{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T14:21:52Z","timestamp":1794061312301,"version":"4.8.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T00:00:00Z","timestamp":1599004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T00:00:00Z","timestamp":1599004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Chang Gung Research Proposal","award":["CMRPG8H0971"],"award-info":[{"award-number":["CMRPG8H0971"]}]},{"name":"Chang Gung Research Proposal","award":["CMRPG8H0971"],"award-info":[{"award-number":["CMRPG8H0971"]}]},{"name":"Chang Gung Research Proposal","award":["CMRPG8H0971"],"award-info":[{"award-number":["CMRPG8H0971"]}]},{"name":"Ministry of Science and Technology","award":["MOST 107-2314-B-182A-091-MY2"],"award-info":[{"award-number":["MOST 107-2314-B-182A-091-MY2"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Fungal keratitis (FK) is the most devastating and vision-threatening microbial keratitis, but clinical diagnosis a great challenge. This study aimed to develop and verify a deep learning (DL)-based corneal photograph model for diagnosing FK. Corneal photos of laboratory-confirmed microbial keratitis were consecutively collected from a single referral center. A DL framework with DenseNet architecture was used to automatically recognize FK from the photo. The diagnoses of FK via corneal photograph for comparing DL-based models were made in the Expert and NCS-Oph group through a majority decision of three non-corneal specialty ophthalmologist and three corneal specialists, respectively. The average percentage of sensitivity, specificity, positive predictive value, and negative predictive value was approximately 71, 68, 60, and 78. The sensitivity was higher than that of the NCS-Oph (52%, <jats:italic>P<\/jats:italic>\u2009&lt;\u2009.01), whereas the specificity was lower than that of the NCS-Oph (83%, <jats:italic>P<\/jats:italic>\u2009&lt;\u2009.01). The average accuracy of around 70% was comparable with that of the NCS-Oph. Therefore, the sensitive DL-based diagnostic model is a promising tool for improving first-line medical care at rural area in early identification of FK.<\/jats:p>","DOI":"10.1038\/s41598-020-71425-9","type":"journal-article","created":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T10:03:28Z","timestamp":1599041008000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":69,"title":["A deep learning approach in diagnosing fungal keratitis based on corneal photographs"],"prefix":"10.1038","volume":"10","author":[{"given":"Ming-Tse","family":"Kuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benny Wei-Yun","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Kai","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Chiung","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Yin","family":"Lai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng-Shan","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent S.","family":"Tseng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,2]]},"reference":[{"key":"71425_CR1","first-page":"214","volume":"79","author":"JP Whitcher","year":"2001","unstructured":"Whitcher, J. P., Srinivasan, M. & Upadhyay, M. P. Corneal blindness: A global perspective. Bull. World Health Organ. 79, 214\u2013221 (2001).","journal-title":"Bull. World Health Organ."},{"key":"71425_CR2","doi-asserted-by":"crossref","unstructured":"Tew, T.B. et al. Therapeutic penetrating keratoplasty for microbial keratitis in Taiwan from 2001 to 2014. J. Formos. Med. Assoc. https:\/\/doi.org\/10.1016\/j.jfma.2019.09.016 (published online October 18, 2018).","DOI":"10.1016\/j.jfma.2019.09.016"},{"key":"71425_CR3","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1080\/09286586.2018.1454964","volume":"25","author":"JD Chidambaram","year":"2018","unstructured":"Chidambaram, J. D. et al. Epidemiology, risk factors, and clinical outcomes in severe microbial keratitis in South India. Ophthalmic Epidemiol. 25, 297\u2013305. https:\/\/doi.org\/10.1080\/09286586.2018.1454964 (2018).","journal-title":"Ophthalmic Epidemiol."