{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:48:06Z","timestamp":1792514886844,"version":"4.5.0"},"reference-count":11,"publisher":"S. Karger AG","issue":"2","license":[{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/karger.com\/pages\/terms-and-conditions"},{"start":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T00:00:00Z","timestamp":1737676800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/karger.com\/pages\/terms-and-conditions"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ocul Oncol Pathol"],"abstract":"<jats:p>Introduction: Ocular surface squamous neoplasia (OSSN) is a broad entity encompassing a spectrum of squamous neoplasms of conjunctiva and cornea. This study aimed to explore the utility of artificial intelligence (AI) models in detecting OSSN from slit-lamp (SL) images. Methods: This is a retrospective observational study. SL images of OSSN disease, non-OSSN ocular surface lesions (OOSD), and normal ocular surfaces (N) were collected (2013\u20132023). Images with minimum resolution of 1,024 \u00d7 1,024 pixels under diffuse illumination were included. Data were divided into training and testing sets (85:15). Deep learning (DL) algorithms were applied for ternary classification of the SL images (OSSN, OOSD, and normal). Three AI models \u2013 MobileNetV2, Xception, and DenseNet121 \u2013 were used in the study. A fivefold cross-validation strategy was utilized for robust model evaluation. Results: A total of 163 images in OSSN group, 202 in OOSD group, and 269 normal ocular surface images were included (n = 634). Data augmentation was performed to increase and balance the data. The average accuracies for OSSN detection for DenseNet121, MobileNetV2, and Xception were 83%, 88.8%, and 84.5%, respectively. MobileNetV2 and Xception had a similar average sensitivity for OSSN detection (74%) while MobileNetV2 was the most specific DL algorithm (96.25%) for OSSN detection. Conclusions: AI models showed good performance in image-based OSSN detection. AI models may provide a promising tool for OSSN screening in primary health care centers and for teleconsultation from remote areas in the future. <\/jats:p>","DOI":"10.1159\/000543766","type":"journal-article","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T12:01:43Z","timestamp":1737720103000},"page":"73-81","source":"Crossref","is-referenced-by-count":11,"title":["Deep Learning-Based Detection of Ocular Surface Squamous Neoplasia from Ocular Surface Images"],"prefix":"10.1159","volume":"11","author":[{"given":"Obaidur","family":"Rehman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramkailash","family":"Gujar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ritul","family":"Kumawat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruby","family":"Pandey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chhavi","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shweta","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Virender","family":"Sangwan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sima","family":"Das","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"127","published-online":{"date-parts":[[2025,1,24]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.1084118"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtos.2019.03.003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/08820530500351694"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.4103\/ijo.IJO_1393_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00571-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4103\/ijo.IJO_644_22"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18240\/ijo.2018.09.21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1097\/ICL.0b013e318235c4d3"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/s0039-6257(05)80054-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1097\/ICL.0b013e31815700af"}],"container-title":["Ocular Oncology and Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/karger.com\/oop\/article-pdf\/doi\/10.1159\/000543766\/4327873\/000543766.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/karger.com\/article-pdf\/doi\/10.1159\/000543766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,25]],"date-time":"2025-07-25T16:01:09Z","timestamp":1753459269000},"score":1,"resource":{"primary":{"URL":"https:\/\/karger.com\/article\/doi\/10.1159\/000543766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,24]]},"references-count":11,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,7,25]]},"published-print":{"date-parts":[[2025,7,30]]}},"URL":"https:\/\/doi.org\/10.1159\/000543766","archive":["Portico"],"relation":{"is-supplemented-by":[{"id-type":"doi","id":"10.6084\/m9.figshare.28263002","asserted-by":"subject"}]},"ISSN":["2296-4681","2296-4657"],"issn-type":[{"value":"2296-4681","type":"print"},{"value":"2296-4657","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,24]]}}}