{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T06:51:38Z","timestamp":1775631098432,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T00:00:00Z","timestamp":1720224000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T00:00:00Z","timestamp":1720224000000},"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":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The main cause of corneal blindness worldwide is keratitis, especially the infectious form caused by bacteria, fungi, viruses, and Acanthamoeba. The key to effective management of infectious keratitis hinges on prompt and precise diagnosis. Nevertheless, the current gold standard, such as cultures of corneal scrapings, remains time-consuming and frequently yields false-negative results. Here, using 23,055 slit-lamp images collected from 12 clinical centers nationwide, this study constructed a clinically feasible deep learning system, DeepIK, that could emulate the diagnostic process of a human expert to identify and differentiate bacterial, fungal, viral, amebic, and noninfectious keratitis. DeepIK exhibited remarkable performance in internal, external, and prospective datasets (all areas under the receiver operating characteristic curves &gt; 0.96) and outperformed three other state-of-the-art algorithms (DenseNet121, InceptionResNetV2, and Swin-Transformer). Our study indicates that DeepIK possesses the capability to assist ophthalmologists in accurately and swiftly identifying various infectious keratitis types from slit-lamp images, thereby facilitating timely and targeted treatment.<\/jats:p>","DOI":"10.1038\/s41746-024-01174-w","type":"journal-article","created":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T13:01:29Z","timestamp":1720270889000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Deep learning for multi-type infectious keratitis diagnosis: A nationwide, cross-sectional, multicenter study"],"prefix":"10.1038","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9759-7461","authenticated-orcid":false,"given":"Zhongwen","family":"Li","sequence":"first","affiliation":[]},{"given":"He","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Zhouqian","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Daoyuan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Kuan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Xihang","family":"Zong","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Qiang","sequence":"additional","affiliation":[]},{"given":"Feng","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Zhihong","family":"Deng","sequence":"additional","affiliation":[]},{"given":"Limin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Huiping","family":"Li","sequence":"additional","affiliation":[]},{"given":"He","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Pengcheng","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Tao","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Yanning","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0011-3702","authenticated-orcid":false,"given":"Qinxiang","family":"Zheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4306-793X","authenticated-orcid":false,"given":"Jiewei","family":"Jiang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4040-6721","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,6]]},"reference":[{"key":"1174_CR1","doi-asserted-by":"publisher","first-page":"e1221","DOI":"10.1016\/S2214-109X(17)30393-5","volume":"5","author":"SR Flaxman","year":"2017","unstructured":"Flaxman, S. R. et al. Global causes of blindness and distance vision impairment 1990-2020: a systematic review and meta-analysis. Lancet Glob. Health. 5, e1221\u2013e1234 (2017).","journal-title":"Lancet Glob. Health."},{"key":"1174_CR2","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1016\/j.ophtha.2017.05.012","volume":"124","author":"A Austin","year":"2017","unstructured":"Austin, A., Lietman, T. & Rose-Nussbaumer, J. Update on the management of infectious Keratitis. Ophthalmology 124, 1678\u20131689 (2017).","journal-title":"Ophthalmology"},{"key":"1174_CR3","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.jtos.2021.11.003","volume":"23","author":"D Ting","year":"2022","unstructured":"Ting, D. et al. Diagnostic armamentarium of infectious keratitis: A comprehensive review. Ocul. Surf. 23, 27\u201339 (2022).","journal-title":"Ocul. Surf."},{"key":"1174_CR4","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1038\/s41433-020-01339-3","volume":"35","author":"D Ting","year":"2021","unstructured":"Ting, D., Ho, C. S., Deshmukh, R., Said, D. G. & Dua, H. S. Infectious keratitis: An update on epidemiology, causative microorganisms, risk factors, and antimicrobial resistance. Eye. 35, 1084\u20131101 (2021).","journal-title":"Eye."