{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T07:12:25Z","timestamp":1793862745359,"version":"4.6.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T00:00:00Z","timestamp":1710720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eye and Vis"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>To describe the diagnostic performance of a deep learning (DL) algorithm in detecting Fuchs endothelial corneal dystrophy (FECD) based on specular microscopy (SM) and to reliably detect widefield peripheral SM images with an endothelial cell density (ECD) &gt;\u20091000\u00a0cells\/mm<jats:sup>2<\/jats:sup>.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Methods<\/jats:title>\n                <jats:p>Five hundred and forty-seven subjects had SM imaging performed for the central cornea endothelium. One hundred and seventy-three images had FECD, while 602 images had other diagnoses. Using fivefold cross-validation on the dataset containing 775 central SM images combined with ECD, coefficient of variation (CV) and hexagonal endothelial cell ratio (HEX), the first DL model was trained to discriminate FECD from other images and was further tested on an external set of 180 images. In eyes with FECD, a separate DL model was trained with 753 central\/paracentral SM images to detect SM with ECD &gt;\u20091000\u00a0cells\/mm<jats:sup>2<\/jats:sup> and tested on 557 peripheral SM images. Area under curve (AUC), sensitivity and specificity were evaluated.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>The first model achieved an AUC of 0.96 with 0.91 sensitivity and 0.91 specificity in detecting FECD from other images. With an external validation set, the model achieved an AUC of 0.77, with a sensitivity of 0.69 and specificity of 0.68 in differentiating FECD from other diagnoses. The second model achieved an AUC of 0.88 with 0.79 sensitivity and 0.78 specificity in detecting peripheral SM images with ECD &gt;\u20091000\u00a0cells\/mm<jats:sup>2<\/jats:sup>.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Our pilot study developed a DL model that could reliably detect FECD from other SM images and identify widefield SM images with ECD &gt;\u20091000\u00a0cells\/mm<jats:sup>2<\/jats:sup> in eyes with FECD. This could be the foundation for future DL models to track progression of eyes with FECD and identify candidates suitable for therapies such as Descemet stripping only.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s40662-024-00378-1","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T03:01:46Z","timestamp":1710730906000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Deep learning for detection of Fuchs endothelial dystrophy from widefield specular microscopy imaging: a pilot\nstudy"],"prefix":"10.1186","volume":"11","author":[{"given":"Valencia Hui Xian","family":"Foo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gilbert Y. S.","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Chi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hon Shing","family":"Ong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Evan","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stacy","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jipson","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jodhbir S.","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel S. W.","family":"Ting","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3022-0795","authenticated-orcid":false,"given":"Marcus","family":"Ang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,18]]},"reference":[{"issue":"6","key":"378_CR1","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1016\/0002-9394(67)93073-5","volume":"64","author":"DW Lorenzetti","year":"1967","unstructured":"Lorenzetti DW, Uotila MH, Parikh N, Kaufman HE. Central cornea guttata. Incidence in the general population. Am J Ophthalmol. 1967;64(6):1155\u20138.","journal-title":"Am J Ophthalmol"},{"issue":"10","key":"378_CR2","doi-asserted-by":"publisher","first-page":"1166","DOI":"10.1097\/ICO.0000000000001292","volume":"36","author":"ZA Syed","year":"2017","unstructured":"Syed ZA, Tran JA, Jurkunas UV. Peripheral endothelial cell count is a predictor of disease severity in advanced Fuchs endothelial corneal dystrophy. Cornea. 