{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T06:04:54Z","timestamp":1784009094362,"version":"3.55.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Subclinical retinal microvascular remodeling may occur before clinically detectable diabetic retinopathy (DR). This study investigated artificial intelligence (AI)-derived ultra-widefield retinal vascular metrics in patients with type 2 diabetes mellitus (T2DM) with and without non-proliferative DR (NPDR), and evaluated their potential for early vascular phenotyping and diagnostic discrimination.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this observational cross-sectional single-center study, 237 participants were included: 63 healthy controls (103 eyes), 101 patients with T2DM without DR (No-DR; 201 eyes), and 73 patients with NPDR (132 eyes). Non-mydriatic 200-degree ultra-widefield fundus images were analyzed using an AI-based vascular segmentation and quantification system. AI-exported values coded as -1 were treated as missing, and sparse parameters were excluded from primary inference. Intergroup comparisons of retained vascular parameters were performed using age- and sex-adjusted mixed-effects models with participant as a random intercept, followed by Benjamini-Hochberg false discovery rate (FDR) correction. Multiparameter logistic models were evaluated using 5-fold subject-level cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      After quality control, covariate adjustment, and FDR correction, 38 vascular-parameter rows remained significant. Whole-field vessel density was highest in the No-DR group, intermediate in NPDR, and lowest in controls [control, 0.017 (0.008\u20130.023); No-DR, 0.026 (0.020\u20130.032); NPDR, 0.021 (0.015\u20130.026); FDR\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001]. Fractal-dimension metrics showed similar early alterations, with arterial fractal dimension increased in No-DR and intermediate in NPDR [control, 1.287 (1.164\u20131.359); No-DR, 1.380 (1.328\u20131.420); NPDR, 1.329 (1.271\u20131.374); FDR\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001]. Whole-field mean vessel diameter was lower in No-DR than in controls, whereas total vessel length decreased across controls, No-DR, and NPDR (FDR P &amp;lt; 0.001 for both). Regional heatmaps showed that significant density and fractal-dimension signals clustered mainly in the superotemporal, superonasal, and inferotemporal regions. Cross-validated models showed good discrimination for No-DR versus control (AUC, 0.853; 95% CI, 0.807\u20130.893), NPDR versus control (AUC, 0.785; 95% CI, 0.720\u20130.841), and No-DR\/NPDR versus control (AUC, 0.830; 95% CI, 0.788\u20130.873), but more modest discrimination between NPDR and No-DR (AUC, 0.658; 95% CI, 0.596\u20130.720).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI-derived ultra-widefield retinal vascular metrics demonstrate early, spatially heterogeneous microvascular remodeling in T2DM before clinically apparent DR. Vessel density, fractal dimension, vessel diameter, and vessel length provide complementary information, and multiparameter vascular modeling may support early detection and risk stratification. External validation and longitudinal studies are required before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1906162","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T05:38:23Z","timestamp":1784007503000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial intelligence\u2013based analysis of retinal vascular changes in the preclinical and early stages of diabetic retinopathy using ultra-widefield fundus imaging: an observational cross-sectional study"],"prefix":"10.3389","volume":"13","author":[{"given":"Tingting","family":"Sun","sequence":"first","affiliation":[{"name":"Tongren Hospital, Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingjun","family":"Min","sequence":"additional","affiliation":[{"name":"Tongren Hospital, Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caihong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tongren Hospital, Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nurbiya","family":"Abduriyim","sequence":"additional","affiliation":[{"name":"Bachu County Hospital of Traditional Chinese Medicine","place":["Kashgar, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenting","family":"Wen","sequence":"additional","affiliation":[{"name":"Tongren Hospital, Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinghua","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tongren Hospital, Shanghai Jiao Tong University School of Medicine","place":["Shanghai, China"]},{"name":"Department of Ophthalmology, Shigatse People\u2019s Hospital","place":["Shigatse, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"556","DOI":"10.2337\/dc11-1909","article-title":"Global prevalence and major risk factors of diabetic retinopathy.","volume":"35","author":"Yau","year":"2012","journal-title":"Diabetes Care"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis.","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology"},{"key":"B3","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.tem.2013.09.005","article-title":"Neurodegeneration in the diabetic eye: new insights and therapeutic perspectives.","volume":"25","author":"Sim\u00f3","year":"2014","journal-title":"Trends Endocrinol Metab"},{"key":"B4","doi-asserted-by":"publisher","first-page":"E2655","DOI":"10.1073\/pnas.1522014113","article-title":"Retinal neurodegeneration may precede microvascular changes characteristic of diabetic retinopathy in diabetes mellitus.","volume":"113","author":"Sohn","year":"2016","journal-title":"Proc Natl Acad Sci U S A"},{"key":"B5","doi-asserted-by":"publisher","first-page":"S231","DOI":"10.2337\/dc24-S012","article-title":"12. Retinopathy, neuropathy, and foot care: standards of care in diabetes-2024.","volume":"47","year":"2024","journal-title":"Diabetes Care."