{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T21:52:14Z","timestamp":1787003534228,"version":"build-2736575974"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T00:00:00Z","timestamp":1682035200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T00:00:00Z","timestamp":1682035200000},"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":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Cornea topography maps allow ophthalmologists to screen and diagnose cornea pathologies. We aim to automatically identify any cornea abnormalities based on such cornea topography maps, with focus on diagnosing keratoconus. To do so, we represent the OCT scans as images and apply Convolutional Neural Networks (CNNs) for the automatic analysis. The model is based on a state-of-the-art\n                    <jats:italic>ConvNeXt<\/jats:italic>\n                    CNN architecture with weights fine-tuned for the given specific application using the cornea scans dataset. A set of 1940 consecutive screening scans from the Saarland University Hospital Clinic for Ophthalmology was annotated and used for model training and validation. All scans were recorded with a CASIA2 anterior segment Optical Coherence Tomography (OCT) scanner. The proposed model achieves a sensitivity of 98.46% and a specificity of 91.96% when distinguishing between\n                    <jats:italic>healthy<\/jats:italic>\n                    and\n                    <jats:italic>pathological<\/jats:italic>\n                    corneas. Our approach enables the screening of cornea pathologies and the classification of common pathologies like\n                    <jats:italic>keratoconus<\/jats:italic>\n                    . Furthermore, the approach is independent of the topography scanner and enables the visualization of those scan regions which drive the model\u2019s decisions.\n                  <\/jats:p>","DOI":"10.1038\/s41598-023-33793-w","type":"journal-article","created":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T09:02:34Z","timestamp":1682067754000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Automated cornea diagnosis using deep convolutional neural networks based on cornea topography maps"],"prefix":"10.1038","volume":"13","author":[{"given":"Benjamin","family":"Fassbind","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Achim","family":"Langenbucher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Streich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,4,21]]},"reference":[{"key":"33793_CR1","doi-asserted-by":"publisher","first-page":"15","DOI":"10.4103\/0974-9233.61212","volume":"17","author":"L Espandar","year":"2010","unstructured":"Espandar, L. & Meyer, J. Keratoconus: Overview and update on treatment. Middle East Afr. J. Ophthalmol. 17, 15. https:\/\/doi.org\/10.4103\/0974-9233.61212 (2010).","journal-title":"Middle East Afr. J. Ophthalmol."},{"key":"33793_CR2","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/B978-0-7020-2983-7.00006-1","volume-title":"Ocular Disease","author":"MC Kenney","year":"2010","unstructured":"Kenney, M. C. & Gaster, R. N. Keratoconus. In Ocular Disease 42\u201348 (W.B. Saunders, 2010). https:\/\/doi.org\/10.1016\/B978-0-7020-2983-7.00006-1."},{"key":"33793_CR3","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/694542","author":"SA Kurna","year":"2022","unstructured":"Kurna, S. A., Altun, A., Gencaga, T., Akkaya, S. & Sengor, T. Vision related quality of life in patients with keratoconus. J. Ophthalmol.https:\/\/doi.org\/10.1155\/2014\/694542 (2022).","journal-title":"J. Ophthalmol."},{"key":"33793_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/j.yaoo.2021.04.019","volume":"6","author":"E Oyeniran","year":"2021","unstructured":"Oyeniran, E. & Tauqeer, Z. Update in the management of keratoconus. Ad. Ophthalmol. Optometry 6, 307\u2013324. https:\/\/doi.org\/10.1016\/j.yaoo.2021.04.019 (2021).","journal-title":"Ad. Ophthalmol. Optometry"},{"key":"33793_CR5","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1186\/s12909-021-02738-0","volume":"21","author":"PB Baenninger","year":"2021","unstructured":"Baenninger, P. B. et al. Mismatch of corneal specialists\u2019 expectations and keratoconus knowledge in general ophthalmologists\u2014a prospective observational study in Switzerland. BMC Med. Educ. 21, 297. https:\/\/doi.org\/10.1186\/s12909-021-02738-0 (2021).","journal-title":"BMC Med. Educ."