Morphological Phenotyping of Corneal Endothelial Cells Using Elliptic Fourier Descriptors
DOI:
https://doi.org/10.3991/ijoe.v22i09.61857Keywords:
Corneal endothelial cells, Elliptic Fourier Descriptors, specular microscopy, unsupervised clustering, morphological phenotyping, K_Means, Zernike moments, statistical validationAbstract
Corneal endothelial cell morphology is clinically important to understand corneal health, and is routinely examined using specular microscopy. Traditional metrics such as endothelial cell density (ECD), coefficient of variation (CV), and hexagonality percentage provide limited morphological information and are unreliable when used on large diverse datasets. This paper presents an automated phenotyping framework using Elliptic Fourier Descriptors (EFDs), Zernike moments, and geometric features combined with unsupervised K-Means clustering for endothelial cell classification. The framework was validated on two independent datasets. The primary dataset comprised 179 cells (1,253 post augmentation) from four specular microscopy images. The external validation set (SREP-18-33533B) comprised 35,890 cells across 385 images. EFD based features achieved a mean silhouette score of 0.6213 (SD = 0.056) on the primary dataset, representing a large effect size over traditional measures (Cohen’s d = 5.290). Across datasets, traditional measures declined by nearly 40% (0.5986 to 0.3628), whereas EFD based scores remained stable with under 1% change (0.6213 to 0.6119), as confirmed by the Wilcoxon signed-rank test (p < 0.001). Three reproducible phenotypes were identified. Cluster 0, contained regular compact cells (64.4%). Cluster 1, contained moderately regular cells (29.2%) and Cluster 2, contained irregular or elongated cells (6.4%). These results indicate that EFD based shape analysis remains discriminative on a 35,890 cells where traditional clinical metrics fail. The framework can support real world analysis of corneal endothelial cell phenotypes when combined with clinical expertise of researchers and ophthalmologists.
References
1. L. J. Jeang, C. E. Margo, and E. M. Espana, "Diseases of the corneal endothelium," Experimental Eye Research, vol. 205, p. 108495, 2021, doi: 10.1016/j.exer.2021.108495.
2. J. P. Vigueras-Guillén, J. van Rooij, B. T. van Dooren, H. G. Lemij, E. Islamaj, L. J. van Vliet, and K. A. Vermeer, "DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae," Scientific Reports, vol. 12, no. 1, p. 14035, 2022, doi: 10.1038/s41598-022-18180-1
3. N. Tananuvat and N. Khumchoo, "Corneal thickness and endothelial morphology in normal Thai eyes," BMC Ophthalmology, vol. 20, no. 1, p. 167, 2020, doi: 10.1186/s12886-020-01385-1.
4. B. Mohd-Ali and L. Y. Chen, "The morphology of corneal endothelial cells in long term soft contact lens wearers in Kuala Lumpur," Contact Lens and Anterior Eye, vol. 44, no. 1, pp. 72–75, 2021, doi: 10.1016/j.clae.2020.06.007.
5. A. Consejo, I. Trillo-Moreno, and L. Remon, "Corneal tissue changes following short-term soft contact lens wear of different materials," Ophthalmic and Physiological Optics, vol. 43, no. 1, pp. 35–45, 2023, doi: 10.1111/opo.13062.
6. I. Gustafsson, "The assessment of disease progression in keratoconus and corneal crosslinking in thin corneae," Ph.D. dissertation, Lund Univ., Lund, Sweden, 2021.
7. A. R. Doke, S. Palaniswamy, and S. P. Srinivas, "Automated detection of tight junction damage in corneal endothelium using machine learning," in Proc. 4th Int. Conf. Ubiquitous Computing and Intelligent Information Systems (ICUIS), 2024, pp. 675–679, doi: 10.1109/ICUIS64676.2024.10866485.
8. P. Gain, R. Jullienne, Z. He, M. Aldossary, S. Acquart, F. Cognasse, and G. Thuret, "Global survey of corneal transplantation and eye banking," JAMA Ophthalmology, vol. 134, no. 2, pp. 167–173, 2016, doi: 10.1001/jamaophthalmol.2015.4776.
9. T. Ono, Y. Mori, R. Nejima, T. Iwasaki, T. Miyai, and K. Miyata, "Corneal endothelial cell density and morphology in ophthalmologically healthy young individuals in Japan: an observational study of 16842 eyes," Scientific Reports, vol. 11, no. 1, p. 18224, 2021, doi: 10.1038/s41598-021-97776-5.
10. B. Selig, K. A. Vermeer, B. Rieger, T. Hillenaar, and C. L. Luengo Hendriks, "Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy," BMC Medical Imaging, vol. 15, no. 1, p. 13, 2015, doi: 10.1186/s12880-015-0054-3.
