{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T18:22:05Z","timestamp":1790274125501,"version":"4.1.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005967","name":"Linnaeus University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005967","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The purpose of this study was to compare manual assessment of corneal nerve fiber length (CNFL) and dendritic cell (DC) density with an automated assessment method utilizing deep learning segmentation to perform rule-based density estimation. Corneal images were acquired using in vivo confocal microscopy (IVCM) from 100 participants with persistent ocular symptoms after mild COVID-19 (Group 1) and 30 controls without symptoms (Group 2). In total, 1,300 IVCM images were selected and manually annotated for CNFL, and 1,300 for DCs (with dendrites and without dendrites), using FIJI tools. The between-method difference in mean CNFL density was 0.2\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {mm\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [0.09, 0.23]) for Group 1 and \u22120.2\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {mm\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [\u22120.34, \u22120.10]) for Group 2. For Group 1, the mean difference for DCs with dendrites was \u22121.1\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {cells\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [\u22121.78, \u22120.39]), and for DCs without dendrites it was \u22123.1\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {cells\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [\u22125.1, \u22121.0]). For Group 2, the mean difference for DCs with dendrites was \u22121.0\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {cells\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [\u22121.79, \u22120.27]), and for DCs without dendrites it was 0.3\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\hbox {cells\/mm}^2$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (95% CI: [\u22121.93, 2.60]). Both manual and automated methods showed significant between-group differences for CNFL (\n                    <jats:italic>p<\/jats:italic>\n                    =0.012 and\n                    <jats:italic>p<\/jats:italic>\n                    =0.034, respectively) and DC densities (\n                    <jats:italic>p<\/jats:italic>\n                    =0.005 and\n                    <jats:italic>p<\/jats:italic>\n                    =0.010). The automated approach performed comparably to manual assessment, supporting its potential for reliable, scalable analysis of CNFL and DC in IVCM images.\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-34412-6","type":"journal-article","created":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T07:23:55Z","timestamp":1768289035000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning-based segmentation and density estimation of corneal nerves and dendritic cells from In Vivo confocal microscopy images"],"prefix":"10.1038","volume":"16","author":[{"given":"Meichen","family":"Ji","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jenny","family":"Roth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ava","family":"Dashti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jorge","family":"Lazo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alisa","family":"Lincke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ant\u00f3nio Filipe Teixeira","family":"Macedo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Welf","family":"L\u00f6we","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neil","family":"Lagali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"34412_CR1","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.jtos.2021.10.010","volume":"23","author":"A Barros","year":"2022","unstructured":"Barros, A. et al. Small fiber neuropathy in the cornea of covid-19 patients associated with the generation of ocular surface disease. Ocular Surf.23, 40\u201348. https:\/\/doi.org\/10.1016\/j.jtos.2021.10.010 (2022).","journal-title":"Ocular Surf."},{"key":"34412_CR2","doi-asserted-by":"publisher","first-page":"1635","DOI":"10.1136\/bjophthalmol-2021-319450","volume":"106","author":"G Bitirgen","year":"2022","unstructured":"Bitirgen, G. et al. Corneal confocal microscopy identifies corneal nerve fibre loss and increased dendritic cells in patients with long covid. Br. J. Ophthalmol.106, 1635\u20131641. https:\/\/doi.org\/10.1136\/bjophthalmol-2021-319450 (2022).","journal-title":"Br. J. Ophthalmol."