-affected dogs. Vet Ophthalmol 23(1):44–51

    Article  Google Scholar 

  15. Huang J, Maram J, Tepelus TC et al (2018) Comparison of manual & automated analysis methods for corneal endothelial cell density measurements by specular microscopy. J Opt 11(3):182–191

    Article  Google Scholar 

  16. Villalba R, Jimenez A, Fornes G et al (2014) Flex center method versus center method for endothelial corneal evaluation in eye banking. a comparative analysis. Cell Tissue Bank 15(4):507–512

    Article  CAS  Google Scholar 

  17. Thuret G, Manissolle C, Acquart S et al (2003) Is manual counting of corneal endothelial cell density in eye banks still acceptable? the french experience. Br J Ophthalmol 87(12):1481–1486

    Article  CAS  Google Scholar 

  18. Vincent LM, Masters BR (1992) Morphological image processing and network analysis of cornea endothelial cell images. In: Image Algebra and Morphological Image Processing III, vol. 1769, pp. 212–226. International Society for Optics and Photonics

  19. Salerno M, Sargeni F, Bonaiuto V, etal (1998) A new CNN based tool for an automated morphometry analysis of the corneal endothelium. In: Proceedings of Fifth IEEE International Workshop on Cellular Neural Networks and Their Applications. (Cat. No. 98TH8359), pp. 169–174

  20. Foracchia M, Ruggeri A, etal. (2002), Estimating cell density in corneal endothelium by means of Fourier analysis. In: Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society, Engineering in Medicine and Biology, vol. 2, pp. 1097–1098.

  21. Grisan E, Paviotti A, Laurenti N, etal (2006), A lattice estimation approach for the automatic evaluation of corneal endothelium density. In: 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, pp. 1700–1703.

  22. Foracchia M, Ruggeri A (2007) Corneal endothelium cell field analysis by means of interacting bayesian shape models. In: 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6035–6038.

  23. Ruggeri A, Scarpa F, De Luca M et al (2012) A system for the automatic estimation of morphometric parameters of corneal endothelium in alizarine red-stained images. Br J Ophthalmol 94(5):643–647

    Article  Google Scholar 

  24. Kumar KK, Srinivasa G (2018) Corneal endothelium cell segmentation and count using k-means and watershed algorithms. In: Second International Conference on Advances in Electronics, Computers and Communications (ICAECC), pp. 1–7. IEEE

  25. Selig B, Vermeer KA, Rieger B et al (2015) Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy. BMC Med Imaging 15(1):13

    Article  Google Scholar 

  26. Ruggeri A, Grisan E, Jaroszewski J (2005) A new system for the automatic estimation of endothelial cell density in donor corneas. Br J Ophthalmol 89(3):306–311

    Article  CAS  Google Scholar 

  27. Hiroyasu T, Sekiya S, Nunokawa S, et al. (2013), Extracting rules for cell segmentation in corneal endothelial cell images using GP. In: IEEE International Conference on Systems, Man, and Cybernetics, pp. 1811–1816

  28. Foracchia M, Ruggeri A, (2000), Cell contour detection in corneal endothelium in-vivo microscopy. In: Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No. 00CH37143), vol. 2, pp. 1033–1035

  29. Vigueras-Guillen JP, van Rooij J, Engel A et al (2020) Deep learning for assessing the corneal endothelium from specular microscopy images up to 1 year after ultrathin-DSAEK surgery. Translat Vision Sci Technol 9(2):49–49

    Article  Google Scholar 

  30. Daniel MC, Atzrodt L, Bucher F et al (2019) Automated segmentation of the corneal endothelium in a large set of ‘real-world’specular microscopy images using the u-net architecture. Sci Rep 9(1):1–7

    Google Scholar 

  31. Kolluru C, Benetz BA, Joseph N, et al. (2019), Machine learning for segmenting cells in corneal endothelium images. In: Medical Imaging 2019: Computer-Aided Diagnosis, vol. 10950, p. 109504

  32. Nurzynska K (2018) Deep learning as a tool for automatic segmentation of corneal endothelium images. Symmetry 10(3):60

    Article  Google Scholar 

  33. Vigueras-Guillen JP, Sari B, Goes SF et al (2019) Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation. BMC Biomed Eng 1(1):1–16