},{"key":"33793_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10051094","author":"M Dembski","year":"2021","unstructured":"Dembski, M., Nowi\u0144ska, A., Ulfik-Dembska, K. & Wyl\u0119ga\u0142a, E. Swept source optical coherence tomography analysis of the selected eye\u2019s anterior segment parameters. J. Clin. Med.https:\/\/doi.org\/10.3390\/jcm10051094 (2021).","journal-title":"J. Clin. Med."},{"key":"33793_CR7","doi-asserted-by":"publisher","first-page":"2732","DOI":"10.4103\/ijo.IJO_2111_20","volume":"68","author":"K Doctor","year":"2020","unstructured":"Doctor, K. et al. Simplifying and understanding various topographic indices for keratoconus using Scheimpflug based topographers. Indian J. Ophthalmol. 68, 2732. https:\/\/doi.org\/10.4103\/ijo.IJO_2111_20 (2020).","journal-title":"Indian J. Ophthalmol."},{"key":"33793_CR8","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1007\/s00347-014-3135-8","volume":"112","author":"C Spira","year":"2015","unstructured":"Spira, C. et al. Comparison of the specificity and sensitivity of various instrument-guided keratoconus indices and classifiers. Ophthalmologe 112, 353\u2013358. https:\/\/doi.org\/10.1007\/s00347-014-3135-8 (2015).","journal-title":"Ophthalmologe"},{"key":"33793_CR9","doi-asserted-by":"publisher","first-page":"6280690","DOI":"10.1155\/2021\/6280690","volume":"2021","author":"F An","year":"2021","unstructured":"An, F., Li, X. & Ma, X. Medical image classification algorithm based on visual attention mechanism-MCNN. Oxid. Med. Cell. Longev. 2021, 6280690. https:\/\/doi.org\/10.1155\/2021\/6280690 (2021).","journal-title":"Oxid. Med. Cell. Longev."},{"key":"33793_CR10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s12880-020-00530-y","volume":"21","author":"H Hirano","year":"2021","unstructured":"Hirano, H., Minagi, A. & Takemoto, K. Universal adversarial attacks on deep neural networks for medical image classification. BMC Med. Imaging 21, 9. https:\/\/doi.org\/10.1186\/s12880-020-00530-y (2021).","journal-title":"BMC Med. Imaging"},{"key":"33793_CR11","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005 (2017).","journal-title":"Med. Image Anal."},{"key":"33793_CR12","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6110121","author":"TG Debelee","year":"2020","unstructured":"Debelee, T. G., Kebede, S. R., Schwenker, F. & Shewarega, Z. M. Deep learning in selected cancers\u2019 image analysis\u2014a survey. J. Imaginghttps:\/\/doi.org\/10.3390\/jimaging6110121 (2020).","journal-title":"J. Imaging"},{"key":"33793_CR13","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1007\/s10278-017-0045-8","volume":"31","author":"LJ Caffery","year":"2018","unstructured":"Caffery, L. J. et al. Transforming dermatologic imaging for the digital era: Metadata and standards. J. Digit. Imaging 31, 568. https:\/\/doi.org\/10.1007\/s10278-017-0045-8 (2018).","journal-title":"J. Digit. Imaging"},{"key":"33793_CR14","doi-asserted-by":"publisher","first-page":"365","DOI":"10.4103\/ijd.IJD_421_20","volume":"65","author":"K Basu","year":"2020","unstructured":"Basu, K., Sinha, R., Ong, A. & Basu, T. Artificial intelligence: How is it changing medical sciences and its future?. Indian J. Dermatol. 65, 365. https:\/\/doi.org\/10.4103\/ijd.IJD_421_20 (2020).","journal-title":"Indian J. Dermatol."},{"key":"33793_CR15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2109.11369","author":"H Qu","year":"2021","unstructured":"Qu, H., Rahmani, H., Xu, L., Williams, B. & Liu, J. Recent advances of continual learning in computer vision: An overview. arXivhttps:\/\/doi.org\/10.48550\/arXiv.2109.11369 (2021).","journal-title":"arXiv"},{"key":"33793_CR16","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1162\/jocn_a_01544","volume":"33","author":"GW Lindsay","year":"2021","unstructured":"Lindsay, G. W. Convolutional neural networks as a model of the visual system: Past, present, and future. J. Cogn. Neurosci. 33, 2017\u20132031. https:\/\/doi.org\/10.1162\/jocn_a_01544 (2021).","journal-title":"J. Cogn. Neurosci."},{"key":"33793_CR17","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/tnnls.2020.3027314","volume":"32","author":"E Tjoa","year":"2021","unstructured":"Tjoa, E. & Guan, C. A survey on explainable artificial intelligence (XAI): Toward medical XAI. IEEE Trans. Neural Netw. Learn. Syst. 32, 4793\u20134813. https:\/\/doi.org\/10.1109\/tnnls.2020.3027314 (2021).