11. B. A. Benetz, V. S. Shivade, N. M. Joseph, N. J. Romig, J. C. McCormick, J. Chen, M. S. Titus, O. B. Sawant, J. M. Clover, N. Yoganathan, and H. J. Menegay, "Automatic determination of endothelial cell density from donor cornea endothelial cell images," Translational Vision Science & Technology, vol. 13, no. 8, p. 40, 2024, doi: 10.1167/tvst.13.8.40.
12. J. P. Vigueras-Guillén, J. van Rooij, A. Engel, H. G. Lemij, L. J. van Vliet, and K. A. Vermeer, "Deep learning for assessing the corneal endothelium from specular microscopy images up to 1 year after ultrathin-DSAEK surgery," Translational Vision Science & Technology, vol. 9, no. 2, p. 49, 2020, doi: 10.1167/tvst.9.2.49.
13. Y. Wang and W. Jiang, "An automatic classification and clustering algorithm for online learning goals based on cognitive thinking," International Journal of Emerging Technologies in Learning (iJET), vol. 13, no. 11, pp. 54–66, 2018, doi: 10.3991/ijet.v13i11.9587.
14. M. Amane, K. Aissaoui, and M. Berrada, "Multi-label classification of learning objects using clustering algorithms based on feature selection," International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 20, pp. 248–260, 2022, doi: 10.3991/ijet.v17i20.32323.
15. A. Ruggeri, E. Grisan, and J. Jaroszewski, "A new system for the automatic estimation of endothelial cell density in donor corneas," British Journal of Ophthalmology, vol. 89, no. 3, pp. 306–311, 2005, doi: 10.1136/bjo.2004.051722.
16. A. Fabijańska, "Segmentation of corneal endothelium images using a U-Net-based convolutional neural network," Artificial Intelligence in Medicine, vol. 88, pp. 1–13, 2018, doi: 10.1016/j.artmed.2018.04.004.
17. J. P. Vigueras-Guillén, B. Sari, S. F. Goes, H. G. Lemij, J. van Rooij, K. A. Vermeer, and L. J. van Vliet, "Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation," BMC Biomedical Engineering, vol. 1, no. 1, p. 4, 2019, doi: 10.1186/s42490-019-0003-2.
18. B. J. Sowmya, Meeradevi, S. S. Shedole, P. Dayananda, S. S. Sirisha, G. S. Smitha, and S. Rohith, "A visual computing unified application using deep learning and computer vision techniques," International Journal of Interactive Mobile Technologies (iJIM), vol. 18, no. 1, pp. 59–74, 2024, doi: 10.3991/ijim.v18i01.42673.
19. F. P. Kuhl and C. R. Giardina, "Elliptic Fourier features of a closed contour," Computer Graphics and Image Processing, vol. 18, no. 3, pp. 236–258, 1982, doi: 10.1016/0146-664X(82)90034-X.
20. D. G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004, doi: 10.1023/B:VISI.0000029664.99615.94.
21. M. J. Doughty, S. Jonuscheit, and N. F. Button, "Assessment of the reliability of endothelial cell-density estimates in the presence of pseudoguttata," Graefe's Archive for Clinical and Experimental Ophthalmology, vol. 250, no. 1, pp. 111–121, 2012, doi: 10.1007/s00417-011-1812-8.
22. E. G. Stocker and J. P. Schoessler, “Corneal endothelial polymegathism induced by PMMA contact lens wear,” Investigative Ophthalmology & Visual Science, vol. 26, no. 6, pp. 857–863, 1985. [Online]. https://pubmed.ncbi.nlm.nih.gov/3891666/
23. S. Sanchez, N. Vallez, G. Bueno, and A. G. Marrugo, "Data augmentation via warping transforms for modeling natural variability in the corneal endothelium enhances semi-supervised segmentation," PLOS ONE, vol. 19, no. 11, p. e0311849, 2024, doi: 10.1371/journal.pone.0311849.
24. M. C. Daniel, L. Atzrodt, F. Bucher, K. Wacker, S. Böhringer, T. Reinhard, and D. Boehringer, "Automated segmentation of the corneal endothelium in a large set of 'real-world' specular microscopy images using the U-Net architecture," Scientific Reports, vol. 9, no. 1, p. 4752, 2019, doi: 10.1038/s41598-019-41034-2.
25. K. Zuiderveld, "Contrast limited adaptive histogram equalization," in Graphics Gems IV, P. S. Heckbert, Ed. San Diego, CA, USA: Academic Press, pp. 474–485,1994.
26. A. Kucharski and A. Fabijańska, "CNN-watershed: A watershed transform with predicted markers for corneal endothelium image segmentation," Biomedical Signal Processing and Control, vol. 68, p. 102805, 2021, doi: 10.1016/j.bspc.2021.102805.
