{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T16:10:48Z","timestamp":1792858248278,"version":"4.5.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"15","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Acer Incorporated"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eye"],"published-print":{"date-parts":[[2026,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background\/objectives<\/jats:title>\n                    <jats:p>This study aimed to develop an interpretable artificial intelligence (AI) screening system that replicates a specialist\u2019s evaluation of fundus photographs. The system analyses three signs: visible retinal nerve fibre layer (RNFL) defects (as observed on fundus photography, not OCT-based measurement), vertical cup-to-disc ratio (VCDR) and rim-to-disc ratio (RDR).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Subjects\/methods<\/jats:title>\n                    <jats:p>A total of 773 fundus images from the independent test cohort were annotated by three fellowship-trained glaucoma specialists, followed by repeated consensus meetings to improve annotation consistency. Two models were trained on the development cohort: an EfficientNet-B4 classifier for RNFL and a U-Net with an EfficientNet-B4 encoder for optic disc\/cup (OD\/OC) segmentation. During the testing phase, a referral was triggered whenever a feature was classified as abnormal, with the system explicitly reporting the specific sign that prompted the referral decision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 773 expert-annotated cases, 749 were included in the analysis after excluding low-quality or insufficient-information images (AI drop rate: 3.1%). The final independent test cohort comprised 268 referral and 481 non-referral cases, providing a basis for evaluation. The combined model achieved a sensitivity of 0.903 (95% confidence interval [CI], 0.868\u20130.938), specificity of 0.821 (95% CI, 0.787\u20130.855) and a positive predictive value (PPV) of 0.738 (95% CI, 0.690\u20130.785). The system captured complementary aspects of glaucomatous optic neuropathy that are often missed by single-feature approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Consensus-based annotation, combined with lesion-level modelling, enhances alignment with clinical reasoning. By providing an explicit referral rationale, the system fosters trust in AI-assisted glaucoma screening and facilitates adoption in clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s41433-026-04758-w","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T06:50:17Z","timestamp":1784789417000},"page":"2424-2431","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Clinically aligned artificial intelligence for glaucoma diagnosis: enhancing retinal nerve fibre layer interpretation from fundus images"],"prefix":"10.1038","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-5962-8913","authenticated-orcid":false,"given":"Shang-Lin","family":"Chung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jehn-Yu","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Ching","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9220-7599","authenticated-orcid":false,"given":"Chien-Chia","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Hsia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pai-Huei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pei-Yao","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo-I","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8881-6252","authenticated-orcid":false,"given":"Chien-Hung","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming-Chi","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Jin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei-Hao","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai-Cheng","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4703-6628","authenticated-orcid":false,"given":"Chia-En","family":"Lien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"4758_CR1","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1136\/bjo.2005.081224","volume":"90","author":"HA Quigley","year":"2006","unstructured":"Quigley HA, Broman AT. The number of people with glaucoma worldwide in 2010 and 2020. Br J Ophthalmol. 2006;90:262\u20137.","journal-title":"Br J Ophthalmol"},{"key":"4758_CR2","doi-asserted-by":"publisher","first-page":"1901","DOI":"10.1001\/jama.2014.3192","volume":"311","author":"RN Weinreb","year":"2014","unstructured":"Weinreb RN, Aung T, Medeiros FA. The pathophysiology and treatment of glaucoma: a review. JAMA. 2014;311:1901\u201311.","journal-title":"JAMA"},{"key":"4758_CR3","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1111\/j.1755-3768.2007.00947.x","volume":"85","author":"H Vaahtoranta-Lehtonen","year":"2007","unstructured":"Vaahtoranta-Lehtonen H, Tuulonen A, Aronen P, Sintonen H, Suoranta L, Kovanen N, et al. Cost-effectiveness and cost-utility of an organized screening programme for glaucoma. Acta Ophthalmol Scand. 