},{"key":"71425_CR4","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1136\/bjo.2009.169607","volume":"95","author":"A Shah","year":"2011","unstructured":"Shah, A., Sachdev, A., Coggon, D. & Hossain, P. Geographic variations in microbial keratitis: An analysis of the peer-reviewed literature. Br. J. Ophthalmol. 95, 762\u2013767. https:\/\/doi.org\/10.1136\/bjo.2009.169607 (2011).","journal-title":"Br. J. Ophthalmol."},{"key":"71425_CR5","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s12348-019-0174-y","volume":"9","author":"TV Dave","year":"2019","unstructured":"Dave, T. V. et al. Infectious endophthalmitis leading to evisceration: spectrum of bacterial and fungal pathogens and antibacterial susceptibility profile. J. Ophthalmic Inflamm. Infect. 9, 9. https:\/\/doi.org\/10.1186\/s12348-019-0174-y (2019).","journal-title":"J. Ophthalmic Inflamm. Infect."},{"key":"71425_CR6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1097\/ICO.0000000000001781","volume":"38","author":"N Sharma","year":"2019","unstructured":"Sharma, N. et al. Management algorithm for fungal keratitis: the TST (topical, systemic, and targeted therapy) protocol. Cornea 38, 141\u2013145. https:\/\/doi.org\/10.1097\/ICO.0000000000001781 (2019).","journal-title":"Cornea"},{"key":"71425_CR7","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1097\/ICO.0000000000000691","volume":"35","author":"G Chen","year":"2016","unstructured":"Chen, G. et al. Deep anterior lamellar keratoplasty versus penetrating keratoplasty: A meta-analysis of randomized controlled trials. Cornea 35, 169\u2013174. https:\/\/doi.org\/10.1097\/ICO.0000000000000691 (2016).","journal-title":"Cornea"},{"key":"71425_CR8","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1001\/jamaophthalmol.2017.0722","volume":"135","author":"BH Jeng","year":"2017","unstructured":"Jeng, B. H. Challenges in the management of fungal keratitis. JAMA Ophthalmol. 135, 525\u2013526. https:\/\/doi.org\/10.1001\/jamaophthalmol.2017.0722 (2017).","journal-title":"JAMA Ophthalmol."},{"key":"71425_CR9","doi-asserted-by":"publisher","first-page":"940","DOI":"10.1016\/j.ajo.2007.02.030","volume":"143","author":"MA Dahlgren","year":"2007","unstructured":"Dahlgren, M. A., Lingappan, A. & Wilhelmus, K. R. The clinical diagnosis of microbial keratitis. Am. J. Ophthalmol. 143, 940\u2013944 (2007).","journal-title":"Am. J. Ophthalmol."},{"key":"71425_CR10","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1167\/iovs.11-8478","volume":"53","author":"C Dalmon","year":"2012","unstructured":"Dalmon, C. et al. The clinical differentiation of bacterial and fungal keratitis: A photographic survey. Invest. Ophthalmol. Vis. Sci. 53, 1787\u20131791. https:\/\/doi.org\/10.1167\/iovs.11-8478 (2012).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"71425_CR11","doi-asserted-by":"publisher","first-page":"1554","DOI":"10.1136\/bjo.2005.076315","volume":"89","author":"PA Thomas","year":"2005","unstructured":"Thomas, P. A., Leck, A. K. & Myatt, M. Characteristic clinical features as an aid to the diagnosis of suppurative keratitis caused by filamentous fungi. Br. J. Ophthalmol. 89, 1554\u20131558 (2005).","journal-title":"Br. J. Ophthalmol."},{"key":"71425_CR12","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","volume":"103","author":"DSW Ting","year":"2019","unstructured":"Ting, D. S. W. et al. Artificial intelligence and deep learning in ophthalmology. Br. J. Ophthalmol. 103, 167\u2013175. https:\/\/doi.org\/10.1136\/bjophthalmol-2018-313173 (2019).","journal-title":"Br. J. Ophthalmol."},{"key":"71425_CR13","doi-asserted-by":"publisher","first-page":"10750","DOI":"10.1038\/s41598-019-47181-w","volume":"9","author":"J Sahlsten","year":"2019","unstructured":"Sahlsten, J. et al. Deep learning fundus image analysis for diabetic retinopathy and macular edema grading. Sci. Rep. 9, 10750. https:\/\/doi.org\/10.1038\/s41598-019-47181-w (2019).","journal-title":"Sci. Rep."