{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T03:57:26Z","timestamp":1779940646133,"version":"3.53.1"},"reference-count":26,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH CORE Grant","award":["P30 EY08098"],"award-info":[{"award-number":["P30 EY08098"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: To evaluate the challenges and limitations of a deep learning model for automated choroidal boundary detection in eyes with geographic atrophy (GA) using spectral-domain OCT (SD-OCT), and to assess the workflow efficiency of an AI-assisted manual verification approach. Methods: In this retrospective study, total 5723 scans (Heidelberg Spectralis) with GA were analyzed. A previously validated tool (NMI ChoroidAI) was used to segment the choroidal inner (CIB) and outer (COB) boundaries. We compared the \u201cAI-assisted\u201d workflow (automated segmentation followed by manual verification) against \u201cmanual segmentation only\u201d in terms of accuracy and time consumption. Slice-wise boundary errors were graded as 0 (accurate), 1 (\u226433% deviation), 2 (33\u201366% deviation), or 3 (&gt;66% deviation). Outcomes included error rates and weighted F1 score (and precision where applicable). Total time for manual-only segmentation versus AI-assisted verification was recorded. -Interreader variability was assessed between the two readers using intraclass correlation coefficient. Results: For CIB, only 5.2% of B-scans showed any deviation (strictly accurate in 94.8%), with weighted F1 score 0.97 and precision 1.00. COB was more error-prone: 19.0% of B-scans showed deviation; however, when minor deviations were considered acceptable, COB acceptability increased to 94.2% (i.e., 5.8% remained &gt;33% deviated). Only 13.2% of B-scans required minor manual correction. For a 97-scan volume, processing time decreased from an average of 7 h (manual only) to 45 min (AI + human verification), an approximate 90% reduction in manual effort. Inter-reader agreement was high (ICC 0.923 for CIB and 0.938 for COB). Conclusions: Although the deep learning model exhibits limitations in COB detection due to artifacts, it serves as a valuable assistive tool. Our model substantially reduces human effort, but mandatory human verification is required to correct boundary errors caused by hyper-transmission before use in clinical trials.<\/jats:p>","DOI":"10.3390\/diagnostics16050737","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:22:21Z","timestamp":1772551341000},"page":"737","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Learning\u2013Based Choroidal Boundary Detection in Geographic Atrophy Using Spectral-Domain Optical Coherence Tomography"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8454-458X","authenticated-orcid":false,"given":"Elham","family":"Rahmanipour","sequence":"first","affiliation":[{"name":"Immunology Research Center, Mashhad University of Medical Sciences, Mashhad 91779 48564, Iran"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasiq","family":"Hasan","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adarsh","family":"Gadari","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"},{"name":"NetraMind Innovations Inc., Pittsburgh, PA 15238, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Whitley","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soumya","family":"Sharma","sequence":"additional","affiliation":[{"name":"College of Medicine, The University of Toledo, Toledo, OH 43606, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreyaa","family":"Lall","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristian de los","family":"Santos","sequence":"additional","affiliation":[{"name":"Fundacion Retina, Buenos Aires B1669, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3802-3219","authenticated-orcid":false,"given":"Elham","family":"Sadeghi","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandeep Chandra","family":"Bollepalli","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"},{"name":"NetraMind Innovations Inc., Pittsburgh, PA 15238, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiran Kumar","family":"Vupparaboina","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"},{"name":"NetraMind Innovations Inc., Pittsburgh, PA 15238, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario J.","family":"Savaria","sequence":"additional","affiliation":[{"name":"Fundacion Retina, Buenos Aires B1669, Argentina"},{"name":"Buenos Aires Macula Clinical Research, Buenos Aires B1669, Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1772-3558","authenticated-orcid":false,"given":"Jay","family":"Chhablani","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, University of Pittsburgh, Pittsburgh, PA 15261, USA"},{"name":"NetraMind Innovations Inc., Pittsburgh, PA 15238, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e106","DOI":"10.1016\/S2214-109X(13)70145-1","article-title":"Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: A systematic review and meta-analysis","volume":"2","author":"Wong","year":"2014","journal-title":"Lancet Glob. Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.survophthal.2024.10.004","article-title":"Choroidal biomarkers in age-related macular degeneration","volume":"70","author":"Sadeghi","year":"2025","journal-title":"Surv. Ophthalmol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.oret.2017.08.016","article-title":"Pachychoroid Geographic Atrophy: Clinical and Genetic Characteristics","volume":"2","author":"Takahashi","year":"2018","journal-title":"Ophthalmol. Retina"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1097\/IAE.0000000000003305","article-title":"Choroidal vascularity index is associated with geographic atrophy progression","volume":"42","author":"Sacconi","year":"2022","journal-title":"Retina"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2578","DOI":"10.1167\/iovs.16-19083","article-title":"Choroidal Caverns: A Novel Optical Coherence Tomography Finding in Geographic Atrophy","volume":"57","author":"Querques","year":"2016","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"6210","DOI":"10.1038\/s41598-024-56376-9","article-title":"Three-dimensional