{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T18:29:24Z","timestamp":1786645764668,"version":"build-2736575974"},"reference-count":20,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ziemer Ophthalmics, Bern, Switzerland"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>This feasibility study developed and validated an AI algorithm for automatic classification of human lens opacification (cataracts) using anterior segment optical coherence tomography (OCT). The dataset comprised 1,802 unprocessed OCT images from 901 eyes, with cataract severity graded by slit-lamp examination using the Lens Opacities Classification System (LOCS) III. Nuclear opalescence (NO) was stratified as mild (\u22643.0), moderate (3.5\u20134.0), or severe (\u22654.5), while posterior subcapsular cataract (PSC) was classified as mild (&lt;4) or severe (\u22654). Nuclear color (NC) and cortical cataract (C) were not evaluated. After balancing, images were randomly divided into three sets: 70% for training, 20% for testing and 10% for validation. A convolutional neural network was trained five times. Patients had a mean age of 72\u2009\u00b1\u20098.8 years, with mean LOCS III grades of 3.81\u2009\u00b1\u20090.79 (NO) and 1.74\u2009\u00b1\u20091.55 (PSC). The AI achieved 60.3% accuracy for NO classification; among misclassifications, 34.9% were within one category, 4.8% were grossly inaccurate. PSC classification performed with 86.4% accuracy, yielding a true positive rate of 81.8% and a true negative rate of 90.9%. These results demonstrate the potential of deep learning for automated cataract grading.<\/jats:p>","DOI":"10.1371\/journal.pone.0355969","type":"journal-article","created":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:35:36Z","timestamp":1786642536000},"page":"e0355969","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence-based grading of human cataracts: A feasibility study"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8003-4547","authenticated-orcid":true,"given":"Catharina","family":"Latz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Franziska","family":"Rothen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annika","family":"Licht","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katharina A.","family":"Ponto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Mirshahi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,13]]},"reference":[{"key":"pone.0355969.ref001","author":"World Health Organization. World Report on Vision","year":"2019"},{"key":"pone.0355969.ref002","author":"Eurostat"},{"issue":"6","key":"pone.0355969.ref003","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1515\/aot-2021-0044","article-title":"Femtosecond lasers for eye surgery applications: historical overview and modern low pulse energy concepts","volume":"10","author":"T Asshauer","year":"2021","journal-title":"Advanced Optical Technologies"},{"issue":"6","key":"pone.0355969.ref004","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1001\/archopht.1993.01090060119035","article-title":"The Lens Opacities Classification System III. The Longitudinal Study of Cataract Study Group","volume":"111","author":"LT Chylack","year":"1993","journal-title":"Arch Ophthalmol"},{"issue":"3","key":"pone.0355969.ref005","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1007\/s11633-022-1329-0","article-title":"Machine Learning for Cataract Classification\/Grading on Ophthalmic Imaging Modalities: A Survey","volume":"19","author":"XQ Zhang","year":"2022","journal-title":"Machine Intelligence Research"},{"key":"pone.0355969.ref006","first-page":"4971572","article-title":"Applications of Anterior Segment Optical Coherence Tomography in Cornea and Ocular Surface Diseases","volume":"2016","author":"SB Han","year":"2016","journal-title":"J Ophthalmol"},{"issue":"12","key":"pone.0355969.ref007","doi-asserted-by":"crossref","first-page":"1746","DOI":"10.1016\/j.jcrs.2019.07.033","article-title":"Average lens density quantification with swept-source optical coherence tomography: optimized, automated cataract grading technique","volume":"45","author":"C Panthier","year":"2019","journal-title":"J Cataract Refract Surg"},{"issue":"1","key":"pone.0355969.ref008","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1136\/bjo.2008.137653","article-title":"Quantitative assessment