},{"key":"71425_CR14","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2019.3501","author":"H Liu","year":"2019","unstructured":"Liu, H. et al. Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol. https:\/\/doi.org\/10.1001\/jamaophthalmol.2019.3501 (2019).","journal-title":"JAMA Ophthalmol."},{"key":"71425_CR15","doi-asserted-by":"publisher","DOI":"10.1097\/IJG.0000000000001319","author":"LA Al-Aswad","year":"2019","unstructured":"Al-Aswad, L. A. et al. Evaluation of a deep learning system for identifying glaucomatous optic neuropathy based on color fundus photographs. J. Glaucoma https:\/\/doi.org\/10.1097\/IJG.0000000000001319 (2019).","journal-title":"J. Glaucoma"},{"key":"71425_CR16","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1016\/j.ophtha.2017.02.008","volume":"124","author":"R Gargeya","year":"2017","unstructured":"Gargeya, R. & Leng, T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology 124, 962\u2013969. https:\/\/doi.org\/10.1016\/j.ophtha.2017.02.008 (2017).","journal-title":"Ophthalmology"},{"key":"71425_CR17","doi-asserted-by":"publisher","first-page":"2434","DOI":"10.1016\/j.ophtha.2012.06.049","volume":"119","author":"MT Kuo","year":"2012","unstructured":"Kuo, M. T. et al. A highly sensitive method for molecular diagnosis of fungal keratitis: a dot hybridization assay. Ophthalmology 119, 2434\u20132442. https:\/\/doi.org\/10.1016\/j.ophtha.2012.06.049 (2012).","journal-title":"Ophthalmology"},{"key":"71425_CR18","first-page":"306","volume":"23","author":"PC Fang","year":"2017","unstructured":"Fang, P. C. et al. A dot hybridization assay for the diagnosis of bacterial keratitis. Mol. Vis. 23, 306\u2013317 (2017).","journal-title":"Mol. Vis."},{"key":"71425_CR19","first-page":"614","volume":"23","author":"FC Huang","year":"2017","unstructured":"Huang, F. C. et al. A DNA dot hybridization model for molecular diagnosis of parasitic keratitis. Mol. Vis. 23, 614\u2013623 (2017).","journal-title":"Mol. Vis."},{"key":"71425_CR20","doi-asserted-by":"publisher","first-page":"2158","DOI":"10.1167\/iovs.15-17741","volume":"57","author":"MT Kuo","year":"2016","unstructured":"Kuo, M. T. et al. A multiplex dot hybridization assay for detection and differentiation of Acanthamoeba and herpes Keratitis. Invest. Ophthalmol. Vis. Sci. 57, 2158\u20132163. https:\/\/doi.org\/10.1167\/iovs.15-17741 (2016).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"71425_CR21","unstructured":"Haykin, S. Neural Networks: A Comprehensive Foundation 2nd edn. 23\u201366 (Prentice Hall, 1998)."},{"key":"71425_CR22","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Maaten, L.V.D. & Weinberger, K.Q. Densely connected convolutional networks. IEEE CVPR 2261\u20132269, https:\/\/doi.org\/10.1109\/CVPR.2017.243 (2017).","DOI":"10.1109\/CVPR.2017.243"},{"key":"71425_CR23","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. IEEE CVPR 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"71425_CR24","doi-asserted-by":"publisher","unstructured":"Chattopadhay, A., Sarkar, A., Howlader, P. & Balasubramanian, V.N. Grad-CAM++: Generalized gradient-based visual explanations for deep convolutional networks. IEEE WACV 839\u2013847, https:\/\/doi.org\/10.1109\/WACV.2018.00097 (2018).","DOI":"10.1109\/WACV.2018.00097"},{"key":"71425_CR25","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.ajo.2013.08.032","volume":"157","author":"J Mascarenhas","year":"2014","unstructured":"Mascarenhas, J. et al. Acanthamoeba, fungal, and bacterial keratitis: a comparison of risk factors and clinical features. Am. J. Ophthalmol. 157, 56\u201362. https:\/\/doi.org\/10.1016\/j.ajo.2013.08.032 (2014).","journal-title":"Am. J. Ophthalmol."},{"key":"71425_CR26","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1076\/ceyr.27.2.111.15949","volume":"27","author":"JS Saini","year":"2003","unstructured":"Saini, J. S. et al. Neural network approach to classify infective keratitis. Curr. Eye Res. 27, 111\u2013116 (2003).","journal-title":"Curr. Eye Res."