Skip to main content
Article
Licensed
Unlicensed Requires Authentication

Machine learning based endothelial cell image analysis of patients undergoing descemet membrane endothelial keratoplasty surgery

  • ORCID logo , ORCID logo , ORCID logo , ORCID logo EMAIL logo and ORCID logo
Published/Copyright: March 18, 2024
Biomedical Engineering / Biomedizinische Technik
From the journal Biomedical Engineering / Biomedizinische Technik Volume 69 Issue 5

Abstract

Objectives

In this study, we developed a machine learning approach for postoperative corneal endothelial cell images of patients who underwent Descemet’s membrane keratoplasty (DMEK).

Methods

An AlexNet model is proposed and validated throughout the study for endothelial cell segmentation and cell location determination. The 506 images of postoperative corneal endothelial cells were analyzed. Endothelial cell detection, segmentation, and determining of its polygonal structure were identified. The proposed model is based on the training of an R-CNN to locate endothelial cells. Next, by determining the ridges separating adjacent cells, the density and hexagonality rates of DMEK patients are calculated.

Results

The proposed method reached accuracy and F1 score rates of 86.15 % and 0.857, respectively, which indicates that it can reliably replace the manual detection of cells in vivo confocal microscopy (IVCM). The AUC score of 0.764 from the proposed segmentation method suggests a satisfactory outcome.

Conclusions

A model focused on segmenting endothelial cells can be employed to assess the health of the endothelium in DMEK patients.

Keywords: DMEK; deep learning; automatic detection of endothelial cell boundaries; R-CNN
Corresponding author: Kasım Oztoprak, Department of Computer Engineering, Konya Food and Agriculture University, Beyşehir Cd., 42080 Meram, Konya, Türkiye, Phone: +90 5323614148, E-mail:

Acknowledgments

The study was approved by the Institutional Review Board and adhered to the tenets of the Declaration of Helsinki.

  1. Research ethics: The local Institutional Review Board deemed the study exempt from review.

  2. Informed consent: Informed consent was obtained from all individuals included in this study.

  3. Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.

  4. Competing interests: Authors state no conflict of interest.

  5. Research funding: This study is supported by the Scientific and Technical Council of Turkey (TUBITAK) under Grant 123E450.

  6. Data availability: The raw data can be obtained on request from the corresponding author.

References

1. Williams, KA, Muehlberg, SM, Lewis, RF, Coster, DJ. How successful is corneal transplantation? A report from the Australian Corneal Graft Register. Eye 1995;9:219–27. https://doi.org/10.1038/eye.1995.43.Search in Google Scholar PubMed

2. Melles, GR, San Ong, T, Ververs, B, van der Wees, J. Descemet membrane endothelial keratoplasty (DMEK). Cornea 2006;25:987–90. https://doi.org/10.1097/01.ico.0000248385.16896.34.Search in Google Scholar PubMed

3. Parker, J, Dockery, P, Preda-Naumescu, A, Jager, M, van Dijk, K, Dapena, I, et al.. Descemet membrane endothelial keratoplasty and bowman layer transplantation: an anatomic review and historical survey. Ophthalmic Res 2021;64:532–53. https://doi.org/10.1159/000516093.Search in Google Scholar PubMed

4. Basak, SK, Basak, S, Gajendragadkar, N, Ghatak, M. Overall clinical outcomes of Descemet membrane endothelial keratoplasty in 600 consecutive eyes: a large retrospective case series. Indian J Ophthalmol 2020;68:1044. https://doi.org/10.4103/ijo.ijo_1563_19.Search in Google Scholar

5. Birbal, RS, Dhubhghaill, SN, Bourgonje, VJ, Hanko, J, Ham, L, Jager, MJ, et al.. Five-year graft survival and clinical outcomes of 500 consecutive cases after Descemet membrane endothelial keratoplasty. Cornea 2020;39:290–7. https://doi.org/10.1097/ico.0000000000002120.Search in Google Scholar

6. Jonuscheit, S, Doughty, M, Ramaesh, K. In vivo confocal microscopy of the corneal endothelium: comparison of three morphometry methods after corneal transplantation. Eye 2011;25:1130–7. https://doi.org/10.1038/eye.2011.121.Search in Google Scholar PubMed PubMed Central

7. Guthoff, RF, Baudouin, C, Stave, J. Atlas of confocal laser scanning in-vivo microscopy in ophthalmology. Leipzig: Springer Science & Business Media; 2007.10.1007/3-540-32707-XSearch in Google Scholar

