{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T09:33:10Z","timestamp":1785576790422,"version":"3.56.0"},"reference-count":40,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2018,3,6]],"date-time":"2018-03-06T00:00:00Z","timestamp":1520294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sileian University of Technology","award":["BKM-509\/RAU2\/2017"],"award-info":[{"award-number":["BKM-509\/RAU2\/2017"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The automatic analysis of the state of the corneal endothelium is of much interest in ophthalmology. Up till now, several manual and semi-automatic methods have been introduced, but the need of fully-automatic segmentation of cells in the endothelium is still in search. This work addresses the problem of automatic delineation of cells in the corneal endothelium images and suggests to use the convolutional neural network (CNN) to classify between cell center, cell body, and cell border in order to achieve precise segmentation. Additionally, a method to automatically select and split merged cells is given. In order to skeletonize the result, the best-fit method is used. The achieved outcomes are compared to manual annotations in order to define the mutual overlapping. The Dice index, Jaccard coefficient, modified Hausdorff distance, and several other metrics for mosaic overlapping are used. As a final check-up, the visual inspection is shown. The performed experiments revealed the best architecture for CNN. The correctness and precision of the segmentation were evaluated on Endothelial Cell \u201cAlizarine\u201d dataset. According to the Dice index and Jaccard coefficient, the automatically achieved cell delineation overlaps the original one with 93% precision. While modified Hausdorff distance shows 0.14 pixel distance, proving very high accuracy. These findings are confirmed by other metrics and also supported by presented visual inspection of achieved segmentations. To conclude, the methodology to achieve fully-automatic delineation of cell boundaries in the corneal endothelium images was presented. The segmentation obtained as a result of pixel classification with CNN proved very high precision.<\/jats:p>","DOI":"10.3390\/sym10030060","type":"journal-article","created":{"date-parts":[[2018,3,6]],"date-time":"2018-03-06T12:16:27Z","timestamp":1520338587000},"page":"60","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Deep Learning as a Tool for Automatic Segmentation of Corneal Endothelium Images"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5137-5732","authenticated-orcid":false,"given":"Karolina","family":"Nurzynska","sequence":"first","affiliation":[{"name":"Institute of Informatics, Department of Automatic Control, Electronics and Computer Science, Silesian University of Technology, 44-100 Gliwice, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2018,3,6]]},"reference":[{"key":"ref_1","unstructured":"Agarwal, S., Agarwal, A., Apple, D., and Buratto, L. (2002). Textbook of Ophthalmology, Jaypee Brothers, Medical Publishers Ltd."},{"key":"ref_2","first-page":"940","article-title":"Corneal endothelial morphology in the rat","volume":"29","author":"Meyer","year":"1988","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_3","first-page":"271","article-title":"Cell size-shape relationships in corneal endothelium","volume":"22","author":"Rao","year":"1982","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1016\/0892-8967(90)90064-M","article-title":"The ambiguous coefficient of variation: Polymegethism of the corneal endothelium and central corneal thickness","volume":"17","author":"Doughty","year":"1990","journal-title":"Int. Contact Lens Clin."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/0014-4835(92)90102-X","article-title":"Concerning the symmetry of the hexagonal cells of the corneal endothelium","volume":"55","author":"Doughty","year":"1992","journal-title":"Exp. Eye Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Mazurek, P. (September, January 29). Cell structures modeling using fractal generator and torus geometry. Proceedings of the 2016 21st International Conference on Methods and Models in Automation and Robotics (MMAR), Miedzyzdroje, Poland.","DOI":"10.1109\/MMAR.2016.7575230"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"149","DOI":"10.5566\/ias.1554","article-title":"The correlation analysis of the shape parameters for endothelial image characterisation","volume":"35","author":"Nurzynska","year":"2016","journal-title":"Image Anal. Stereol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1002\/met.299","article-title":"Shape parameters for automatic classification of snow particles into snowflake and graupel","volume":"20","author":"Nurzynska","year":"2013","journal-title":"Meteorol. Appl."