},{"key":"B6","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.survophthal.2008.10.003","article-title":"Retinal vascular caliber: systemic, environmental, and genetic associations.","volume":"54","author":"Sun","year":"2009","journal-title":"Surv Ophthalmol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1519768","DOI":"10.3389\/fmed.2025.1519768","article-title":"Artificial intelligence versus manual screening for the detection of diabetic retinopathy: a comparative systematic review and meta-analysis.","volume":"12","author":"Tahir","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1295850","DOI":"10.3389\/fcell.2023.1295850","article-title":"Editorial: artificial intelligence applications in chronic ocular diseases.","volume":"11","author":"Xu","year":"2023","journal-title":"Front Cell Dev Biol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"930520","DOI":"10.3389\/fphar.2022.930520","article-title":"Systematic bibliometric and visualized analysis of research hotspots and trends on the application of artificial intelligence in ophthalmic disease diagnosis.","volume":"13","author":"Zhao","year":"2022","journal-title":"Front Pharmacol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"B11","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2017.18152","article-title":"Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes.","volume":"318","author":"Ting","year":"2017","journal-title":"JAMA"},{"key":"B12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning.","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"B13","doi-asserted-by":"publisher","first-page":"100658","DOI":"10.1016\/j.xops.2024.100658","article-title":"Automated quantitative assessment of retinal vascular tortuosity in patients with sickle cell disease.","volume":"5","author":"Chen","year":"2024","journal-title":"Ophthalmol Sci"},{"key":"B14","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1016\/j.ophtha.2015.01.008","article-title":"Peripheral lesions identified on ultrawide field imaging predict increased risk of diabetic retinopathy progression over 4 years.","volume":"122","author":"Silva","year":"2015","journal-title":"Ophthalmology"},{"key":"B15","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1097\/IAE.0b013e3182278b64","article-title":"Ultra-wide-field angiography improves the detection and classification of diabetic retinopathy.","volume":"32","author":"Wessel","year":"2012","journal-title":"Retina"},{"key":"B16","doi-asserted-by":"publisher","first-page":"856","DOI":"10.1001\/jamaophthalmol.2024.2890","article-title":"Ultra-widefield and early treatment diabetic retinopathy study 7-field grading of diabetic retinopathy.","volume":"142","author":"Aiello","year":"2024","journal-title":"JAMA Ophthalmol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"793726","DOI":"10.3389\/fmed.2021.793726","article-title":"Retinal image enhancement using cycle-constraint adversarial network.","volume":"8","author":"Wan","year":"2022","journal-title":"Front Med (Lausanne)"},{"key":"B18","doi-asserted-by":"publisher","first-page":"946","DOI":"10.1001\/jamaophthalmol.2022.3131","article-title":"Association of predominantly peripheral lesions on ultra-widefield imaging and the risk of diabetic retinopathy worsening over time.","volume":"140","author":"Marcus","year":"2022","journal-title":"JAMA Ophthalmol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"e70121","DOI":"10.1111\/1753-0407.70121","article-title":"Global, regional, and national epidemiology of vision impairment due to diabetic retinopathy among working-age population, 1990-2021.","volume":"17","author":"Meng","year":"2025","journal-title":"J Diabetes"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1405","DOI":"10.3390\/biomedicines12071405","article-title":"Advances in structural and functional retinal imaging and biomarkers for early detection of diabetic retinopathy.","volume":"12","author":"Zhang","year":"2024","journal-title":"Biomedicines"},{"key":"B21","doi-asserted-by":"publisher","first-page":"e003758","DOI":"10.1136\/bmjdrc-2023-003758","article-title":"Ocular microvascular complications in diabetic retinopathy: insights from machine learning.","volume":"12","author":"Ahmed","year":"2024","journal-title":"BMJ Open Diabetes Res Care"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1415","DOI":"10.1007\/s00125-022-05727-0","article-title":"Diabetic retinopathy screening in the emerging era of artificial intelligence.","volume":"65","author":"Grauslund","year":"2022","journal-title":"Diabetologia."