},{"key":"1174_CR5","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.survophthal.2018.12.003","volume":"64","author":"L Ung","year":"2019","unstructured":"Ung, L., Bispo, P., Shanbhag, S. S., Gilmore, M. S. & Chodosh, J. The persistent dilemma of microbial keratitis: Global burden, diagnosis, and antimicrobial resistance. Surv. Ophthalmol. 64, 255\u2013271 (2019).","journal-title":"Surv. Ophthalmol."},{"key":"1174_CR6","unstructured":"Singh, P., Gupta, A. & Tripathy, K. Keratitis. StatPearls. https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK559014\/ (2023)."},{"key":"1174_CR7","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.ophtha.2021.09.019","volume":"129","author":"TK Redd","year":"2022","unstructured":"Redd, T. K. et al. Expert performance in visual differentiation of bacterial and fungal Keratitis. Ophthalmology 129, 227\u2013230 (2022).","journal-title":"Ophthalmology"},{"key":"1174_CR8","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 (2012).","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"1174_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":"1174_CR10","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1136\/bjophthalmol-2019-314336","volume":"104","author":"S Resnikoff","year":"2020","unstructured":"Resnikoff, S. et al. Estimated number of ophthalmologists worldwide (International Council of Ophthalmology update): will we meet the needs? Br. J. Ophthalmol. 104, 588\u2013592 (2020).","journal-title":"Br. J. Ophthalmol."},{"key":"1174_CR11","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1016\/j.eng.2020.04.012","volume":"7","author":"Y Xu","year":"2021","unstructured":"Xu, Y. et al. Deep sequential feature learning in clinical image classification of infectious Keratitis. Engineering 7, 1002\u20131010 (2021).","journal-title":"Engineering"},{"key":"1174_CR12","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2017.18152","volume":"318","author":"D Ting","year":"2017","unstructured":"Ting, D. et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. Jama 318, 2211\u20132223 (2017).","journal-title":"Jama"},{"key":"1174_CR13","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1056\/NEJMoa1917130","volume":"382","author":"D Milea","year":"2020","unstructured":"Milea, D. et al. Artificial Intelligence to detect Papilledema from ocular fundus photographs. N. Engl. J. Med. 382, 1687\u20131695 (2020).","journal-title":"N. Engl. J. Med."},{"key":"1174_CR14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s42003-019-0730-x","volume":"3","author":"Z Li","year":"2020","unstructured":"Li, Z. et al. Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images. Commun. Biol. 3, 15 (2020).","journal-title":"Commun. Biol."},{"key":"1174_CR15","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1097\/ICO.0000000000002830","volume":"41","author":"AK Ghosh","year":"2022","unstructured":"Ghosh, A. K., Thammasudjarit, R., Jongkhajornpong, P., Attia, J. & Thakkinstian, A. Deep learning for discrimination between fungal Keratitis and bacterial Keratitis: DeepKeratitis. Cornea 41, 616\u2013622 (2022).","journal-title":"Cornea"},{"key":"1174_CR16","doi-asserted-by":"publisher","first-page":"892","DOI":"10.1038\/s41591-020-0867-7","volume":"26","author":"J Yim","year":"2020","unstructured":"Yim, J. et al. Predicting conversion to wet age-related macular degeneration using deep learning. Nat. Med. 26, 892\u2013899 (2020).","journal-title":"Nat. Med."},{"key":"1174_CR17","doi-asserted-by":"publisher","first-page":"1246","DOI":"10.3390\/diagnostics11071246","volume":"11","author":"N Hung","year":"2021","unstructured":"Hung, N. et al. Using slit-lamp images for deep learning-based identification of bacterial and fungal keratitis: model development and validation with different convolutional neural networks. Diagnostics 11, 1246 (2021).","journal-title":"Diagnostics"},{"key":"1174_CR18","doi-asserted-by":"publisher","first-page":"100119","DOI":"10.1016\/j.xops.2022.100119","volume":"2","author":"TK Redd","year":"2022","unstructured":"Redd, T. K. et al. Image-based differentiation of bacterial and fungal Keratitis using deep convolutional neural networks. Ophthalmol. Sci. 2, 100119 (2022).","journal-title":"Ophthalmol. Sci."},{"key":"1174_CR19","doi-asserted-by":"publisher","first-page":"e345","DOI":"10.1016\/S2666-5247(21)00093-8","volume":"2","author":"B Rayamajhee","year":"2021","unstructured":"Rayamajhee, B., Willcox, M. D., Henriquez, F. L., Petsoglou, C. & Carnt, N. Acanthamoeba keratitis: An increasingly common infectious disease of the cornea. Lancet Microbe 2, e345\u2013e346 (2021).","journal-title":"Lancet Microbe"},{"key":"1174_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24116-6","volume":"12","author":"Z Li","year":"2021","unstructured":"Li, Z. et al. Preventing corneal blindness caused by keratitis using artificial intelligence. Nat. Commun. 