2017;36(10):1166\u201371.","journal-title":"Cornea"},{"key":"378_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1146\/annurev-vision-102016-061400","volume":"3","author":"MO Price","year":"2017","unstructured":"Price MO, Gupta P, Lass J, Price FW Jr. EK (DLEK, DSEK, DMEK): new frontier in cornea surgery. Annu Rev Vis Sci. 2017;3:69\u201390.","journal-title":"Annu Rev Vis Sci"},{"key":"378_CR4","doi-asserted-by":"publisher","first-page":"100768","DOI":"10.1016\/j.preteyeres.2019.07.001","volume":"73","author":"D Hos","year":"2019","unstructured":"Hos D, Matthaei M, Bock F, Maruyama K, Notara M, Clahsen T, et al. Immune reactions after modern lamellar (DALK, DSAEK, DMEK) versus conventional penetrating corneal transplantation. Prog Retin Eye Res. 2019;73:100768.","journal-title":"Prog Retin Eye Res"},{"issue":"2","key":"378_CR5","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1001\/jamaophthalmol.2015.4776","volume":"134","author":"P Gain","year":"2016","unstructured":"Gain P, Jullienne R, He Z, Aldossary M, Acquart S, Cognasse F, et al. Global survey of corneal transplantation and eye banking. JAMA Ophthalmol. 2016;134(2):167\u201373.","journal-title":"JAMA Ophthalmol"},{"issue":"6","key":"378_CR6","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1097\/ICO.0000000000001209","volume":"36","author":"G Moloney","year":"2017","unstructured":"Moloney G, Petsoglou C, Ball M, Kerdraon Y, H\u00f6llhumer R, Spiteri N, et al. Descemetorhexis without grafting for Fuchs endothelial dystrophy-supplementation with topical ripasudil. Cornea. 2017;36(6):642\u20138.","journal-title":"Cornea"},{"issue":"4","key":"378_CR7","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1097\/ICU.0000000000000579","volume":"30","author":"D Garcerant","year":"2019","unstructured":"Garcerant D, Hirnschall N, Toalster N, Zhu M, Wen L, Moloney G. Descemet\u2019s stripping without endothelial keratoplasty. Curr Opin Ophthalmol. 2019;30(4):275\u201385.","journal-title":"Curr Opin Ophthalmol"},{"issue":"1","key":"378_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/ICO.0b013e31815892da","volume":"27","author":"BE McCarey","year":"2008","unstructured":"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):1\u201316.","journal-title":"Cornea"},{"key":"378_CR9","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/B978-0-323-06387-6.00021-0","volume-title":"Cornea: fundamentals, diagnosis and management","author":"BA Benetz","year":"2011","unstructured":"Benetz BA, Yee R, Bidros M, Lass J. Specular microscopy. In: Krachmer JH, Mannis MJ, Holland EJ, editors. Cornea: fundamentals, diagnosis and management. 3rd ed. New York: Elsevier Inc.; 2011. p. 177\u2013203.","edition":"3"},{"issue":"9","key":"378_CR10","doi-asserted-by":"publisher","first-page":"1188","DOI":"10.1097\/ICO.0000000000002975","volume":"41","author":"N Din","year":"2022","unstructured":"Din N, Cohen E, Popovic M, Mimouni M, Trinh T, Gouvea L, et al. Surgical management of Fuchs endothelial corneal dystrophy: a treatment algorithm and individual patient meta-analysis of Descemet stripping only. Cornea. 2022;41(9):1188\u201395.","journal-title":"Cornea"},{"issue":"13","key":"378_CR11","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1167\/tvst.10.13.27","volume":"10","author":"PS Shilpashree","year":"2021","unstructured":"Shilpashree PS, Suresh KV, Sudhir RR, Srinivas SP. Automated image segmentation of the corneal endothelium in patients with Fuchs dystrophy. Transl Vis Sci Technol. 2021;10(13):27.","journal-title":"Transl Vis Sci Technol"},{"issue":"1","key":"378_CR12","doi-asserted-by":"publisher","first-page":"14035","DOI":"10.1038\/s41598-022-18180-1","volume":"12","author":"JP Vigueras-Guill\u00e9n","year":"2022","unstructured":"Vigueras-Guill\u00e9n JP, van Rooij J, van Dooren BTH, Lemij HG, Islamaj E, van Vliet LJ, et al. Dense UNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae. Sci Rep. 2022;12(1):14035.","journal-title":"Sci Rep"},{"key":"378_CR13","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/s42490-019-0003-2","volume":"1","author":"JP Vigueras-Guill\u00e9n","year":"2019","unstructured":"Vigueras-Guill\u00e9n JP, Sari B, Goes SF, Lemij HG, van Rooij J, Vermeer KA, et al. Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation. BMC Biomed Eng. 2019;1:4.","journal-title":"BMC Biomed Eng"},{"issue":"1","key":"378_CR14","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1364\/BOE.477495","volume":"14","author":"JS Sierra","year":"2022","unstructured":"Sierra JS, Pineda J, Rueda D, Tello A, Prada AM, Galvis V, et al. Corneal endothelium assessment in specular microscopy images with Fuchs\u2019 dystrophy via deep regression of signed distance maps. Biomed Opti Express. 2022;14(1):335\u201341.","journal-title":"Biomed Opti Express"},{"key":"378_CR15","doi-asserted-by":"crossref","unstructured":"Sierra JS, Castro JDP, Meza J, Rueda D, Berrospi RD, Tello A, et al. Deep learning for robust segmentation of corneal endothelium images in the presence of cornea guttata. In: Emerging Topics in Artificial Intelligence (ETAI) International Society for Optics and Photonics. USA: San Diego. 2021. Vol. 11804, p. 118041F.","DOI":"10.1117\/12.2594231"},{"issue":"4","key":"378_CR16","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1007\/s00417-021-05483-8","volume":"260","author":"R Karmakar","year":"2022","unstructured":"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. 2022;260(4):1215\u201324.","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"378_CR17","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.ajo.2022.02.026","volume":"239","author":"JH Qu","year":"2022","unstructured":"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\u201353.","journal-title":"Am J Ophthalmol"},{"issue":"4","key":"378_CR18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1167\/tvst.12.4.8","volume":"12","author":"N Tang","year":"2023","unstructured":"Tang N, Huang G, Lei D, Jiang L, Chen Q, He W, et al. A hybrid system for automatic identification of corneal layers on in vivo confocal microscopy images. Transl Vis Sci Technol. 2023;12(4):8.","journal-title":"Transl Vis Sci Technol"},{"issue":"3","key":"378_CR19","doi-asserted-by":"publisher","first-page":"60","DOI":"10.3390\/sym10030060","volume":"10","author":"K Nurzynska","year":"2018","unstructured":"Nurzynska K. Deep learning as a tool for automatic segmentation of corneal endothelium images. Symmetry. 2018;10(3):60.","journal-title":"Symmetry"},{"issue":"7","key":"378_CR20","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1097\/ICO.0000000000002956","volume":"41","author":"N Okumura","year":"2022","unstructured":"Okumura N, Yamada S, Nishikawa T, Narimoto K, Okamura K, Izumi A, et al. U-Net convolutional neural network for segmenting the corneal endothelium in a mouse model of Fuchs endothelial corneal dystrophy. Cornea. 2022;41(7):901\u20137.","journal-title":"Cornea"},{"issue":"1","key":"378_CR21","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1073\/pnas.1912546116","volume":"117","author":"C Liu","year":"2020","unstructured":"Liu C, Miyajima T, Melangath G, Miyai T, Vasanth S, Deshpande N, et al. Ultraviolet A light induces DNA damage and estrogen-DNA adducts in Fuchs endothelial corneal dystrophy causing females to be more affected. Proc Natl Acad Sci USA. 2020;117(1):573\u201383.","journal-title":"Proc Natl Acad Sci USA"},{"issue":"8","key":"378_CR22","doi-asserted-by":"publisher","first-page":"5090","DOI":"10.1167\/iovs.14-14249","volume":"55","author":"H Fujimoto","year":"2014","unstructured":"Fujimoto H, Maeda N, Soma T, Oie Y, Koh S, Tsujikawa M, et al. Quantitative regional differences in corneal endothelial abnormalities in the central and peripheral zones in Fuchs\u2019 endothelial corneal dystrophy. Invest Ophthalmol Vis Sci. 2014;55(8):5090\u20138.","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"1","key":"378_CR23","doi-asserted-by":"publisher","first-page":"4752","DOI":"10.1038\/s41598-019-41034-2","volume":"9","author":"MC