of lens opacities with anterior segment optical coherence tomography","volume":"93","author":"AL Wong","year":"2009","journal-title":"Br J Ophthalmol"},{"key":"pone.0355969.ref009","first-page":"3025413","article-title":"Quantitative Analysis of Lens Nuclear Density Using Optical Coherence Tomography (OCT) with a Liquid Optics Interface: Correlation between OCT Images and LOCS III Grading","volume":"2016","author":"YN Kim","year":"2016","journal-title":"J Ophthalmol"},{"issue":"10","key":"pone.0355969.ref010","doi-asserted-by":"crossref","first-page":"2406","DOI":"10.3390\/diagnostics12102406","article-title":"Automatic Quantitative Assessment of Lens Opacities Using Two Anterior Segment Imaging Techniques: Correlation with Functional and Surgical Metrics","volume":"12","author":"LHB Mackenbrock","year":"2022","journal-title":"Diagnostics"},{"issue":"2","key":"pone.0355969.ref011","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1167\/iovs.17-23596","article-title":"Three-Dimensional Cataract Crystalline Lens Imaging With Swept-Source Optical Coherence Tomography","volume":"59","author":"A de Castro","year":"2018","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"3","key":"pone.0355969.ref012","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1097\/j.jcrs.0000000000001598","article-title":"CATALYZE: a deep learning approach for cataract assessment and grading on SS-OCT images","volume":"51","author":"C Panthier","year":"2025","journal-title":"J Cataract Refract Surg"},{"issue":"8","key":"pone.0355969.ref013","doi-asserted-by":"crossref","first-page":"3821","DOI":"10.1364\/BOE.9.003821","article-title":"Volumetric macro- and micro-scale assessment of crystalline lens opacities in cataract patients using long-depth-range swept source optical coherence tomography","volume":"9","author":"I Grulkowski","year":"2018","journal-title":"Biomed Opt Express"},{"issue":"2","key":"pone.0355969.ref014","doi-asserted-by":"crossref","first-page":"1479","DOI":"10.1007\/s40747-022-00869-5","article-title":"Nuclear cataract classification in anterior segment OCT based on clinical global\u2013local features","volume":"9","author":"X Zhang","year":"2022","journal-title":"Complex Intell Syst"},{"key":"pone.0355969.ref015","doi-asserted-by":"crossref","unstructured":"Zhang X, Xiao Z, Higashita R, Chen W, Yuan J, Fang J, et al. A Novel Deep Learning Method for Nuclear Cataract Classification Based on Anterior Segment Optical Coherence Tomography Images. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2020. 662\u20138. https:\/\/doi.org\/10.1109\/smc42975.2020.9283218","DOI":"10.1109\/SMC42975.2020.9283218"},{"key":"pone.0355969.ref016","author":"scikit-learn Development Team"},{"issue":"2","key":"pone.0355969.ref017","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual explanations from deep networks via gradient-based localization","volume":"128","author":"RR Selvaraju","year":"2020","journal-title":"Int J Comput Vis"},{"issue":"2","key":"pone.0355969.ref018","doi-asserted-by":"crossref","first-page":"122","DOI":"10.3390\/mi12020122","article-title":"Femtosecond-Laser Assisted Surgery of the Eye: Overview and Impact of the Low-Energy Concept","volume":"12","author":"C Latz","year":"2021","journal-title":"Micromachines (Basel)"},{"key":"pone.0355969.ref019","doi-asserted-by":"crossref","first-page":"2021","DOI":"10.2147\/OPTH.S94306","article-title":"Update and clinical utility of the LenSx femtosecond laser in cataract surgery","volume":"10","author":"TV Roberts","year":"2016","journal-title":"Clin Ophthalmol"},{"issue":"5","key":"pone.0355969.ref020","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0251549","article-title":"Perioperative pupil size in low-energy femtosecond laser-assisted cataract surgery","volume":"16","author":"A Mirshahi","year":"2021","journal-title":"PLoS One"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355969","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T17:35:40Z","timestamp":1786642540000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0355969"}},"subtitle":[],"editor":[{"given":"Miquel","family":"Vall-llosera Camps","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,13]]},"references-count":20,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0355969","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,13]]}}}