{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:14Z","timestamp":1785545054458,"version":"3.56.0"},"reference-count":57,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Form Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Optic disc tilt is a morphological change in myopic eyes that complicates clinical interpretation and artificial intelligence (AI)\u2013based analysis of fundus images. Accurate detection of optic disc tilt is necessary to avoid misinterpretation of disc morphology and enhance diagnostic reliability across different disease types.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study developed and externally validated an end-to-end AI-based pipeline for optic disc segmentation and quantitative tilt classification in color fundus photographs (CFPs), offering an objective alternative to manual segmentation and subjective clinical assessments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We trained a nnU-Net\u2013based optic disc segmentation model on the Standardized Multi-Channel Dataset for Glaucoma (SMDG; n=3103 CFPs) and externally validated it on the Samsung Medical Center (SMC) dataset (n=2448 CFPs from n=1370 patients). Model generalizability was assessed using both a fixed 80:20 random split and 5-fold cross-validation. Tilt was classified using the ratio of the long-axis diameter to the short-axis diameter, with a ratio of \u22651.3 indicating tilt. Segmentation performance was evaluated using the Dice similarity coefficient, intersection over union, and pixel accuracy on the SMDG dataset and using the clinical acceptance rate determined by 2 independent ophthalmologists on the external SMC dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using the SMDG dataset, nnU-Net achieved consistently high performance, with mean Dice similarity coefficients of 0.956 (SD 0.042) across 5-fold cross-validation and 0.961 (SD 0.055) for the best-performing single-fold model across 8 datasets. On the SMC dataset, 2 independent expert reviews yielded mean clinical acceptance rates of 98.61% and 98.86% across disease types, with acceptance rates ranging from 81.63% and 93.88% for edema to 99.59% and 99.17% for pallor, respectively. Tilt was detected in 7.5% (186\/2448) of images, with rates of 9.7% (118\/1215) for normal images, 3.9% (35\/894) for glaucoma, 7.8% (19\/241) for pallor, and 14.2% (14\/98) for edema. Segmentation errors were observed in 1.39% (34\/2448) and 1.14% (28\/2448) of cases by the 2 reviewers, mainly due to edema-related swelling, peripapillary atrophy, and vessel confusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our pipeline provides objective and reproducible detection of optic disc tilt in CFPs, with strong generalizability to clinical images. By replacing manual segmentation and subjective assessments, the pipeline supports tilt-aware AI diagnostics and scalable screening for myopia-related conditions, with future refinements needed to address edema-related challenges.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/86380","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T12:35:08Z","timestamp":1779712508000},"page":"e86380-e86380","source":"Crossref","is-referenced-by-count":0,"title":["Automated Optic Disc Tilt Classification in Fundus Photographs Using Segmentation and the Elliptical Ratio: External Clinical Validation Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8592-1153","authenticated-orcid":false,"given":"Chae Yeon","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8003-5849","authenticated-orcid":false,"given":"Jaeryung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2100-1876","authenticated-orcid":false,"given":"Joonhyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5508-3024","authenticated-orcid":false,"given":"Chaeyeon","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5029-4708","authenticated-orcid":false,"given":"Euido","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6271-3343","authenticated-orcid":false,"given":"Myung Jin","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6331-6630","authenticated-orcid":false,"given":"Sei Yeul","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2591-0129","authenticated-orcid":false,"given":"Taeyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7907-5635","authenticated-orcid":false,"given":"Kyung Ah","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1136\/bjo-2024-325427","article-title":"Global prevalence, trend and projection of myopia in children and adolescents from 1990 to 2050: a comprehensive systematic review and meta-analysis","volume":"109","author":"Liang","journal-title":"Br J Ophthalmol"},{"issue":"9827","key":"R2","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1016\/S0140-6736(12)60272-4","article-title":"Myopia","volume":"379","author":"Morgan","journal-title":"Lancet"},{"issue":"3","key":"R3","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.aopr.2024.06.003","article-title":"Complications