Daniel","year":"2019","unstructured":"Daniel MC, Atzrodt L, Bucher F, Wacker K, B\u00f6hringer S, Reinhard T, et al. Automated segmentation of the corneal endothelium in a large set of \u2018real-world\u2019 specular microscopy images using the U-Net architecture. Sci Rep. 2019;9(1):4752.","journal-title":"Sci Rep"},{"issue":"3","key":"378_CR24","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1097\/APO.0000000000000394","volume":"10","author":"R Rampat","year":"2021","unstructured":"Rampat R, Deshmukh R, Chen X, Ting DSW, Said DG, Dua HS, et al. Artificial intelligence in cornea, refractive surgery, and cataract: basic principles, clinical applications, and future directions. Asia Pac J Ophthalmol (Phila). 2021;10(3):268\u201381.","journal-title":"Asia Pac J Ophthalmol (Phila)"},{"issue":"12","key":"378_CR25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1167\/tvst.11.12.19","volume":"11","author":"K Bitton","year":"2022","unstructured":"Bitton K, Z\u00e9boulon P, Ghazal W, Rizk M, Elahi S, Gatinel D. Deep learning model for the detection of corneal edema before Descemet membrane endothelial keratoplasty on optical coherence tomography images. Transl Vis Sci Technol. 2022;11(12):19.","journal-title":"Transl Vis Sci Technol"},{"issue":"2","key":"378_CR26","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1167\/tvst.9.2.49","volume":"9","author":"JP Vigueras-Guill\u00e9n","year":"2020","unstructured":"Vigueras-Guill\u00e9n JP, van Rooij J, Engel A, Lemij HG, van Vliet LJ, Vermeer KA. Deep learning for assessing the corneal endothelium from specular microscopy images up to 1 year after ultrathin-DSAEK surgery. Trans Vis Sci Tech. 2020;9(2):49.","journal-title":"Trans Vis Sci Tech"},{"issue":"2","key":"378_CR27","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1097\/ICO.0000000000001776","volume":"38","author":"M Treder","year":"2019","unstructured":"Treder M, Lauermann JL, Alnawaiseh M, Eter N. Using deep learning in automated detection of graft detachment in Descemet membrane endothelial keratoplasty: a pilot study. Cornea. 2019;38(2):157\u201361.","journal-title":"Cornea"},{"issue":"2","key":"378_CR28","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1097\/ICL.0000000000000634","volume":"46","author":"T Hayashi","year":"2020","unstructured":"Hayashi T, Tabuchi H, Masumoto H, Morita S, Oyakawa I, Inoda S, et al. A deep learning approach in rebubbling after Descemet\u2019s membrane endothelial keratoplasty. Eye Contact Lens. 2020;46(2):121\u20136.","journal-title":"Eye Contact Lens"},{"issue":"11","key":"378_CR29","doi-asserted-by":"publisher","first-page":"2036","DOI":"10.1001\/archopht.1978.03910060424004","volume":"96","author":"JH Krachmer","year":"1978","unstructured":"Krachmer JH, Purcell JJ, Young CW, Bucher KD. Corneal endothelial dystrophy: a study of 64 families. Arch Ophthalmol. 1978;96(11):2036\u20139.","journal-title":"Arch Ophthalmol"}],"container-title":["Eye and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40662-024-00378-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s40662-024-00378-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s40662-024-00378-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T03:02:04Z","timestamp":1710730924000},"score":1,"resource":{"primary":{"URL":"https:\/\/eandv.biomedcentral.com\/articles\/10.1186\/s40662-024-00378-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["378"],"URL":"https:\/\/doi.org\/10.1186\/s40662-024-00378-1","relation":{},"ISSN":["2326-0254"],"issn-type":[{"value":"2326-0254","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,18]]},"assertion":[{"value":"1 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethics review and institutional board exemption were obtained from the SingHealth Institutional Review Board (IRB number 2018\/2008).","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interest. No conflicting relationship exists for any author.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"11"}}