{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:16:31Z","timestamp":1787026591640,"version":"build-2736575974"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T00:00:00Z","timestamp":1681948800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81770899"],"award-info":[{"award-number":["81770899"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82101081"],"award-info":[{"award-number":["82101081"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>\n                      In order to automatically and rapidly recognize the layers of corneal images using\n                      <jats:italic>in vivo<\/jats:italic>\n                      confocal microscopy (IVCM) and classify them into normal and abnormal images, a computer-aided diagnostic model was developed and tested based on deep learning to reduce physicians\u2019 workload.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 19,612 corneal images were retrospectively collected from 423 patients who underwent IVCM between January 2021 and August 2022 from Renmin Hospital of Wuhan University (Wuhan, China) and Zhongnan Hospital of Wuhan University (Wuhan, China). Images were then reviewed and categorized by three corneal specialists before training and testing the models, including the layer recognition model (epithelium, bowman\u2019s membrane, stroma, and endothelium) and diagnostic model, to identify the layers of corneal images and distinguish normal images from abnormal images. Totally, 580 database-independent IVCM images were used in a human-machine competition to assess the speed and accuracy of image recognition by 4 ophthalmologists and artificial intelligence (AI). To evaluate the efficacy of the model, 8 trainees were employed to recognize these 580 images both with and without model assistance, and the results of the two evaluations were analyzed to explore the effects of model assistance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The accuracy of the model reached 0.914, 0.957, 0.967, and 0.950 for the recognition of 4 layers of epithelium, bowman\u2019s membrane, stroma, and endothelium in the internal test dataset, respectively, and it was 0.961, 0.932, 0.945, and 0.959 for the recognition of normal\/abnormal images at each layer, respectively. In the external test dataset, the accuracy of the recognition of corneal layers was 0.960, 0.965, 0.966, and 0.964, respectively, and the accuracy of normal\/abnormal image recognition was 0.983, 0.972, 0.940, and 0.982, respectively. In the human-machine competition, the model achieved an accuracy of 0.929, which was similar to that of specialists and higher than that of senior physicians, and the recognition speed was 237 times faster than that of specialists. With model assistance, the accuracy of trainees increased from 0.712 to 0.886.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A computer-aided diagnostic model was developed for IVCM images based on deep learning, which rapidly recognized the layers of corneal images and classified them as normal and abnormal. This model can increase the efficacy of clinical diagnosis and assist physicians in training and learning for clinical purposes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2023.1164188","type":"journal-article","created":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T17:26:44Z","timestamp":1682011604000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Evaluation of a computer-aided diagnostic model for corneal diseases by analyzing in vivo confocal microscopy images"],"prefix":"10.3389","volume":"10","author":[{"given":"Yulin","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiyan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwen","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linying","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongmei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiling","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianlian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simin","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuelan","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiewen","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyu","family":"Cong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshuo","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zixian","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingmei","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Biqing","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanning","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,4,20]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"101011","DOI":"10.1016\/j.preteyeres.2021.101011","article-title":"Regenerative therapy for the cornea","volume":"87","author":"Kumar","year":"2022","journal-title":"Prog Retin Eye Res"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1001\/jama.2021.0424","article-title":"Infectious keratitis in 2021","volume":"326","author":"Durand","year":"2021","journal-title":"JAMA"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"951081","DOI":"10.1155\/2015\/951081","article-title":"In vivo confocal microscopy of the human cornea in the assessment of peripheral neuropathy and systemic diseases","volume":"2015","author":"Wang","year":"2015","journal-title":"Biomed Res Int"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"813","DOI":"10.1016\/j.ophtha.2020.06.042","article-title":"In pursuit of the elimination of corneal blindness: is establishing eye banks and training surgeons enough?","volume":"128","author":"Jeng","year":"2021","journal-title":"Ophthalmology"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1016\/j.ophtha.2017.05.012","article-title":"Update on the management of infectious keratitis","volume":"124","author":"Austin","year":"2017","journal-title":"Ophthalmology"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"103","DOI":"10.3760\/cma.j.cn112142-20210228-00099","article-title":"Imaging features of posterior polymorphous corneal dystrophy observed by in vivo confocal microscopy","volume":"58","author":"Gu","year":"2022","journal-title":"Zhonghua Yan Ke Za Zhi"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.preteyeres.2009.11.001","article-title":"Clinical in vivo confocal microscopy of the human cornea in health and