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Vincent, L.M., and Masters, B.R. (1992, January 1). Morphological image processing and network analysis of cornea endothelial cell images. Proceedings of the International Society for Optics and Photonics, San Diego, CA, USA.","DOI":"10.1117\/12.60644"},{"key":"ref_10","unstructured":"Caetano, C.A.C., Entura, L., Sousa, S.J., and Tufo, R.E.A. (2000, January 17\u201320). Identification and segmentation of cells in images of donated corneas using mathematical morphology. Proceedings of the XIII Brazilian Symposium on Computer Graphics and Image Processing, Gramado, Brazil."},{"key":"ref_11","first-page":"309","article-title":"Exact Evaluation of Stochastic Watersheds: From Trees to General Graphs","volume":"Volume 8668","author":"Barcucci","year":"2014","journal-title":"Discrete Geometry for Computer Imagery"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1016\/j.patrec.2013.02.012","article-title":"Improving the Stochastic Watershed","volume":"34","author":"Bernander","year":"2013","journal-title":"Pattern Recognit. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Selig, B., Malmberg, F., and Luengo Hendriks, C.L. (2015, January 27\u201329). Fast evaluation of the robust stochastic watershed. Proceedings of the 12th International Syposium on Mathematical Morphology Mathematical Morphology and Its Applications to Signal and Image Processing, Lecture Notes in Computer Science, Reykjavik, Iceland.","DOI":"10.1007\/978-3-319-18720-4_59"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Selig, B., Vermeer, K.A., Rieger, B., Hillenaar, T., and Hendriks, C.L.L. (2015). Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy. BMC Med. Imaging, 15.","DOI":"10.1186\/s12880-015-0054-3"},{"key":"ref_15","first-page":"56","article-title":"Detection and complement of hexagonal borders in corneal endothelial cell image","volume":"14","author":"Mahzoun","year":"1996","journal-title":"Med. Imaging Technol."},{"key":"ref_16","unstructured":"Serra, J., and Mlynarczuk, M. (2000, January 20\u201323). Morphological merging of multidimensional data. Proceedings of the STERMAT 2000, Krakow, Poland."},{"key":"ref_17","unstructured":"Foracchia, M., and Ruggeri, A. (2003, January 17\u201321). Corneal endothelium analysis by means of Bayesian shape modeling. Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Cancun, Mexico."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Foracchia, M., and Ruggeri, A. (2007, January 22\u201326). Corneal Endothelium Cell Field Analysis by means of Interacting Bayesian Shape Models. Proceedings of the 29th Annual International Conference of the Engineering in Medicine and Biology Society, Lyon, France.","DOI":"10.1109\/IEMBS.2007.4353724"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1049\/iet-ipr.2009.0178","article-title":"Noise adaptive switching median-based filter for impulse noise removal from extremely corrupted images","volume":"5","author":"Sankowski","year":"2011","journal-title":"IET Image Process."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/978-3-319-23814-2_14","article-title":"Cell detection in corneal endothelial images using directional filters","volume":"Volume 389","author":"Habrat","year":"2016","journal-title":"Image Processing and Communications Challenges 7"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"905","DOI":"10.1016\/j.imavis.2007.10.010","article-title":"WaterBalloons: A hybrid watershed Balloon Snake segmentation","volume":"26","author":"Dagher","year":"2008","journal-title":"Image Vis. Comput."},{"key":"ref_22","first-page":"47","article-title":"Automatic segmentation of corneal endothelial cells using active contours","volume":"14","author":"Charlampowicz","year":"2014","journal-title":"Adv. Comput. Sci. Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.bbe.2014.02.003","article-title":"MESA: Complete approach for design and evaluation of segmentation methods using real and simulated tomographic images","volume":"34","author":"Reska","year":"2014","journal-title":"Biocybern. Biomed. Eng."},{"key":"ref_24","unstructured":"Zhou, Y. (2007). Cell Segmentation Using Level Set Method. [Master\u2019s Thesis, Johannes Kepler Universitat]."