},{"key":"34412_CR3","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1038\/s41433-022-02018-1","volume":"37","author":"E Mirza","year":"2023","unstructured":"Mirza, E., Belviranli, S., Gundogan, A. O., Adam, M. & Oltulu, R. Quantitative assessment of the effect of sars-cov-2 on the corneal sub-basal nerve plexus of post-covid-19 patients using in vivo confocal microscopy. Eye (London, England)37, 660\u2013664. https:\/\/doi.org\/10.1038\/s41433-022-02018-1 (2023).","journal-title":"Eye (London, England)"},{"key":"34412_CR4","doi-asserted-by":"publisher","first-page":"11230","DOI":"10.1039\/c9ra00818g","volume":"9","author":"MK Kim","year":"2019","unstructured":"Kim, M. K. & Kim, J. Properties of immature and mature dendritic cells: phenotype, morphology, phagocytosis, and migration. RSC Advances9, 11230\u201311238. https:\/\/doi.org\/10.1039\/c9ra00818g (2019).","journal-title":"RSC Advances"},{"key":"34412_CR5","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2217795120","volume":"120","author":"LE Downie","year":"2023","unstructured":"Downie, L. E. et al. Redefining the human corneal immune compartment using dynamic intravital imaging. Proc. Natl. Acad. Sci.120, e2217795120 (2023).","journal-title":"Proc. Natl. Acad. Sci."},{"key":"34412_CR6","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2024-098294","volume":"15","author":"SA Sandvik","year":"2025","unstructured":"Sandvik, S. A. et al. Methods for the evaluation of corneal nerve fibres in diabetes mellitus by in vivo confocal microscopy: A scoping review. BMJ Open15, e098294 (2025).","journal-title":"BMJ Open"},{"key":"34412_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.578233","volume":"8","author":"J Xu","year":"2021","unstructured":"Xu, J. et al. In vivo confocal microscopic evaluation of corneal dendritic cell density and subbasal nerve parameters in dry eye patients: A systematic review and meta-analysis. Front. Med.8, 578233. https:\/\/doi.org\/10.3389\/fmed.2021.578233 (2021).","journal-title":"Front. Med."},{"key":"34412_CR8","doi-asserted-by":"publisher","first-page":"1149803","DOI":"10.3389\/fmed.2023.1149803","volume":"10","author":"R Guo","year":"2023","unstructured":"Guo, R. et al. Evaluation of corneal dendritic cell density and subbasal nerve density in contact lens wearers using ivcm: A systematic review and meta-analysis. Front. Med.10, 1149803. https:\/\/doi.org\/10.3389\/fmed.2023.1149803 (2023).","journal-title":"Front. Med."},{"key":"34412_CR9","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1167\/tvst.11.6.24","volume":"11","author":"MAK Setu","year":"2022","unstructured":"Setu, M. A. K., Schmidt, S., Musial, G., Stern, M. E. & Steven, P. Segmentation and evaluation of corneal nerves and dendritic cells from in vivo confocal microscopy images using deep learning. Trans. Vis. Sci. Technol.11, 24\u201324. https:\/\/doi.org\/10.1167\/tvst.11.6.24 (2022) https:\/\/arvojournals.org\/arvo\/content_public\/journal\/tvst\/938595\/i2164-2591-11-6-24_1656330221.66309.pdf.","journal-title":"Trans. Vis. Sci. Technol."},{"key":"34412_CR10","doi-asserted-by":"publisher","unstructured":"Jha, D. et al. Resunet++: An advanced architecture for medical image segmentation. arXiv preprint, arXiv:1911.07067, https:\/\/doi.org\/10.48550\/arXiv.1911.07067 (2019). 21st IEEE International Symposium on Multimedia.","DOI":"10.48550\/arXiv.1911.07067"},{"key":"34412_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1167\/tvst.9.2.32","volume":"9","author":"S Wei","year":"2020","unstructured":"Wei, S., Shi, F., Wang, Y., Chou, Y. & Li, X. A deep learning model for automated sub-basal corneal nerve segmentation and evaluation using in vivo confocal microscopy. Trans. Vis. Sci. Technol.9, 32. https:\/\/doi.org\/10.1167\/tvst.9.2.32 (2020).","journal-title":"Trans. Vis. Sci. Technol."},{"key":"34412_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0252653","volume":"16","author":"F Xu","year":"2021","unstructured":"Xu, F. et al. A deep transfer learning framework for the automated assessment of corneal inflammation on in vivo confocal microscopy images. PLOS One16, 1\u201315. https:\/\/doi.org\/10.1371\/journal.pone.0252653 (2021).","journal-title":"PLOS One"},{"key":"34412_CR13","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1038\/nmeth.2019","volume":"9","author":"J Schindelin","year":"2012","unstructured":"Schindelin, J. et al. Fiji: An open-source platform for biological-image analysis. Nature Methods9, 676\u2013682. https:\/\/doi.org\/10.1038\/nmeth.2019 (2012).","journal-title":"Nature Methods"},{"key":"34412_CR14","doi-asserted-by":"publisher","unstructured":"Dabbah, M.\u00a0A., Graham, J., Petropoulos, I., Tavakoli, M. & Malik, R.\u00a0A. Dual-model automatic detection of nerve-fibres in corneal confocal microscopy images. Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention13, 300\u20137, https:\/\/doi.org\/10.1007\/978-3-642-15705-9_37 (2010).","DOI":"10.1007\/978-3-642-15705-9_37"},{"key":"34412_CR15","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1167\/tvst.12.11.29","volume":"12","author":"A Lincke","year":"2023","unstructured":"Lincke, A. et al. Ai-based decision-support system for diagnosing acanthamoeba keratitis using in vivo confocal microscopy images. Trans. Visi. Sci. Technol.12, 29. https:\/\/doi.org\/10.1167\/tvst.12.11.29 (2023).","journal-title":"Trans. Visi. Sci. Technol."},{"key":"34412_CR16","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/JPROC.2010.2050290","volume":"98","author":"A Torralba","year":"2010","unstructured":"Torralba, A., Russell, B. C. & Yuen, J. Labelme: Online image annotation and applications. Proc. IEEE98, 1467\u20131484. https:\/\/doi.org\/10.1109\/JPROC.2010.2050290 (2010).","journal-title":"Proc. IEEE"},{"key":"34412_CR17","unstructured":"Clark, A. et al. Pillow (2019). Computer software."