27. F. P. Kuhl and C. R. Giardina, “Elliptic Fourier features of a closed contour,” Computer Graphics and Image Processing, vol. 18, no. 3, pp. 236–258, 1982, doi: 10.1016/0146-664X(82)90034-X
28. H. Iwata and Y. Ukai, “SHAPE: A computer program package for quantitative evaluation of biological shapes based on elliptic Fourier descriptors,” Journal of Heredity, vol. 93, no. 5, pp. 384–385, 2002, doi: 10.1093/jhered/93.5.384
29. D. P. Huttenlocher, G. A. Klanderman, and W. J. Rucklidge, "Comparing images using the Hausdorff distance," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, no. 9, pp. 850–863, 1993, doi: 10.1109/34.232073.
30. G. Borgefors, “Hierarchical chamfer matching: A parametric edge matching algorithm,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 6, pp. 849–865, 1988, doi: 10.1109/34.9107
31. W. M. Bourne, "Biology of the corneal endothelium in health and disease," Eye, vol. 17, no. 8, pp. 912–918, 2003, doi: 10.1038/sj.eye.6700559.
32. E. Alizadeh, S. M. Lyons, J. M. Castle, and A. Prasad, "Measuring systematic changes in invasive cancer cell shape using Zernike moments," Integrative Biology, vol. 8, no. 11, pp. 1183–1193, 2016, doi: 10.1039/c6ib00100a.
33. S. Tadepalli, R. Kiruba, S. Paneerselvam, A. Ravikumar, R. R. Sudhir, P. Padmanabhan, and S. P. Srinivas, "Blink-induced artifacts in aqueous flare measurements by EOG-based spot fluorometer and their reduction using unsupervised clustering," Biomedical Signal Processing and Control, vol. 96, p. 106486, 2024, doi: 10.1016/j.bspc.2024.106486.
34. D. Chicco, A. Campagner, A. Spagnolo, D. Ciucci, and G. Jurman, "The silhouette coefficient and the Davies-Bouldin index are more informative than Dunn index, Calinski-Harabasz index, Shannon entropy, and gap statistic for unsupervised clustering internal evaluation of two convex clusters," PeerJ Computer Science, vol. 11, p. e3309, 2025, doi: 10.7717/peerj-cs.3309.
35. M. J. Warrens and H. van der Hoef, “Understanding the adjusted Rand index and other partition comparison indices based on counting object pairs,” Journal of Classification, vol. 39, no. 3, pp. 487–509, 2022, doi: 10.1007/s00357-022-09413-z
36. R. F. Mutwaly, "Corneal endothelial polymegathism and pleomorphism induced by daily-wear soft contact lenses," Cureus, vol. 16, no. 11, 2024, doi: 10.7759/cureus.74187.
37. E. Karmiris, A. Tsiogka, K. Tsiripidis, E. Papakonstantinou, I. Georgalas, and E. Chalkiadaki, "Correlations of corneal endothelial morphology and corneal thickness with anterior segment parameters in healthy individuals," Cornea, vol. 43, no. 6, pp. 764–770, 2024, doi: 10.1097/ICO.0000000000003515.
38. K. H. Carlson, W. M. Bourne, and R. F. Brubaker, “Effect of long-term contact lens wear on corneal endothelial cell morphology and function,” Investigative Ophthalmology & Visual Science, vol. 29, no. 2, pp. 185–193, 1988. https://iovs.arvojournals.org/article.aspx?articleid=2177982
39. S. M. Mac Rae, M. Matsuda, S. Shellans, and L. F. Rich, "The effects of hard and soft contact lenses on the corneal endothelium," American Journal of Ophthalmology, vol. 102, no. 1, pp. 50–57, 1986, doi: 10.1016/0002-9394(86)90209-6.
40. S. Akshay, S. Dhanush, G. N. Aswin, and J. Amudha, "Eyehelp: Predicting an AOI based on eye gaze for patient assistance," Procedia Computer Science, vol. 258, pp. 1486–1495, 2025, doi: 10.1016/j.procs.2025.04.381.
41. S. Tadepalli, H. P. Farhath, R. R. Sudhir, P. Padmanabhan, J. Biswas, S. Saravana, M. Rathore, S. Paneerselvam, A. Ravikumar, and S. P. Srinivas, "Reliability of aqueous flare measurements during uveitis by a spot fluorometer," Journal of Ocular Pharmacology and Therapeutics, vol. 38, no. 1, pp. 66–73, 2022, doi: 10.1089/jop.2021.0053.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ashwini Ramchandra Doke, Suja Palaniswamy
This work is licensed under a Creative Commons Attribution 4.0 International License.
