{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T10:47:53Z","timestamp":1767869273273,"version":"3.49.0"},"reference-count":16,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"unspecified","delay-in-days":14,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Ophth"],"accepted":{"date-parts":[[2025,6,15]]},"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To investigate whether corneal changes observed via in vivo confocal microscopy (IVCM) in patients with aniridia-related keratopathy (ARK) reflect clinical severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A cross-sectional, observational study. Patients with congenital aniridia and healthy controls were included. IVCM of the epithelium, anterior stroma and posterior stroma were collected, manually annotated and analysed using the pretrained DINOv2 model as a feature extractor. High-dimensional embeddings were visualised using t-distributed stochastic neighbour embedding (t-SNE) to assess layer-specific clustering. Structural deviations from normal controls were quantified using centroid and Euclidean distance metrics. The cumulative structural changes across corneal layers were then correlated with Ocular Surface Score (OSS), a clinical grading scale for ARK severity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>20 patients with congenital aniridia and six healthy controls were included. t-SNE analysis revealed distinct clusters for normal corneal layers; whereas, ARK samples displayed overlapping clusters, suggestive of blurred structural boundaries. Notably, significant clustering patterns were observed in the anterior stroma, even in cases with mild ARK, underscoring its potential as an early disease marker. Anterior stromal changes were significantly associated with OSS scores (p&lt;0.05), while cumulative structural deviations across all layers demonstrated a stronger correlation with disease severity (p&lt;0.01). The posterior stroma showed relative structural preservation, aligning closely with healthy controls.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DINOv2 is a useful tool for identifying subtle structural changes in corneal layers affected by ARK. The corneal stromal features characterised using IVCM showed strong associations with clinical disease and may serve as structural biomarkers of clinical disease.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjophth-2025-002300","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T08:50:15Z","timestamp":1752655815000},"page":"e002300","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Characterising corneal changes in aniridia-related keratopathy using in vivo confocal microscopy and a self-supervised AI model"],"prefix":"10.1136","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7810-6169","authenticated-orcid":false,"given":"Abigail Eve","family":"Kaye","sequence":"first","affiliation":[{"name":"University College London, London, UK"},{"name":"Moorfields Eye Hospital NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7873-0922","authenticated-orcid":false,"given":"Yalin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Eye and Vision Science, University of Liverpool, Liverpool, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8336-4314","authenticated-orcid":false,"given":"Sajjad","family":"Ahmad","sequence":"additional","affiliation":[{"name":"University College London, London, UK"},{"name":"Moorfields Eye Hospital NHS Foundation Trust, London, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"239","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"2026010721210079000_10.1.e002300.1","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.jtos.2024.07.010","article-title":"A novel artificial intelligence model for diagnosing Acanthamoeba keratitis through confocal microscopy","volume":"34","author":"Shareef","year":"2024","journal-title":"Ocul Surf"},{"key":"2026010721210079000_10.1.e002300.2","doi-asserted-by":"crossref","DOI":"10.1167\/tvst.12.11.29","article-title":"AI-Based Decision-Support System for Diagnosing Acanthamoeba Keratitis Using In Vivo Confocal Microscopy Images","volume":"12","author":"Lincke","year":"2023","journal-title":"Transl Vis Sci Technol"},{"key":"2026010721210079000_10.1.e002300.3","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-35085-9","article-title":"Interpretable deep learning for diagnosis of fungal and acanthamoeba keratitis using in vivo confocal microscopy images","volume":"13","author":"Essalat","year":"2023","journal-title":"Sci Rep"},{"key":"2026010721210079000_10.1.e002300.4","doi-asserted-by":"publisher","DOI":"10.1007\/s00125-021-05617-x"},{"key":"2026010721210079000_10.1.e002300.5","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s00125-019-05023-4","article-title":"An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study","volume":"63","author":"Williams","year":"2020","journal-title":"Diabetologia"},{"key":"2026010721210079000_10.1.e002300.6","doi-asserted-by":"crossref","DOI":"10.3390\/jcm11206199","article-title":"Artificial Intelligence and Corneal Confocal Microscopy: The Start of a Beautiful Relationship","volume":"11","author":"Alam","year":"2022","journal-title":"J Clin Med"},{"key":"2026010721210079000_10.1.e002300.7","unstructured":"Dosovitskiy A , Beyer L , Kolesnikov A , et al . An image is worth 16x16 words: transformers for image recognition at scale. arXiv 2020."},{"key":"2026010721210079000_10.1.e002300.8","unstructured":"Oquab M , Darcet T , Moutakanni T , et al . DINOv2: Learning robust visual features without supervision. arXiv 2024."},{"key":"2026010721210079000_10.1.e002300.9","doi-asserted-by":"crossref","unstructured":"Men Y , Fhima J , Celi LA , et al . Deep learning generalization for diabetic retinopathy staging from fundus images. Physiol Meas 2025;13. doi:10.1088\/1361-6579\/ada86a","DOI":"10.1088\/1361-6579\/ada86a"},{"key":"2026010721210079000_10.1.e002300.10","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-011-0841-3"},{"key":"2026010721210079000_10.1.e002300.11","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1002\/sctm.18-0140","article-title":"Allogeneic Ex Vivo Expanded Corneal Epithelial Stem Cell Transplantation: A Randomized Controlled Clinical Trial","volume":"8","author":"Campbell","year":"2019","journal-title":"Stem Cells Transl Med"},{"key":"2026010721210079000_10.1.e002300.12","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-019-45100-7","article-title":"Pax 6 Controls Neural Crest Potential of Limbal Niche Cells to Support Self-Renewal of Limbal Epithelial Stem Cells","volume":"9","author":"Chen","year":"2019","journal-title":"Sci Rep"},{"key":"2026010721210079000_10.1.e002300.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtos.2015.12.006"},{"key":"2026010721210079000_10.1.e002300.14","doi-asserted-by":"publisher","DOI":"10.1097\/00003226-199809000-00012"},{"key":"2026010721210079000_10.1.e002300.15","doi-asserted-by":"crossref","DOI":"10.1038\/s41377-023-01224-0","article-title":"Unveiling the lamellar structure of the human cornea over its full thickness using polarization-resolved SHG microscopy","volume":"12","author":"Raoux","year":"2023","journal-title":"Light Sci Appl"},{"key":"2026010721210079000_10.1.e002300.16","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1080\/02713683.2024.2320779","article-title":"Examination of Subbasal Nerve Plexus and Central Corneal Stromal Microstructure in Subjects With Congenital Aniridia, Using in Vivo Confocal Laser Scanning Microscopy","volume":"49","author":"Csorba","year":"2024","journal-title":"Curr Eye Res"}],"container-title":["BMJ Open Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjophth-2025-002300","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:21:53Z","timestamp":1767849713000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjophth.bmj.com\/lookup\/doi\/10.1136\/bmjophth-2025-002300"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":16,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,7,16]]},"published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1136\/bmjophth-2025-002300"],"URL":"https:\/\/doi.org\/10.1136\/bmjophth-2025-002300","relation":{},"ISSN":["2397-3269"],"issn-type":[{"value":"2397-3269","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}