of high myopia: an update from clinical manifestations to underlying mechanisms","volume":"4","author":"Du","journal-title":"Adv Ophthalmol Pract Res"},{"issue":"5","key":"R4","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1177\/11206721211063716","article-title":"Research advance in optic disc tilt and rotation in high myopia and its implications for glaucoma and visual field defects","volume":"32","author":"Zhang","journal-title":"Eur J Ophthalmol"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2022.101156","article-title":"Myopia: histology, clinical features, and potential implications for the etiology of axial elongation","volume":"96","author":"Jonas","journal-title":"Prog Retin Eye Res"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-38960-6","article-title":"Vertical disc tilt and features of the optic nerve head anatomy are related to visual field defect in myopic eyes","volume":"9","author":"Park","journal-title":"Sci Rep"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-50256-4","article-title":"Deep learning-based optic disc classification is affected by optic-disc tilt","volume":"14","author":"Nam","journal-title":"Sci Rep"},{"issue":"18","key":"R8","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1056\/NEJMoa1917130","article-title":"Artificial intelligence to detect papilledema from ocular fundus photographs","volume":"382","author":"Milea","journal-title":"N Engl J Med"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","first-page":"97","DOI":"10.18502\/jovr.v18i1.12730","article-title":"Clinical applications of artificial intelligence in glaucoma","volume":"18","author":"Yousefi","journal-title":"J Ophthalmic Vis Res"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","DOI":"10.1186\/s12886-020-01657-w","article-title":"Computer-aided recognition of myopic tilted optic disc using deep learning algorithms in fundus photography","volume":"20","author":"Cho","journal-title":"BMC Ophthalmol"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.survophthal.2022.08.005","article-title":"Automatic detection of glaucoma via fundus imaging and artificial intelligence: a review","volume":"68","author":"Coan","journal-title":"Surv Ophthalmol"},{"key":"R12","unstructured":"Kiefer R . SMDG, a standardized fundus glaucoma dataset. Kaggle. URL: https:\/\/www.kaggle.com\/datasets\/deathtrooper\/multichannel-glaucoma-benchmark-dataset [Accessed 04-06-2026]"},{"issue":"11","key":"R13","doi-asserted-by":"publisher","first-page":"6925","DOI":"10.1167\/iovs.15-17892","article-title":"Implications of optic disc tilt in the progression of primary open-angle glaucoma","volume":"56","author":"Lee","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"R14","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1094937","article-title":"Myopic tilted disc: mechanism, clinical significance, and public health implication","volume":"10","author":"Chan","journal-title":"Front Med (Lausanne)"},{"issue":"9","key":"R15","doi-asserted-by":"publisher","first-page":"1844","DOI":"10.1016\/j.ophtha.2012.03.006","article-title":"Optic disc torsion direction predicts the location of glaucomatous damage in normal-tension glaucoma patients with myopia","volume":"119","author":"Park","journal-title":"Ophthalmology"},{"key":"R16","doi-asserted-by":"crossref","unstructured":"Isensee F J\u00e4ger PF Kohl SA Petersen J Maier-Hein KH . Automated design of deep learning methods for biomedical image segmentation. arXiv. Preprint posted online on Apr 17, 2019. [doi: 10.1038\/s41592-020-01008-z]","DOI":"10.1038\/s41592-020-01008-z"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104699","article-title":"Sharp U-Net: depthwise convolutional network for biomedical image segmentation","volume":"136","author":"Zunair","journal-title":"Comput Biol Med"},{"issue":"5","key":"R18","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13966","article-title":"Hepatic vessels segmentation using deep learning and preprocessing enhancement","volume":"24","author":"Alirr","journal-title":"J Appl Clin Med Phys"},{"key":"R19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ibneur.2022.10.014","article-title":"A deep learning framework integrating MRI image preprocessing methods for brain tumor segmentation and classification","volume":"13","author":"Dang","journal-title":"IBRO Neurosci Rep"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101570","article-title":"REFUGE Challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs","volume":"59","author":"Orlando","journal-title":"Med Image Anal"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01388-1","article-title":"PAPILA: dataset with fundus images and clinical data of both eyes of the same patient for glaucoma assessment","volume":"9","author":"Kovalyk","journal-title":"Sci Data"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5626137","article-title":"ORIGA(-light): an online retinal fundus image database for glaucoma analysis and research","volume":"2010","author":"Zhang","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"R23","doi-asserted-by":"crossref","unstructured":"Bajwa MN Singh GA Neumeier W Malik MI Dengel A Ahmed S . G1020: a benchmark retinal fundus image dataset for computer-aided glaucoma detection. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE; 2020. [doi: 10.1109\/IJCNN48605.2020.9207664]","DOI":"10.1109\/IJCNN48605.2020.9207664"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Sivaswamy J Krishnadas SR Datt Joshi G Jain M Syed Tabish AU . Drishti-GS: retinal image dataset for optic nerve head (ONH) segmentation. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI). IEEE; 2014. [doi: 10.1109\/ISBI.2014.6867807]","DOI":"10.1109\/ISBI.2014.6867807"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1097\/ICB.0000000000001327","article-title":"Lisdexamfetamine (vyvanse) use associated with branch retinal artery occlusion","volume":"18","author":"Blair","journal-title":"Retin Cases Brief Rep"},{"issue":"1","key":"R26","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1109\/TMI.2010.2064333","article-title":"A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features","volume":"30","author":"Marin","journal-title":"IEEE Trans Med Imaging"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/180972","article-title":"Optic disc and optic cup segmentation methodologies for glaucoma image detection: a survey","volume":"2015","author":"Almazroa","journal-title":"J Ophthalmol"},{"issue":"18","key":"R28","doi-asserted-by":"publisher","DOI":"10.3390\/s22186899","article-title":"Multiple preprocessing hybrid level set model for optic disc segmentation in fundus images","volume":"22","author":"Xue","journal-title":"Sensors (Basel)"},{"issue":"3prt4","key":"R29","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1111\/cgf.12134","article-title":"Synthetic brainbows","volume":"32","author":"Wan","journal-title":"Comput Graph Forum"},{"key":"R30","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-7460-4","article-title":"Automated detection of glaucoma using deep learning convolution network (G-net)","volume":"79","author":"Juneja","journal-title":"Multimed Tools Appl"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.12.040","article-title":"Optic disc and cup segmentations for glaucoma assessment using cup-to-disc ratio","volume":"196","author":"Neto","journal-title":"Procedia Comput Sci"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3008539","article-title":"Dual machine-learning system to aid glaucoma diagnosis using disc and cup feature extraction","volume":"8","author":"Civit-Masot","journal-title":"IEEE Access"},{"key":"R33","unstructured":"Agrawal V Kori A Alex V Krishnamurthi G . Enhanced optic disk and cup segmentation with glaucoma screening from fundus images using position encoded CNNs. arXiv. Preprint posted online on Sep 14, 2018. [doi: 10.48550\/arXiv.1809.05216]"},{"issue":"14","key":"R34","doi-asserted-by":"publisher","first-page":"4916","DOI":"10.3390\/app10144916","article-title":"Deep learning for optic disc segmentation and glaucoma diagnosis on retinal images","volume":"10","author":"Sreng","journal-title":"Appl Sci"},{"key":"R35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.07.012","article-title":"Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation","volume":"55","author":"Zilly","journal-title":"Comput Med Imaging Graph"},{"issue":"1","key":"R36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2023.108247","article-title":"W-Net: a boundary-aware cascade network for robust and accurate optic disc segmentation","volume":"27","author":"Tang","journal-title":"iScience"},{"issue":"15","key":"R37","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ace6f0","article-title":"Predicting dice similarity coefficient of deformably registered contours using Siamese neural network","volume":"68","author":"Yeap","journal-title":"Phys Med Biol"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348697","article-title":"Probabilistic intersection-over-union for training and evaluation of oriented object detectors","volume":"33","author":"Murrugarra-Llerena","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"R39","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1016\/j.ogla.2022.02.004","article-title":"Prevalence and factors associated with optic disc tilt in the Primary Open-Angle African American Glaucoma Genetics study","volume":"5","author":"Daniel","journal-title":"Ophthalmol Glaucoma"},{"key":"R40","doi-asserted-by":"crossref","unstructured":"Ronneberger O Fischer P Brox T . U-Net: convolutional networks for biomedical image segmentation. In: Navab N Hornegger J Wells W Frangi A , editors. Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015. Springer; 2015. [doi: 10.1007\/978-3-319-24574-4_28]","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"4","key":"R41","first-page":"24","volume":"2","author":"Zhu","journal-title":"J Comput Sci Softw Appl"},{"key":"R42","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","journal-title":"Med Image Anal"},{"issue":"5","key":"R43","doi-asserted-by":"publisher","first-page":"2958","DOI":"10.1167\/iovs.14-15953","article-title":"Lamina cribrosa configuration in tilted optic discs with different tilt axes: a new hypothesis regarding optic disc tilt and torsion","volume":"56","author":"Lee","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"1","key":"R44","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-26520-4","article-title":"Deep learning-based 3D OCT imaging for detection of lamina cribrosa defects in eyes with high myopia","volume":"12","author":"Ota-Itadani","journal-title":"Sci Rep"},{"key":"R45","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2024.1366593","article-title":"Multimodal imaging of optic nerve head abnormalities in high myopia","volume":"15","author":"Hu","journal-title":"Front Neurol"},{"issue":"1","key":"R46","doi-asserted-by":"publisher","DOI":"10.1186\/s40662-024-00411-3","article-title":"Exploring optical coherence tomography parameters in eyes with myopic tilted disc","volume":"11","author":"Zhang","journal-title":"Eye Vis (Lond)"},{"key":"R47","doi-asserted-by":"publisher","DOI":"10.1016\/j.preteyeres.2020.100933","article-title":"Optic nerve head anatomy in myopia and glaucoma, including parapapillary zones alpha, beta, gamma and delta: histology and clinical features","volume":"83","author":"Wang","journal-title":"Prog Retin Eye Res"},{"issue":"8","key":"R48","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.1007\/s40123-024-00981-4","article-title":"Retina fundus photograph-based artificial intelligence algorithms in medicine: a systematic review","volume":"13","author":"Grzybowski","journal-title":"Ophthalmol Ther"},{"key":"R49","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-11056-y","article-title":"A comprehensive review of optic disc segmentation methods in adult and pediatric retinal images: from conventional methods to artificial intelligence (CR-ODSeg-AP-CM2AI)","volume":"58","author":"Bansal","journal-title":"Artif Intell Rev"},{"issue":"2","key":"R50","doi-asserted-by":"publisher","first-page":"145","DOI":"10.4258\/hir.2023.29.2.145","article-title":"Automatic method for optic disc segmentation using deep learning on retinal fundus images","volume":"29","author":"Septiarini","journal-title":"Healthc Inform Res"},{"issue":"5","key":"R51","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1001\/jamaophthalmol.2014.96","article-title":"Glaucomatous optic neuropathy evaluation project: factors associated with underestimation of glaucoma likelihood","volume":"132","author":"O\u2019Neill","journal-title":"JAMA Ophthalmol"},{"issue":"4","key":"R52","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1046\/j.1475-1313.2000.00528.x","volume":"20","author":"Harper","journal-title":"Ophthalmic Physiol Opt"},{"issue":"2","key":"R53","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/s0161-6420(92)31990-6","article-title":"Expert agreement in evaluating the optic disc for glaucoma","volume":"99","author":"Varma","journal-title":"Ophthalmology"},{"key":"R54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2016.06.005","article-title":"Visual field progression pattern associated with optic disc tilt morphology in myopic open-angle glaucoma","volume":"169","author":"Han","journal-title":"Am J Ophthalmol"},{"issue":"2","key":"R55","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1097\/IJG.0000000000000528","article-title":"Patterns of damage in young myopic glaucomatous-appearing patients with different optic disc tilt direction","volume":"26","author":"Lee","journal-title":"J Glaucoma"},{"key":"R56","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.835804","article-title":"Benefits of integrating telemedicine and artificial intelligence into outreach eye care: stepwise approach and future directions","volume":"9","author":"Chia","journal-title":"Front Med (Lausanne)"},{"key":"R57","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2025.1576465","article-title":"Artificial intelligence technology in ophthalmology public health: current applications and future directions","volume":"13","author":"Chen","journal-title":"Front Cell Dev Biol"}],"container-title":["JMIR Formative Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e86380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:32Z","timestamp":1785536732000},"score":1,"resource":{"primary":{"URL":"https:\/\/formative.jmir.org\/2026\/1\/e86380"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":57,"URL":"https:\/\/doi.org\/10.2196\/86380","relation":{},"ISSN":["2561-326X"],"issn-type":[{"value":"2561-326X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"article-number":"v10i3e86380"}}