Automatic Segmentation of Corneal Endothelium Images with Convolutional Neural Network

  • Karolina NurzynskaEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 928)


A fully-automatic segmentation of corneal endothelial images is addressed in this paper. It can find its application in the medicine removing the burden of manual annotations from the physicians allowing for faster patient diagnosis. The proposed system is based on pre-trained convolutional neural network AlexNet and uses a transfer learning methodology to build a system for delineation of endothelial cells. The training is based on the classification of small patches of an image which represents cell body or cell border class. The validation set proved that 99% correct classification ratio accuracy and F1 score were achieved. Exploiting this network in a system configured for segmentation it proved very good detection of cell bodies and supported by best-fit skeletonization allowed to locate cell borders precisely.


Corneal endothelium images Convolutional neural network Segmentation Classification 



This work was supported by statutory funds for young researchers (BKM-509 /RAU2/2017) of the Institute of Informatics, Silesian University of Technology, Poland.


  1. 1.
    Agarwal, S., Agarwal, A., Apple, D., Buratto, L.: Textbook of Ophthalmology, vol. 2. Jaypee Brothers, Medical Publishers Ltd., New Dehli (2002)Google Scholar
  2. 2.
    Charlampowicz, K., Reska, D., Boldak, C.: Automatic segmentation of corneal endothelial cells using active contours. In: Advances in Computer Science Research, vol. 14, pp. 47–60 (2014)Google Scholar
  3. 3.
    Dagher, I., El Tom, K.: Waterballoons: a hybrid watershed balloon snake segmentation. Image Vis. Comput. 26(7), 905–912 (2008)CrossRefGoogle Scholar
  4. 4.
    Fabijanska, A.: Corneal endothelium image segmentation using feed forward neural network. In: 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), pp. 629–637 (2017)Google Scholar
  5. 5.
    Foracchia, M., Ruggeri, A.: Corneal endothelium analysis by means of Bayesian shape modeling. In: Proceedings of the 25th Annual International Conference of the IEEE-EMBS, pp. 794–797. IEEE (2003)Google Scholar
  6. 6.
    Habrat, K., Habrat, M., Gronkowska-Serafin, J., Piórkowski, A.: Cell detection in corneal endothelial images using directional filters. In: Choraś, R.S. (ed.) Image Processing and Communications Challenges 7. AISC, vol. 389, pp. 113–123. Springer, Cham (2016). Scholar
  7. 7.
    Hoppenreijs, V., Pels, E., Vrensen, G., Treffers, W.: Corneal endothelium and growth factors. Surv. Ophthalmol. 41(2), 155–164 (1996)CrossRefGoogle Scholar
  8. 8.
    Katafuchi, S., Yoshimura, M.: Convolution neural network for contour extraction of corneal endothelial cells. Proc. SPIE 10338, 7 (2017)Google Scholar
  9. 9.
    Khan, M.A.U., Niazi, M.K.K., Khan, M.A., Ibrahim, M.T.: Endothelial cell image enhancement using non-subsampled image pyramid. Inf. Technol. J. 6(7), 1057–1062 (2007)CrossRefGoogle Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, NIPS 2012, pp. 1097–1105. Curran Associates Inc., USA (2012)Google Scholar
  11. 11.
    Meyer, L., Ubels, J., Edelhauser, H.: Corneal endothelial morphology in the rat. Invest. Ophthalmol. Vis. Sci. 29(6), 940–949 (1988)Google Scholar
  12. 12.
    Nadachi, R., Nunokawa, K.: Automated corneal endothelial cell analysis. In: Proceedings of Fifth Annual IEEE Symposium on Computer-Based Medical Systems, pp. 450–457. IEEE (1992)Google Scholar
  13. 13.
    Piórkowski, A.: A statistical dominance algorithm for edge detection and segmentation of medical images. In: Piętka, E., Badura, P., Kawa, J., Wieclawek, W. (eds.) Information Technologies in Medicine. AISC, vol. 471, pp. 3–14. Springer, Cham (2016). Scholar
  14. 14.
    Piórkowski, A.: Best-fit segmentation created using flood-based iterative thinning. In: Choraś, R. (ed.) IP&C 2016. AISC, vol. 525, pp. 61–68. Springer, Cham (2017). Scholar
  15. 15.
    Piorkowski, A., Nurzynska, K., Gronkowska-Serafin, J., Selig, B., Boldak, C., Reska, D.: Influence of applied corneal endothelium image segmentation techniques on the clinical parameters. Comput. Med. Imaging Graph. 55(Suppl. C), 13–27 (2017). Special Issue on Ophthalmic Medical Image AnalysisCrossRefGoogle Scholar
  16. 16.
    Ruggeri, A., Scarpa, F.: Computerized analysis of human corneal endothelium morphology. Acta Ophthalmol. 93 (2015).
  17. 17.
    Ruggeri, A., Scarpa, F., De Luca, M., Meltendorf, C., Schroeter, J.: A system for the automatic estimation of morphometric parameters of corneal endothelium in alizarine red stained images. Br. J. Ophthalmol. 94(5), 643 (2010)CrossRefGoogle Scholar
  18. 18.
    Starosolski, R.: New simple and efficient color space transformations for lossless image compression. J. Vis. Commun. Image Represent. 25(5), 1056–1063 (2014). Scholar
  19. 19.
    Vincent, L.M., Masters, B.R.: Morphological image processing and network analysis of cornea endothelial cell images. In: San Diego 1992, vol. 1769, pp. 212–226. International Society for Optics and Photonics (1992)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Institute of InformaticsSilesian University of TechnologyGliwicePoland

Personalised recommendations