},{"key":"B23","doi-asserted-by":"publisher","first-page":"5410672","DOI":"10.1155\/2019\/5410672","article-title":"Analysis of retinal perfusion in children, adolescents, and young adults with type 1 diabetes using optical coherence tomography angiography.","volume":"2019","author":"Mameli","year":"2019","journal-title":"J Diabetes Res"},{"key":"B24","doi-asserted-by":"publisher","first-page":"OCT519","DOI":"10.1167\/iovs.15-18901","article-title":"Linking retinal microvasculature features with severity of diabetic retinopathy using optical coherence tomography angiography.","volume":"57","author":"Bhanushali","year":"2016","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"B25","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/s10456-024-09911-1","article-title":"Microglia in retinal angiogenesis and diabetic retinopathy.","volume":"27","author":"Hu","year":"2024","journal-title":"Angiogenesis"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e3812","DOI":"10.1002\/dmrr.3812","article-title":"Optical coherence tomography angiography for detection of microvascular changes in early diabetes: a systematic review and meta-analysis.","volume":"40","author":"Yang","year":"2024","journal-title":"Diabetes Metab Res Rev"},{"key":"B27","doi-asserted-by":"publisher","first-page":"7438","DOI":"10.1167\/iovs.15-17449","article-title":"Retinal vascular fractals correlate with early neurodegeneration in patients with type 2 diabetes mellitus.","volume":"56","author":"Frydkjaer-Olsen","year":"2015","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"B28","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s40942-025-00688-z","article-title":"Retinal vessel tortuosity and fractal dimension in diabetic retinopathy.","volume":"11","author":"Fathimah","year":"2025","journal-title":"Int J Retina Vitreous"},{"key":"B29","doi-asserted-by":"publisher","first-page":"106","DOI":"10.2337\/dc08-1233","article-title":"Quantitative assessment of early diabetic retinopathy using fractal analysis.","volume":"32","author":"Cheung","year":"2009","journal-title":"Diabetes Care"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.1007\/s00125-017-4333-0","article-title":"Retinal vascular geometry and 6 year incidence and progression of diabetic retinopathy.","volume":"60","author":"Cheung","year":"2017","journal-title":"Diabetologia"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1747","DOI":"10.1136\/bjophthalmol-2018-313582","article-title":"Early retinal neurovascular impairment in patients with diabetes without clinically detectable retinopathy.","volume":"103","author":"Zeng","year":"2019","journal-title":"Br J Ophthalmol"},{"key":"B32","doi-asserted-by":"publisher","first-page":"2708","DOI":"10.2337\/dc07-0732","article-title":"Retinal vascular changes in pre-diabetes and prehypertension: new findings and their research and clinical implications.","volume":"30","author":"Nguyen","year":"2007","journal-title":"Diabetes Care"},{"key":"B33","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.ajo.2014.03.009","article-title":"Patterns of peripheral retinal and central macula ischemia in diabetic retinopathy as evaluated by ultra-widefield fluorescein angiography.","volume":"158","author":"Sim","year":"2014","journal-title":"Am J Ophthalmol"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1097\/IAE.0000000000003479","article-title":"Assessment of fluorescein angiography nonperfusion in eyes with diabetic retinopathy using ultrawide field retinal imaging.","volume":"42","author":"Silva","year":"2022","journal-title":"Retina"},{"key":"B35","doi-asserted-by":"publisher","first-page":"2946","DOI":"10.1038\/s41433-023-02445-8","article-title":"Comparison of diabetic retinopathy severity grading on ETDRS 7-field versus ultrawide-field assessment.","volume":"37","author":"Attiku","year":"2023","journal-title":"Eye (Lond)"},{"key":"B36","doi-asserted-by":"publisher","first-page":"17449","DOI":"10.1038\/s41598-022-21319-9","article-title":"Comparison of two ultra-widefield color-fundus imaging devices for visualization of retinal periphery and microvascular lesions in patients with early diabetic retinopathy.","volume":"12","author":"Stino","year":"2022","journal-title":"Sci Rep"},{"key":"B37","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1016\/j.oret.2020.09.003","article-title":"Retinal vascular caliber association with nonperfusion and diabetic retinopathy severity depends on vascular caliber measurement location.","volume":"5","author":"Ashraf","year":"2021","journal-title":"Ophthalmol Retina."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1016\/j.oret.2020.05.009","article-title":"Extended-zone retinal vascular caliber and risk of diabetic retinopathy in adolescents with type 1 diabetes.","volume":"4","author":"Velayutham","year":"2020","journal-title":"Ophthalmol Retina"},{"key":"B39","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s11892-009-0043-4","article-title":"Retinal vascular changes and diabetic retinopathy.","volume":"9","author":"Nguyen","year":"2009","journal-title":"Curr Diab Rep"},{"key":"B40","doi-asserted-by":"publisher","first-page":"e001596","DOI":"10.1136\/bmjdrc-2020-001596","article-title":"Artificial intelligence-enabled screening for diabetic retinopathy: a real-world, multicenter and prospective study.","volume":"8","author":"Zhang","year":"2020","journal-title":"BMJ Open Diabetes Res Care"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1906162\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T05:38:24Z","timestamp":1784007504000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1906162\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":40,"alternative-id":["10.3389\/fmed.2026.1906162"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1906162","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"article-number":"1906162"}}