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"33793_CR18","doi-asserted-by":"publisher","first-page":"2583","DOI":"10.2147\/OPTH.S251998","volume":"14","author":"AJ Kanellopoulos","year":"2020","unstructured":"Kanellopoulos, A. J. Scheimpflug vs Scanning-slit corneal tomography: Comparison of corneal and anterior chamber tomography indices for repeatability and agreement in healthy eyes. Clin. Ophthalmol. (Auckland, N.Z.) 14, 2583. https:\/\/doi.org\/10.2147\/OPTH.S251998 (2020).","journal-title":"Clin. Ophthalmol. (Auckland, N.Z.)"},{"key":"33793_CR19","doi-asserted-by":"publisher","DOI":"10.1145\/505248.506010","author":"L Pipino","year":"2003","unstructured":"Pipino, L., Lee, Y. & Wang, R. Data quality assessment. Commun. ACMhttps:\/\/doi.org\/10.1145\/505248.506010 (2003).","journal-title":"Commun. ACM"},{"key":"33793_CR20","doi-asserted-by":"publisher","first-page":"90","DOI":"10.5281\/zenodo.7697899","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter, J. D. Matplotlib: A 2d graphics environment. Comput. Sci. Eng. 9, 90\u201395. https:\/\/doi.org\/10.5281\/zenodo.7697899 (2007).","journal-title":"Comput. Sci. Eng."},{"key":"33793_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s40662-016-0038-6","author":"JK Duncan","year":"2016","unstructured":"Duncan, J. K., Belin, M. W. & Borgstrom, M. Assessing progression of keratoconus: Novel tomographic determinants. Eye Vis.https:\/\/doi.org\/10.1186\/s40662-016-0038-6 (2016).","journal-title":"Eye Vis."},{"key":"33793_CR22","doi-asserted-by":"publisher","unstructured":"Liu, Z. et\u00a0al. A convnet for the 2020s. https:\/\/doi.org\/10.48550\/ARXIV.2201.03545 (2022).","DOI":"10.48550\/ARXIV.2201.03545"},{"key":"33793_CR23","unstructured":"Maintainers, T. & contributors. TorchVision: PyTorch\u2019s Computer Vision library (2016)."},{"key":"33793_CR24","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"A Paszke","year":"2019","unstructured":"Paszke, A. et al. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems Vol. 32 (eds Wallach, H. et al.) 8024\u20138035 (Curran Associates Inc., 2019)."},{"key":"33793_CR25","doi-asserted-by":"publisher","unstructured":"Nicki Skafte Detlefsen et\u00a0al. TorchMetrics\u2014measuring reproducibility in PyTorch. https:\/\/doi.org\/10.21105\/joss.04101 (2022).","DOI":"10.21105\/joss.04101"},{"key":"33793_CR26","doi-asserted-by":"publisher","unstructured":"Sundararajan, M., Taly, A. & Yan, Q. Axiomatic attribution for deep networks. https:\/\/doi.org\/10.48550\/ARXIV.1703.01365 (2017).","DOI":"10.48550\/ARXIV.1703.01365"},{"key":"33793_CR27","unstructured":"Kokhlikyan, N. et\u00a0al. Captum: A unified and generic model interpretability library for pytorch (2020). 2009.07896."},{"key":"33793_CR28","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.2147\/OPTH.S215144","volume":"13","author":"HS Ong","year":"2019","unstructured":"Ong, H. S. et al. Corneal ectasia risk and percentage tissue altered in myopic patients presenting for refractive surgery. Clin. Ophthalmol. (Auckland, N.Z.) 13, 2003. https:\/\/doi.org\/10.2147\/OPTH.S215144 (2019).","journal-title":"Clin. Ophthalmol. (Auckland, N.Z.)"},{"key":"33793_CR29","doi-asserted-by":"publisher","first-page":"3021","DOI":"10.21105\/joss.03021","volume":"6","author":"ML Waskom","year":"2021","unstructured":"Waskom, M. L. Seaborn: Statistical data visualization. J. Open Source Softw. 6, 3021. https:\/\/doi.org\/10.21105\/joss.03021 (2021).","journal-title":"J. Open Source Softw."},{"key":"33793_CR30","doi-asserted-by":"publisher","DOI":"10.2196\/27363","volume":"9","author":"H Maile","year":"2021","unstructured":"Maile, H. et al. Machine learning algorithms to detect subclinical keratoconus: Systematic review. JMIR Med. Inform. 9, e27363. https:\/\/doi.org\/10.2196\/27363 (2021).","journal-title":"JMIR Med. Inform."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33793-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33793-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33793-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,21]],"date-time":"2023-04-21T09:04:36Z","timestamp":1682067876000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-33793-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,21]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["33793"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-33793-w","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-2241753\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,21]]},"assertion":[{"value":"5 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2023","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":"6566"}}