8. Aggarwal, S, Cavalcanti, BM, Regali, L, Cruzat, A, Trinidad, M, Williams, C, et al.. In vivo confocal microscopy shows alterations in nerve density and dendritiform cell density in Fuchs’ endothelial corneal dystrophy. Am J Ophthalmol 2018;196:136–44. https://doi.org/10.1016/j.ajo.2018.08.040.Search in Google Scholar PubMed PubMed Central

9. Bozkurt, B, Irkec, M, Mocan, MC. In vivo confocal microscopic findings in posterior polymorphous corneal dystrophy. Cornea 2013;32:1237–42. https://doi.org/10.1097/ico.0b013e31828e324d.Search in Google Scholar PubMed

10. Kobayashi, A, Yokogawa, H, Higashide, T, Nitta, K, Sugiyama, K. Clinical significance of owl eye morphologic features by in vivo laser confocal microscopy in patients with cytomegalovirus corneal endotheliitis. Am J Ophthalmol 2012;153:445–53. https://doi.org/10.1016/j.ajo.2011.07.026.Search in Google Scholar PubMed

11. Qu, JH, Qin, XR, Peng, RM, Xiao, GG, Cheng, J, Gu, SF, et al.. A fully automated segmentation and morphometric parameter estimation system for assessing corneal endothelial cell images. Am J Ophthalmol 2022;239:142–53. https://doi.org/10.1016/j.ajo.2022.02.026.Search in Google Scholar PubMed

12. ászló Módis, LJr, Langenbucher, A, Seitz, B. Corneal endothelial cell density and pachymetry measured by contact and noncontact specular microscopy. J Cataract Refract Surg 2002;28:1763–9. https://doi.org/10.1016/s0886-3350(02)01296-8.Search in Google Scholar PubMed

13. Hara, M, Morishige, N, Ti, C, Nishida, T. Comparison of confocal biomicroscopy and noncontact specular microscopy for evaluation of the corneal endothelium. Cornea 2003;22:512–15. https://doi.org/10.1097/00003226-200308000-00005.Search in Google Scholar PubMed

14. McCarey, BE, Edelhauser, HF, Lynn, MJ. Review of corneal endothelial specular microscopy for FDA clinical trials of refractive procedures, surgical devices and new intraocular drugs and solutions. Cornea 2008;27:1. https://doi.org/10.1097/ico.0b013e31815892da.Search in Google Scholar PubMed PubMed Central

15. Al-Fahdawi, S, Qahwaji, R, Al-Waisy, AS, Ipson, S, Ferdousi, M, Malik, RA, et al.. A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology. Comput Methods Progr Biomed 2018;160:11–23. https://doi.org/10.1016/j.cmpb.2018.03.015.Search in Google Scholar PubMed

16. Gain, P, Thuret, G, Kodjikian, L, Gavet, Y, Turc, P, Theillere, C, et al.. Automated tri-image analysis of stored corneal endothelium. Br J Ophthalmol 2002;86:801–8. https://doi.org/10.1136/bjo.86.7.801.Search in Google Scholar PubMed PubMed Central

17. Ruggeri, A, Grisan, E, Jaroszewski, J. A new system for the automatic estimation of endothelial cell density in donor corneas. Br J Ophthalmol 2005;89:306–11. https://doi.org/10.1136/bjo.2004.051722.Search in Google Scholar PubMed PubMed Central

18. Doughty, MJ, Aakre, BM. Further analysis of assessments of the coefficient of variation of corneal endothelial cell areas from specular microscopic images. Clin Exp Optom 2008;91:438–46. https://doi.org/10.1111/j.1444-0938.2008.00281.x.Search in Google Scholar PubMed

19. Foracchia, M, Ruggeri, A. Corneal endothelium cell field analysis by means of interacting Bayesian shape models. In: 2007 29th annual international conference of the IEEE engineering in medicine and biology society. IEEE; 2007:6035–8 pp.10.1109/IEMBS.2007.4353724Search in Google Scholar PubMed

20. Ren, S, He, K, Girshick, R, Sun, J. Faster R-CNN: towards real-time object detection with region proposal networks. In: Cortes, C, Lawrence, N, Lee, D, Sugiyama, M, Garnett, R, editors. Advances in neural information processing systems, vol 28. Curran Associates, Inc.; 2015. Available from: https://proceedings.neurips.cc/paper/2015/file/14bfa6bb14875e45bba028a21ed38046-Paper.pdf.Search in Google Scholar

21. Ipek, BM, Altun, HO, Öztoprak, K. Towards fully automated detection of epileptic disorders: a novel CNSVM approach with Clough–Tocher interpolation. Biomed Eng/Biomed Tech 2022;67:151–9. https://doi.org/10.1515/bmt-2021-0170.Search in Google Scholar PubMed