12, 3738 (2021).","journal-title":"Nat. Commun."},{"key":"1174_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-75027-3","volume":"10","author":"H Gu","year":"2020","unstructured":"Gu, H. et al. Deep learning for identifying corneal diseases from ocular surface slit-lamp photographs. Sci. Rep. 10, 17851 (2020).","journal-title":"Sci. Rep."},{"key":"1174_CR22","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-02138-w","volume":"11","author":"A Koyama","year":"2021","unstructured":"Koyama, A. et al. Determination of probability of causative pathogen in infectious keratitis using deep learning algorithm of slit-lamp images. Sci. Rep. 11, 22642 (2021).","journal-title":"Sci. Rep."},{"key":"1174_CR23","doi-asserted-by":"publisher","first-page":"106048","DOI":"10.1016\/j.cmpb.2021.106048","volume":"203","author":"Z Li","year":"2021","unstructured":"Li, Z. et al. Development of a deep learning-based image quality control system to detect and filter out ineligible slit-lamp images: A multicenter study. Comput. Methods. Programs. Biomed. 203, 106048 (2021).","journal-title":"Comput. Methods. Programs. Biomed."},{"key":"1174_CR24","unstructured":"White, M. L. & Chodosh, J. Herpes Simplex Virus Keratitis: A Treatment Guideline - 2014. https:\/\/www.aao.org\/education\/clinical-statement\/herpes-simplex-virus-keratitis-treatment-guideline (2014)."},{"key":"1174_CR25","doi-asserted-by":"publisher","first-page":"101031","DOI":"10.1016\/j.preteyeres.2021.101031","volume":"89","author":"S Tuft","year":"2022","unstructured":"Tuft, S. et al. Bacterial keratitis: identifying the areas of clinical uncertainty. Prog. Retin. Eye Res. 89, 101031 (2022).","journal-title":"Prog. Retin. Eye Res."},{"key":"1174_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-36024-4","volume":"13","author":"J Wu","year":"2023","unstructured":"Wu, J. et al. A knowledge-enhanced transform-based multimodal classifier for microbial keratitis identification. Sci. Rep. 13, 9003 (2023).","journal-title":"Sci. Rep."},{"key":"1174_CR27","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"1174_CR28","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00800-w","volume":"10","author":"J Jiang","year":"2023","unstructured":"Jiang, J. et al. Automatic diagnosis of keratitis using object localization combined with cost-sensitive deep attention convolutional neural network. J. Big Data. 10, 121 (2023).","journal-title":"J. Big Data."},{"key":"1174_CR29","first-page":"2579","volume":"9","author":"L Van der Maaten","year":"2008","unstructured":"Van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008).","journal-title":"J. Mach. Learn. Res."},{"key":"1174_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. 2017 IEEE International Conference on Computer Vision (ICCV). IEEE; 618\u2013626 (2017).","DOI":"10.1109\/ICCV.2017.74"},{"key":"1174_CR31","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1038\/s41591-020-1034-x","volume":"26","author":"X Liu","year":"2020","unstructured":"Liu, X., Cruz, R. S., Moher, D., Calvert, M. J. & Denniston, A. K. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. Nat. Med. 26, 1364\u20131374 (2020).","journal-title":"Nat. Med."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01174-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T13:03:08Z","timestamp":1720270988000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-024-01174-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,6]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1174"],"URL":"https:\/\/doi.org\/10.1038\/s41746-024-01174-w","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,6]]},"assertion":[{"value":"19 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2024","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"}},{"value":"This study adhered to the principles of the Declaration of Helsinki and received approval from both the institutional review boards\/ethics committees of Ningbo Eye Hospital (NEH) (identifier, 2021-xjx-009) and the National Clinical Research Center for Ocular Diseases (NCRCOD) (identifier, 2022-222-K-176-01). All original images (ranging in size from 0.2 to 9 megabytes per image) underwent de-identification to erase any information related to patients before being transferred to study investigators. In the case of retrospectively collected images, the ethics committees of NEH and NCRCOD granted an exemption for informed consent. Conversely, for prospectively collected images, informed consent was obtained from the patients. The study adhered to the Consolidated Standards of Reporting Trials (CONSORT)-AI extension guidelines for reporting clinical studies involving the application of AI<sup>31<\/sup>.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Ethical approval"}}],"article-number":"181"}}