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.3923\/itj.2007.1057.1062","article-title":"Endothelial Cell Image Enhancement using Non-subsampled Image Pyramid","volume":"6","author":"Khan","year":"2007","journal-title":"Inf. Technol. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s10561-017-9622-9","article-title":"Morphometry of organ cultured corneal endothelium using Voronoi segmentation","volume":"18","author":"Brookes","year":"2017","journal-title":"Cell Tissue Bank."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/978-3-319-10662-5_22","article-title":"Towards Automated Cell Segmentation in Corneal Endothelium Images","volume":"Volume 313","author":"Piorkowski","year":"2015","journal-title":"Image Processing and Communications Challenges 6"},{"key":"ref_28","first-page":"61","article-title":"Best-Fit Segmentation Created Using Flood-Based Iterative Thinning","volume":"Volume 525","year":"2017","journal-title":"Image Processing and Communications Challenges 8. IP&C 2016"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"317","DOI":"10.2478\/v10006-010-0024-4","article-title":"K3M: A universal algorithm for image skeletonization and a review of thinning techniques","volume":"20","author":"Saeed","year":"2010","journal-title":"Int. J. Appl. Math. Comput. Sci."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1016\/0893-6080(95)00054-2","article-title":"Generalization of shift invariant neural networks: image processing of corneal endothelium","volume":"9","author":"Hasegawa","year":"1996","journal-title":"Neural Netw."},{"key":"ref_31","unstructured":"Foracchia, M., and Ruggeri, A. (2000, January 23\u201328). Cell contour detection in corneal endothelium in-vivo microscopy. Proceedings of the 22nd Annual International Conference of the Engineering in Medicine and Biology Society, Chicago, IL, USA."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1136\/bjo.2009.166561","article-title":"A system for the automatic estimation of morphometric parameters of corneal endothelium in alizarine red stained images","volume":"94","author":"Ruggeri","year":"2010","journal-title":"Br. J. Ophthalmol."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Katafuchi, S., and Yoshimura, M. (2017, January 14). Convolution neural network for contour extraction of corneal endothelial cells. Proceedings of the 13th International Conference on Quality Control by Artificial Vision, Tokyo, Japan.","DOI":"10.1117\/12.2264430"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Fabijanska, A. (2017, January 3\u20136). Corneal endothelium image segmentation using feedforward neural network. Proceedings of the 2017 Federated Conference on Computer Science and Information Systems (FedCSIS), Prague, Check Republic.","DOI":"10.15439\/2017F54"},{"key":"ref_35","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.compmedimag.2016.07.010","article-title":"Influence of applied corneal endothelium image segmentation techniques on the clinical parameters","volume":"55","author":"Piorkowski","year":"2017","journal-title":"Comput. Med. Imaging Gr."},{"key":"ref_37","unstructured":"Gavet, Y., and Pinoli, J.C. (2018, January 12). Human visual perception and dissimilarity. Available online: http:\/\/spie.org\/newsroom\/4338-human-visual-perception-and-dissimilarity."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the Amount of Ecologic Association Between Species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"ref_39","unstructured":"Dubuisson, M.P., and Jain, A. (1994, January 9\u201313). A modified Hausdorff distance for object matching. Proceedings of the 12th IAPR International Conference on Pattern Recognition, Jerusalem, Israel."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/s10851-011-0272-4","article-title":"A Geometric Dissimilarity Criterion Between Jordan Spatial Mosaics. Theoretical Aspects and Application to Segmentation Evaluation","volume":"42","author":"Gavet","year":"2012","journal-title":"J. Math. Imaging Vis."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/10\/3\/60\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T14:57:41Z","timestamp":1760194661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/10\/3\/60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,3,6]]},"references-count":40,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,3]]}},"alternative-id":["sym10030060"],"URL":"https:\/\/doi.org\/10.3390\/sym10030060","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,3,6]]}}}