2007;85:508\u201318.","journal-title":"Acta Ophthalmol Scand"},{"key":"4758_CR4","doi-asserted-by":"crossref","unstructured":"Burr JM, Mowatt G, Hern\u00e1ndez R, Siddiqui MAR, Cook J, Lourenco T, et al. The clinical effectiveness and cost-effectiveness of screening for open-angle glaucoma: a systematic review and economic evaluation. In: NIHR Health Technology Assessment programme: Executive Summaries. NIHR Journals Library, Southampton. 2007.","DOI":"10.3310\/hta11410"},{"key":"4758_CR5","doi-asserted-by":"publisher","first-page":"1444","DOI":"10.1001\/archopht.1979.01020020106002","volume":"97","author":"A Sommer","year":"1979","unstructured":"Sommer A, Pollack I, Maumenee AE. Optic disc parameters and onset of glaucomatous field loss. Arch Ophthalmol. 1979;97:1444\u20138.","journal-title":"Arch Ophthalmol"},{"key":"4758_CR6","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1016\/S0161-6420(92)31774-9","volume":"99","author":"BE Klein","year":"1992","unstructured":"Klein BE, Klein R, Sponsel WE, Franke T, Cantor LB, Martone J, et al. Prevalence of glaucoma. The beaver dam eye Study. Ophthalmology. 1992;99:1499\u2013504.","journal-title":"Ophthalmology"},{"key":"4758_CR7","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1001\/archopht.1994.01090180121046","volume":"112","author":"MC Leske","year":"1994","unstructured":"Leske MC, Connell AM, Schachat AP, Hyman L. The Barbados Eye Study. Prevalence of open-angle glaucoma. Arch Ophthalmol. 1994;112:821\u20139.","journal-title":"Arch Ophthalmol"},{"key":"4758_CR8","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1136\/bjo.86.2.238","volume":"86","author":"PJ Foster","year":"2002","unstructured":"Foster PJ, Buhrmann R, Quigley HA, Johnson GJ. The definition and classification of glaucoma in prevalence surveys. Br J Ophthalmol. 2002;86:238\u201342.","journal-title":"Br J Ophthalmol"},{"key":"4758_CR9","doi-asserted-by":"publisher","first-page":"1011","DOI":"10.1001\/archopht.1984.01040030813022","volume":"102","author":"AG Balazsi","year":"1984","unstructured":"Balazsi AG, Drance SM, Schulzer M, Douglas GR. Neuroretinal rim area in suspected glaucoma and early chronic open-angle glaucoma. Correlation with parameters of visual function. Arch Ophthalmol. 1984;102:1011\u20134.","journal-title":"Arch Ophthalmol"},{"key":"4758_CR10","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1136\/bjo.82.12.1366","volume":"82","author":"JB Jonas","year":"1998","unstructured":"Jonas JB, Budde WM, Lang P. Neuroretinal rim width ratios in morphological glaucoma diagnosis. Br J Ophthalmol. 1998;82:1366\u201371.","journal-title":"Br J Ophthalmol"},{"key":"4758_CR11","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/S0002-9394(02)01833-0","volume":"135","author":"JD Henderer","year":"2003","unstructured":"Henderer JD, Liu C, Kesen M, Altangerel U, Bayer A, Steinmann WC, et al. Reliability of the disk damage likelihood scale. Am J Ophthalmol. 2003;135:44\u201348.","journal-title":"Am J Ophthalmol"},{"key":"4758_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-43385-2","volume":"9","author":"JRH Kumar","year":"2019","unstructured":"Kumar JRH, Seelamantuis CS, Kamath YS, Jampala R. Rim-to-disc ratio outperforms cup-to-disc ratio for glaucoma prescreening. Sci Rep. 2019;9:7099.","journal-title":"Sci Rep"},{"key":"4758_CR13","first-page":"814","volume":"12","author":"WF Hoyt","year":"1973","unstructured":"Hoyt WF, Fris\u00e9n L, Newman NM. Fundoscopy of nerve fiber layer defects in glaucoma. Investig Ophthalmol. 1973;12:814\u201329.","journal-title":"Investig Ophthalmol"},{"key":"4758_CR14","first-page":"920","volume":"84","author":"HA Quigley","year":"1986","unstructured":"Quigley HA. Examination of the retinal nerve fiber layer in the recognition of early glaucoma damage. Trans Am Ophthalmol Soc. 1986;84:920\u201366.","journal-title":"Trans Am Ophthalmol Soc"},{"key":"4758_CR15","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/S0161-6420(92)32018-4","volume":"99","author":"HA Quigley","year":"1992","unstructured":"Quigley HA, Katz J, Derick RJ, Gilbert D, Sommer A. An evaluation of optic disc and nerve fiber layer examinations in monitoring progression of early glaucoma damage. Ophthalmology. 1992;99:19\u201328.","journal-title":"Ophthalmology"},{"key":"4758_CR16","first-page":"3065","volume":"2010","author":"Z Zhang","year":"2010","unstructured":"Zhang Z, Yin FS, Liu J, Wong WK, Tan NM, Lee BH, et al. ORIGA(-light): an online retinal fundus image database for glaucoma analysis and research. Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:3065\u20138.","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"4758_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570","volume":"59","author":"JI Orlando","year":"2020","unstructured":"Orlando JI, Fu H, Barbosa Breda J, van Keer K, Bathula DR, Diaz-Pinto A, et al. REFUGE Challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal. 2020;59:101570.","journal-title":"Med Image Anal"},{"key":"4758_CR18","doi-asserted-by":"publisher","first-page":"2485","DOI":"10.1109\/TMI.2019.2899910","volume":"38","author":"S Wang","year":"2019","unstructured":"Wang S, Yu L, Yang X, Fu CW, Heng PA. Patch-based output space adversarial learning for joint optic disc and cup segmentation. IEEE Trans Med Imaging. 2019;38:2485\u201395.","journal-title":"IEEE Trans Med Imaging"},{"key":"4758_CR19","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1016\/j.neucom.2021.08.102","volume":"464","author":"P Yin","year":"2021","unstructured":"Yin P, Xu Y, Zhu J, Liu J, Yi C, Huang H, et al. Deep level set learning for optic disc and cup segmentation. Neurocomputing. 2021;464:330\u201341.","journal-title":"Neurocomputing"},{"key":"4758_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2025.102559","volume":"123","author":"R Pannu","year":"2025","unstructured":"Pannu R, Zubair M, Owais M, Hassan S, Umair M, Usman SM, et al. Enhanced glaucoma classification through advanced segmentation by integrating cup-to-disc ratio and neuro-retinal rim features. Comput Med Imaging Graph. 2025;123:102559.","journal-title":"Comput Med Imaging Graph"},{"key":"4758_CR21","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1001\/jamaophthalmol.2019.3501","volume":"137","author":"H Liu","year":"2019","unstructured":"Liu H, Li L, Wormstone IM, Qiao C, Zhang C, Liu P, et al. Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol. 2019;137:1353\u201360.","journal-title":"JAMA Ophthalmol"},{"key":"4758_CR22","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.ajo.2020.12.031","volume":"225","author":"T Lee","year":"2021","unstructured":"Lee T, Jammal AA, Mariottoni EB, Medeiros FA. Predicting glaucoma development with longitudinal deep learning predictions from fundus photographs. Am J Ophthalmol. 2021;225:86\u201394.","journal-title":"Am J Ophthalmol"},{"key":"4758_CR23","doi-asserted-by":"publisher","first-page":"2894","DOI":"10.3390\/diagnostics12112894","volume":"12","author":"H Yang","year":"2022","unstructured":"Yang H, Ahn Y, Askaruly S, You JS, Kim SW, Jung W. Deep learning-based glaucoma screening using regional RNFL thickness in fundus photography. Diagnostics. 2022;12:2894.","journal-title":"Diagnostics"},{"key":"4758_CR24","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1038\/s41746-025-01473-w","volume":"8","author":"P Sharma","year":"2025","unstructured":"Sharma P, Takahashi N, Ninomiya T, Sato M, Miya T, Tsuda S, et al. A hybrid multi-model artificial intelligence approach for glaucoma screening using fundus images. npj Digit Med. 2025;8:130.","journal-title":"npj Digit Med"},{"key":"4758_CR25","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1001\/jamaophthalmol.2022.0244","volume":"140","author":"R Fan","year":"2022","unstructured":"Fan R, Bowd C, Christopher M, Brye N, Proudfoot JA, Rezapour J, et al. Detecting glaucoma in the ocular hypertension study using deep learning. JAMA Ophthalmol. 2022;140:383\u201391.","journal-title":"JAMA Ophthalmol"},{"key":"4758_CR26","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R. Visualizing and understanding convolutional networks. 2014.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"4758_CR27","unstructured":"Tan M, Le Q. Efficientnet: rethinking model scaling for convolutional neural networks. In: Proceedings of the International conference on machine learning. 2019."},{"key":"4758_CR28","doi-asserted-by":"crossref","unstructured":"Baheti B, Innani S, Gajre S, Talbar S. Eff-UNet: A novel architecture for semantic segmentation in an unstructured environment. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops. 2020.","DOI":"10.1109\/CVPRW50498.2020.00187"}],"container-title":["Eye"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41433-026-04758-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41433-026-04758-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41433-026-04758-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T17:55:41Z","timestamp":1792173341000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41433-026-04758-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":28,"journal-issue":{"issue":"15","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["4758"],"URL":"https:\/\/doi.org\/10.1038\/s41433-026-04758-w","relation":{},"ISSN":["0950-222X","1476-5454"],"issn-type":[{"value":"0950-222X","type":"print"},{"value":"1476-5454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"assertion":[{"value":"30 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Shang-Lin Chung,\u00a0Ming-Chi Kuo, Wei-Hao Chang\u00a0and Chia-En Lien\u00a0are employed at Acer Incorporated. Chien-Hung Li, Yi-Jin Huang\u00a0and Kai-Cheng Hsu are employed at Acer Medical Inc. All other authors declare no conflicts of interest.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}]}}