},{"key":"34412_CR18","unstructured":"Williams, C. et al. A unified framework for u-net design and analysis (2024). arXiv:2305.19638."},{"key":"34412_CR19","doi-asserted-by":"crossref","unstructured":"Huang, L., Miron, A., Hone, K. & Li, Y. Segmenting medical images: From unet to res-unet and nnunet (2024). arXiv:2407.04353.","DOI":"10.1109\/CBMS61543.2024.00086"},{"key":"34412_CR20","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","volume":"15","author":"AA Taha","year":"2015","unstructured":"Taha, A. A. & Hanbury, A. Metrics for evaluating 3d medical image segmentation: Analysis, selection, and tool. BMC Med. Imag.15, 29. https:\/\/doi.org\/10.1186\/s12880-015-0068-x (2015).","journal-title":"BMC Med. Imag."},{"key":"34412_CR21","unstructured":"Stevens, E., Antiga, L. & Viehmann, T. Deep Learning with PyTorch: Build, train, and tune neural networks using Python tools (Manning, 2020)."},{"key":"34412_CR22","unstructured":"Gulli, A. & Pal, S. Deep learning with Keras (Packt Publishing Ltd, 2017)."},{"key":"34412_CR23","volume-title":"IBM SPSS Statistics for Windows, Version 29","author":"IBM Corp","year":"2024","unstructured":"Corp, I. B. M. IBM SPSS Statistics for Windows, Version 29 (Armonk, NY, 2024)."},{"key":"34412_CR24","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/j.jtos.2023.06.001","volume":"29","author":"H Levine","year":"2023","unstructured":"Levine, H. et al. Automated identification and quantification of activated dendritic cells in central cornea using artificial intelligence. Ocular Sur.29, 480\u2013485. https:\/\/doi.org\/10.1016\/j.jtos.2023.06.001 (2023).","journal-title":"Ocular Sur."},{"key":"34412_CR25","doi-asserted-by":"publisher","unstructured":"Oakley, J.\u00a0D. et al. Deep learning-based analysis of macaque corneal sub-basal nerve fibers in confocal microscopy images. Eye and vision (London, England)7, 27, https:\/\/doi.org\/10.1186\/s40662-020-00192-5 (2020).","DOI":"10.1186\/s40662-020-00192-5"},{"key":"34412_CR26","doi-asserted-by":"publisher","unstructured":"Mou, L. et al. Cs-net: Channel and spatial attention network for curvilinear structure segmentation. In Shen, D. et al. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019 - 22nd International Conference, Proceedings, vol. 11764 LNCS of Lecture Notes in Computer Science, 721\u2013730, https:\/\/doi.org\/10.1007\/978-3-030-32239-7_80 (Springer Nature, 2019).","DOI":"10.1007\/978-3-030-32239-7_80"},{"key":"34412_CR27","doi-asserted-by":"publisher","first-page":"12550","DOI":"10.1038\/s41598-020-69314-2","volume":"10","author":"EL Schaldemose","year":"2020","unstructured":"Schaldemose, E. L. et al. An unbiased stereological method for corneal confocal microscopy in patients with diabetic polyneuropathy. Sci. Rep.10, 12550. https:\/\/doi.org\/10.1038\/s41598-020-69314-2 (2020).","journal-title":"Sci. Rep."},{"key":"34412_CR28","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1038\/s41531-021-00225-3","volume":"7","author":"N-N Che","year":"2021","unstructured":"Che, N.-N. et al. Corneal nerve fiber loss relates to cognitive impairment in patients with Parkinson\u2019s disease. NPJ Parkinson\u2019s Dis.7, 80. https:\/\/doi.org\/10.1038\/s41531-021-00225-3 (2021).","journal-title":"NPJ Parkinson\u2019s Dis."},{"key":"34412_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.exer.2020.108168","volume":"199","author":"LH Colorado","year":"2020","unstructured":"Colorado, L. H., Edwards, K., Chinnery, H. R. & Bazan, H. E. In vivo immune cell dynamics in the human cornea. Exp. Eye Res.199, 108168 (2020).","journal-title":"Exp. Eye Res."},{"key":"34412_CR30","doi-asserted-by":"publisher","first-page":"205520762513262","DOI":"10.1177\/20552076251326223","volume":"11","author":"Q Qiao","year":"2025","unstructured":"Qiao, Q. et al. Automated program using convolutional neural networks for objective and reproducible selection of corneal confocal microscopy images. Dig. Health11, 20552076251326224. https:\/\/doi.org\/10.1177\/20552076251326223 (2025).","journal-title":"Dig. Health"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34412-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34412-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34412-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T23:02:53Z","timestamp":1768345373000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-34412-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["34412"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-34412-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7748380\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]},"assertion":[{"value":"30 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest. M.Ji, None; Y.Song, None; J.Roth, None; A.Dashti, None; J.Lazo, None; A.Lincke, None; A.Macedo, None; W.L\u00f6we, None; N.Lagali, None.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1620"}}