    Article  Google Scholar 

  34. Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention (pp. 234-241). Springer, Cham

  35. Badrinarayanan V, Kendall A, Cipolla R (2017) Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481–2495

    Article  Google Scholar 

  36. Imre L, Nagymihaly A (2001) Reliability and reproducibility of corneal endothelial image analysis by in vivo confocal microscopy. Graefes Arch Clin Exp Ophthalmol 239(5):356–360

    Article  CAS  Google Scholar 

  37. Piorkowski A, Nurzynska K, Boldak C et al (2015) Selected aspects of corneal endothelial segmentation quality. J Med Informat Technol:24

  38. Sharif MS, Qahwaji R, Shahamatnia E, etal (2015) An efficient intelligent analysis system for confocal corneal endothelium images. Comput Methods Prog Biomed 122(3):421–436

    Article  CAS  Google Scholar 

  39. Fabijanska A (2019) Automatic segmentation of corneal endothelial cells from microscopy images. Biomed Signal Proc Cont 47:145–158

    Article  Google Scholar 

  40. Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379–423

    Article  Google Scholar 

  41. Serra J (1983) Image Analysis and Mathematical Morphology. Academic Press Inc

    Google Scholar 

  42. Berzins V (1984) Accuracy of Laplacian edge detectors. Comput Vision Graphics Image Proc 27(2):195–210

    Article  Google Scholar 

  43. Sobel I, Feldman G (1968) A 3x3 isotropic gradient operator for image processing. a talk at the. Stanford Artificial Project 271–272

  44. Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 6:679–698

    Article  Google Scholar 

  45. Beucher S (1994 Watershed, hierarchical segmentation and waterfall algorithm. In: Mathematical Morphology and Its Applications to Image Processing, pp. 69–76. Springer

Download references

Funding

The research is supported by National Science Foundation.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Michigan Technical University, Houghton, MI, USA

    Ranit Karmakar & Saeid Nooshabadi

  2. Department of Ophthalmology, Johns Hopkins University School of Medicine, Baltimore, MD, USA

    Allen Eghrari

Authors
  1. Ranit Karmakar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Saeid Nooshabadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Allen Eghrari
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: Ranit Karmakar. Methodology: Ranit Karmakar. Formal analysis and investigation: Ranit Karmakar, Saeid Nooshabadi, Allen Eghrari. Writing—original draft preparation: Ranit Karmakar. Writing—review and editing: Saeid Nooshabadi, Allen Eghrari. Funding acquisition: Saeid Nooshabadi. Resources: Allen Eghrari. Supervision: Saeid Nooshabadi, Allen Eghrari.

Corresponding author

Correspondence to Ranit Karmakar.

Ethics declarations

Ethics approval

The data used in this research was collected under IRB number IRB00039261 at Johns Hopkins University. All the data was deidentified before sharing with the researchers at Michigan Technological University; hence, they received a waiver for the analysis work.

Consent to participate

Patients were asked for their consent for research.

Consent for publication

Patients were asked for their consent for publication.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original version of this article was revised. The IRB number in the Ethics approval section is now corrected.

Supplementary Information

Supplemental Figure 1.

Bland-Altman plot of difference in measured ECD between the manual flex-center and proposed algorithm measurements demonstrates minimal bias of 8 cells/mm2, approximately 0.3% error. (PNG 959 kb)

High resolution image (TIF 18366 kb)

Supplemental Figure 2.

Distribution plot of the manual analysis, proposed algorithm and Auto Tracer for CD, HEX, and CV that shows the performance difference between Auto Tracer and proposed algorithm compared to the manual analysis. (PNG 768 kb)

High resolution image (TIF 29154 kb)

Supplemental Figure 3.

Example images a original image, b region of interest demarcation, c feature-enhanced image, d cell segmentation, e segmented image with selected cells marked in red. (PNG 17574 kb)

High resolution image (TIF 99650 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Karmakar, R., Nooshabadi, S. & Eghrari, A. An automatic approach for cell detection and segmentation of corneal endothelium in specular microscope. Graefes Arch Clin Exp Ophthalmol 260, 1215–1224 (2022). https://doi.org/10.1007/s00417-021-05483-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00417-021-05483-8

Keywords

Search

Navigation