},{"key":"71425_CR27","doi-asserted-by":"publisher","first-page":"3631","DOI":"10.3390\/ijms20153631","volume":"20","author":"MT Kuo","year":"2019","unstructured":"Kuo, M. T. et al. An omics approach to diagnosing or investigating fungal keratitis. Int. J. Mol. Sci. 20, 3631. https:\/\/doi.org\/10.3390\/ijms20153631 (2019).","journal-title":"Int. J. Mol. Sci."},{"key":"71425_CR28","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1167\/iovs.07-1283","volume":"50","author":"S Vengayil","year":"2009","unstructured":"Vengayil, S. et al. Polymerase chain reaction-guided diagnosis of mycotic keratitis: a prospective evaluation of its efficacy and limitations. Invest. Ophthalmol. Vis. Sci. 50, 152\u2013156. https:\/\/doi.org\/10.1167\/iovs.07-1283 (2009).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"71425_CR29","doi-asserted-by":"publisher","first-page":"281","DOI":"10.4103\/0301-4738.64122","volume":"58","author":"S Das","year":"2010","unstructured":"Das, S. et al. Is inclusion of Sabouraud dextrose agar essential for the laboratory diagnosis of fungal keratitis?. Indian J. Ophthalmol. 58, 281\u2013286. https:\/\/doi.org\/10.4103\/0301-4738.64122 (2010).","journal-title":"Indian J. Ophthalmol."},{"key":"71425_CR30","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1001\/archophthalmol.2010.66","volume":"128","author":"M Itahashi","year":"2010","unstructured":"Itahashi, M., Higaki, S., Fukuda, M. & Shimomura, Y. Detection and quantification of pathogenic bacteria and fungi using real-time polymerase chain reaction by cycling probe in patients with corneal ulcer. Arch. Ophthalmol. 128, 535\u2013540. https:\/\/doi.org\/10.1001\/archophthalmol.2010.66 (2010).","journal-title":"Arch. Ophthalmol."},{"key":"71425_CR31","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1016\/j.ophtha.2011.10.038","volume":"119","author":"P Goldschmidt","year":"2012","unstructured":"Goldschmidt, P. et al. New strategy for rapid diagnosis and characterization of keratomycosis. Ophthalmology 119, 945\u2013950. https:\/\/doi.org\/10.1016\/j.ophtha.2011.10.038 (2012).","journal-title":"Ophthalmology"},{"key":"71425_CR32","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.ajo.2018.03.010","volume":"190","author":"JD Chidambaram","year":"2018","unstructured":"Chidambaram, J. D. et al. In vivo confocal microscopy cellular features of host and organism in bacterial, fungal, and Acanthamoeba keratitis. Am. J. Ophthalmol. 190, 24\u201333. https:\/\/doi.org\/10.1016\/j.ajo.2018.03.010 (2018).","journal-title":"Am. J. Ophthalmol."},{"key":"71425_CR33","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.ajo.2017.04.011","volume":"179","author":"A Kheirkhah","year":"2017","unstructured":"Kheirkhah, A. et al. Sensitivity and specificity of laser-scanning in vivo confocal microscopy for filamentous fungal keratitis: role of observer experience. Am. J. Ophthalmol. 179, 81\u201389. https:\/\/doi.org\/10.1016\/j.ajo.2017.04.011 (2017).","journal-title":"Am. J. Ophthalmol."},{"key":"71425_CR34","doi-asserted-by":"publisher","first-page":"13449","DOI":"10.1109\/ACCESS.2018.2808941","volume":"6","author":"X Wu","year":"2018","unstructured":"Wu, X. et al. Hyphae detection in fungal keratitis images with adaptive robust binary pattern. IEEE Access 6, 13449\u201313460. https:\/\/doi.org\/10.1109\/ACCESS.2018.2808941 (2018).","journal-title":"IEEE Access"},{"key":"71425_CR35","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-71425-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-71425-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-71425-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T18:06:18Z","timestamp":1670349978000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-71425-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,2]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["71425"],"URL":"https:\/\/doi.org\/10.1038\/s41598-020-71425-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,2]]},"assertion":[{"value":"19 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 August 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"14424"}}