22. Hosseini, SH, Chen, H, Jablonski, MM. Automatic detection and counting of retina cell nuclei using deep learning. In: Medical imaging 2020: biomedical applications in molecular, structural, and functional imaging. Houston, Texas: SPIE; 2020, 11317:634–46 pp.10.1117/12.2567454Search in Google Scholar

23. Shilpashree, PS, Suresh, KV, Sudhir, RR, Srinivas, SP. Automated image segmentation of the corneal endothelium in patients with Fuchs dystrophy. Transl Vision Sci Technol 2021;10:27–. https://doi.org/10.1167/tvst.10.13.27.Search in Google Scholar PubMed PubMed Central

24. Bustamante-Arias, A, Cheddad, A, Jimenez-Perez, JC, Rodriguez-Garcia, A. Digital image processing and development of machine learning models for the discrimination of corneal pathology: an experimental model. Photonics 2021;8:118. https://doi.org/10.3390/photonics8040118.Search in Google Scholar

25. Karmakar, R, Nooshabadi, SV, Eghrari, AO. Mobile-CellNet: automatic segmentation of corneal endothelium using an efficient hybrid deep learning model. Cornea 2023;42:456–63. https://doi.org/10.1097/ico.0000000000003186.Search in Google Scholar PubMed PubMed Central

26. Scarpa, F, Ruggeri, A. Segmentation of corneal endothelial cells contour by means of a genetic algorithm. In: Ophthalmic medical image analysis international workshop. Iowa City: University of Iowa; 2015, 2.10.17077/omia.1023Search in Google Scholar

27. Jameel, SK, Aydin, S, Ghaeb, NH, Majidpour, J, Rashid, TA, Salih, SQ, et al.. Exploiting the generative adversarial network approach to create a synthetic topography corneal image. Biomolecules 2022;12:1888. https://doi.org/10.3390/biom12121888.Search in Google Scholar PubMed PubMed Central

28. Alam, U, Anson, M, Meng, Y, Preston, F, Kirthi, V, Jackson, TL, et al.. Artificial intelligence and corneal confocal microscopy: the start of a beautiful relationship. J Clin Med 2022;11:6199. https://doi.org/10.3390/jcm11206199.Search in Google Scholar PubMed PubMed Central

29. Salahouddin, T, Petropoulos, IN, Ferdousi, M, Ponirakis, G, Asghar, O, Alam, U, et al.. Artificial intelligence–based classification of diabetic peripheral neuropathy from corneal confocal microscopy images. Diabetes Care 2021;44:e151. https://doi.org/10.2337/dc20-2012.Search in Google Scholar PubMed PubMed Central

Received: 2023-03-27
Accepted: 2024-02-28
Published Online: 2024-03-18
Published in Print: 2024-10-28

© 2024 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Research Articles
  3. Sparse-view CT reconstruction based on group-based sparse representation using weighted guided image filtering
  4. Comparative evaluation of volumetry estimation from plain and contrast enhanced computed tomography liver images
  5. Vein segmentation and visualization of upper and lower extremities using convolution neural network
  6. STF-Net: sparsification transformer coding guided network for subcortical brain structure segmentation
  7. Machine learning based endothelial cell image analysis of patients undergoing descemet membrane endothelial keratoplasty surgery
  8. AML leukocyte classification method for small samples based on ACGAN
  9. Deep learning classification of EEG-based BCI monitoring of the attempted arm and hand movements
  10. Hybrid method for noise rejection from breath sound using transient artifact reduction algorithm and spectral subtraction
  11. Optimized Schlieren imaging for real-time visualization of high-intensity focused ultrasound waves
https://doi.org/10.1515/bmt-2023-0126
Keywords for this article
DMEK; deep learning; automatic detection of endothelial cell boundaries; R-CNN

Articles in the same Issue

  1. Frontmatter
  2. Research Articles
  3. Sparse-view CT reconstruction based on group-based sparse representation using weighted guided image filtering
  4. Comparative evaluation of volumetry estimation from plain and contrast enhanced computed tomography liver images
  5. Vein segmentation and visualization of upper and lower extremities using convolution neural network
  6. STF-Net: sparsification transformer coding guided network for subcortical brain structure segmentation
  7. Machine learning based endothelial cell image analysis of patients undergoing descemet membrane endothelial keratoplasty surgery
  8. AML leukocyte classification method for small samples based on ACGAN
  9. Deep learning classification of EEG-based BCI monitoring of the attempted arm and hand movements
  10. Hybrid method for noise rejection from breath sound using transient artifact reduction algorithm and spectral subtraction
  11. Optimized Schlieren imaging for real-time visualization of high-intensity focused ultrasound waves
Downloaded on 22.4.2026 from https://www.degruyterbrill.com/document/doi/10.1515/bmt-2023-0126/html
Scroll to top button