choroidal contour mapping in healthy population","volume":"14","author":"Arora","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1038\/s41598-025-85189-7","article-title":"Assessment of choroidal vessels in healthy eyes using 3-dimensional vascular maps and a semi-automated deep learning approach","volume":"15","author":"Valsecchi","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Al-Khersan, H., Sodhi, S.K., Cao, J.A., Saju, S.M., Pattathil, N., Zhou, A.W., Choudhry, N., Russakoff, D.B., Oakley, J.D., and Boyer, D. (2025). Deep Learning-Based Segmentation of Geographic Atrophy: A Multi-Center, Multi-Device Validation in a Real-World Clinical Cohort. Diagnostics, 15.","DOI":"10.3390\/diagnostics15202580"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e665","DOI":"10.1016\/S2589-7500(21)00134-5","article-title":"Clinically relevant deep learning for detection and quantification of geographic atrophy from optical coherence tomography: A model development and external validation study","volume":"3","author":"Zhang","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"42112","DOI":"10.1038\/srep42112","article-title":"Open-source algorithm for automatic choroid segmentation of OCT volume reconstructions","volume":"7","author":"Mazzaferri","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1364\/BOE.7.000581","article-title":"Automated geographic atrophy segmentation for SD-OCT images using region-based CV model via local similarity factor","volume":"7","author":"Niu","year":"2016","journal-title":"Biomed. Opt. Express"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1016\/j.ophtha.2017.08.038","article-title":"The Progression of Geographic Atrophy Secondary to Age-Related Macular Degeneration","volume":"125","author":"Fleckenstein","year":"2018","journal-title":"Ophthalmology"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"21893","DOI":"10.1038\/s41598-021-01227-0","article-title":"Fully-automated atrophy segmentation in dry age-related macular degeneration in optical coherence tomography","volume":"11","author":"Derradji","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1016\/j.ajo.2008.05.050","article-title":"The epidemiology of progression of pure geographic atrophy: The Beaver Dam Eye Study","volume":"146","author":"Klein","year":"2008","journal-title":"Am. J. Ophthalmol."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Ibrahim, M.N., Bollepalli, S.C., Selvam, A., Sant, V., Harihar, S., Sahel, J.A., Chhablani, J., and Vupparaboina, K.K. (2023, January 15\u201318). Accurate Detection of 3D Choroidal Vasculature Using Swept-Source OCT Volumetric Scans Based on Phansalkar Thresholding. Proceedings of the 2023 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), Pittsburgh, PA, USA.","DOI":"10.1109\/BHI58575.2023.10313450"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1605","DOI":"10.1364\/BOE.510464","article-title":"Self-attention CNN for retinal layer segmentation in OCT","volume":"15","author":"Cao","year":"2024","journal-title":"Biomed. Opt. Express"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1806","DOI":"10.1097\/IAE.0000000000001283","article-title":"Clinical endpoints for the study of geographic atrophy secondary to age-related macular degeneration","volume":"36","author":"Sadda","year":"2016","journal-title":"Retina"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3421","DOI":"10.1007\/s00417-024-06497-8","article-title":"Structural OCT and OCT angiography biomarkers associated with the development and progression of geographic atrophy in AMD","volume":"262","author":"Vallino","year":"2024","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Enzendorfer, M.L., Tratnig-Frankl, M., Eidenberger, A., Schrittwieser, J., Kuchernig, L., and Schmidt-Erfurth, U. (2025). Rethinking Clinical Trials in Age-Related Macular Degeneration: How AI-Based OCT Analysis Can Support Successful Outcomes. Pharmaceuticals, 18.","DOI":"10.3390\/ph18030284"},{"key":"ref_20","first-page":"536","article-title":"Deep-learning automated quantification of longitudinal OCT scans demonstrates reduced RPE loss rate, preservation of intact macular area and predictive value of isolated photoreceptor degeneration in geographic atrophy patients receiving C3 inhibition treatment","volume":"108","author":"Fu","year":"2024","journal-title":"Br. J. Ophthalmol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s00417-025-06997-1","article-title":"Artificial intelligence in ophthalmology clinical trials: A narrative review","volume":"264","author":"Rahmanipour","year":"2025","journal-title":"Graefe\u2019s Arch. Clin. Exp. Ophthalmol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"394","DOI":"10.1016\/j.ophtha.2019.09.035","article-title":"Incomplete Retinal Pigment Epithelial and Outer Retinal Atrophy in Age-Related Macular Degeneration: Classification of Atrophy Meeting Report 4","volume":"127","author":"Guymer","year":"2020","journal-title":"Ophthalmology"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"100998","DOI":"10.1016\/j.measen.2023.100998","article-title":"Residual learning for segmentation of the medical images in healthcare","volume":"32","author":"Sahoo","year":"2024","journal-title":"Meas. Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"9262","DOI":"10.1038\/s41598-025-94380-9","article-title":"ARCUNet: Enhancing skin lesion segmentation with residual convolutions and attention mechanisms for improved accuracy and robustness","volume":"15","author":"Soni","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_26","unstructured":"Xie, Y., Yang, B., Guan, Q., Zhang, J., Wu, Q., and Xia, Y. (2023). Attention mechanisms in medical image segmentation: A survey. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/5\/737\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T15:47:02Z","timestamp":1772552822000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/5\/737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":26,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["diagnostics16050737"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16050737","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]}}}