disease","volume":"29","author":"Niederer","year":"2010","journal-title":"Prog Retin Eye Res"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1097\/ACI.0000000000000844","article-title":"Corneal complications of rheumatoid arthritis","volume":"22","author":"Wajnsztajn","year":"2022","journal-title":"Curr Opin Allergy Clin Immunol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e252653","DOI":"10.1371\/journal.pone.0252653","article-title":"A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images","volume":"16","author":"Xu","year":"2021","journal-title":"PLoS One"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"3738","DOI":"10.1038\/s41467-021-24116-6","article-title":"Preventing corneal blindness caused by keratitis using artificial intelligence","volume":"12","author":"Li","year":"2021","journal-title":"Nat Commun"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1097\/ICU.0000000000000885","article-title":"Artificial intelligence and corneal diseases","volume":"33","author":"Kang","year":"2022","journal-title":"Curr Opin Ophthalmol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1167\/tvst.11.6.24","article-title":"Segmentation and evaluation of corneal nerves and dendritic cells from in vivo confocal microscopy images using deep learning","volume":"11","author":"Setu","year":"2022","journal-title":"Transl Vis Sci Technol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1097\/ICO.0000000000002661","article-title":"Combining in vivo corneal confocal microscopy with deep learning-based analysis reveals sensory nerve fiber loss in acute simian immunodeficiency virus infection","volume":"40","author":"McCarron","year":"2021","journal-title":"Cornea"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1167\/tvst.9.2.32","article-title":"A deep learning model for automated sub-basal corneal nerve segmentation and evaluation using in vivo confocal microscopy","volume":"9","author":"Wei","year":"2020","journal-title":"Transl Vis Sci Technol"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.ajo.2022.02.026","article-title":"A fully automated segmentation and morphometric parameter estimation system for assessing corneal endothelial cell images","volume":"239","author":"Qu","year":"2022","journal-title":"Am J Ophthalmol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1159\/000516093","article-title":"Descemet membrane endothelial keratoplasty and Bowman layer transplantation: an anatomic review and historical survey","volume":"64","author":"Parker","year":"2021","journal-title":"Ophthalmic Res"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1016\/j.ophtha.2020.03.023","article-title":"The ongoing debate: Descemet membrane endothelial keratoplasty versus ultrathin Descemet stripping automated endothelial keratoplasty","volume":"127","author":"Busin","year":"2020","journal-title":"Ophthalmology"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.14744\/AnatolJCardiol.2019.28661","article-title":"Artificial intelligence in healthcare: past, present and future","volume":"22","author":"Tekkesin","year":"2019","journal-title":"Anatol J Cardiol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"106048","DOI":"10.1016\/j.cmpb.2021.106048","article-title":"Development of a deep learning-based image quality control system to detect and filter out ineligible slit-lamp images: a multicenter study","volume":"203","author":"Li","year":"2021","journal-title":"Comput Methods Prog Biomed"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"104675","DOI":"10.1016\/j.compbiomed.2021.104675","article-title":"Automatic segmentation of corneal deposits from corneal stromal dystrophy images via deep learning","volume":"137","author":"Deshmukh","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1109\/TBME.2016.2573642","article-title":"An automatic tool for quantification of nerve fibers in corneal confocal microscopy images","volume":"64","author":"Chen","year":"2017","journal-title":"IEEE Trans Biomed Eng"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"4801","DOI":"10.1167\/iovs.08-2061","article-title":"Automatic recognition of corneal nerve structures in images from confocal microscopy","volume":"49","author":"Scarpa","year":"2008","journal-title":"Investig Ophthalmol Vis Sci"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1038\/s41467-021-21466-z","article-title":"Ensembled deep learning model outperforms human experts in diagnosing biliary atresia from sonographic gallbladder images","volume":"12","author":"Zhou","year":"2021","journal-title":"Nat Commun"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1038\/s41551-020-00626-4","article-title":"A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre","volume":"5","author":"Cheung","year":"2021","journal-title":"Nat Biomed Eng"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s42003-019-0730-x","article-title":"Deep learning for detecting retinal detachment and discerning macular status using ultra-widefield fundus images","volume":"3","author":"Li","year":"2020","journal-title":"Commun Biol"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1001\/jama.2016.17563","article-title":"Artificial intelligence with deep learning technology looks into diabetic retinopathy screening","volume":"316","author":"Wong","year":"2016","journal-title":"JAMA"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2079","DOI":"10.1109\/TMI.2022.3156906","article-title":"DeepGrading: deep learning grading of corneal nerve tortuosity","volume":"41","author":"Mou","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-030-33128-3_4","article-title":"Deep learning computer-aided diagnosis for breast lesion in digital mammogram","volume":"1213","author":"Al-Antari","year":"2020","journal-title":"Adv Exp Med Biol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2023.1164188\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,20]],"date-time":"2023-04-20T17:27:04Z","timestamp":1682011624000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2023.1164188\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,20]]},"references-count":29,"alternative-id":["10.3389\/fmed.2023.1164188"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2023.1164188","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,20]]},"article-number":"1164188"}}