{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T05:05:47Z","timestamp":1775538347189,"version":"3.50.1"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"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>Purpose<\/jats:title>\n                    <jats:p>Fundus fluorescein angiography (FFA) is essential for diagnosing and managing retinal vascular diseases, yet its evaluation is time-consuming and subject to inter-observer variability. We aim to develop a deep-learning-based framework for multi-lesion segmentation in FFA images and to evaluate its primary performance on standard 55 \u00b0 images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A dataset of 428 standard 55 \u00b0 FFA images and 53 ultra-wide-field (UWF) FFA images was annotated for non-perfusion areas (NPA), microaneurysms (MA), neovascularization (NV) and laser spots. A residual U-Net framework was trained using a data-pooling strategy. The primary analysis was performed on the 55 \u00b0 test set, whereas the UWF subset was analyzed only as a preliminary exploratory observation because of its limited sample size. Performance was assessed using Dice score, Intersection over Union (IoU) and recall.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On 55 \u00b0 FFA images, the model achieved Dice scores of 0.65 \u00b1 0.24 for NPA, 0.70 \u00b1 0.13 for MA, 0.73 \u00b1 0.23 for NV, and 0.70 \u00b1 0.17 for laser spots. In an exploratory analysis of UWF images, overlap-based performance was lower for NPA (0.48 \u00b1 0.21,\n                      <jats:italic>p<\/jats:italic>\n                      = 0.02) and MA (0.58 \u00b1 0.19,\n                      <jats:italic>p<\/jats:italic>\n                      = 0.01), whereas laser spot segmentation was similar. NV segmentation in CNV achieved a Dice score of 0.90 \u00b1 0.09. NPA segmentation was better in RVO than in DR, whereas MA segmentation was better in DR than in RVO. Moreover, NV segmentation was significantly stronger in the venous phase (0.77 \u00b1 0.17) and late phase (0.75 \u00b1 0.24) than in the arteriovenous phase (0.50 \u00b1 0.32, both\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.05). Exploratory UWF analysis showed lower overlap-based performance, highlighting the likely impact of domain shift and the need for larger UWF-specific datasets.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study has established a highly consistent and reproducible framework for multi-lesion segmentation in FFA images. The model may help standardize lesion quantification, reduce manual grading burden, and support future development of larger multi-center FFA datasets.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1762735","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:22:29Z","timestamp":1775535749000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated interpretation of fundus fluorescein angiography with multi-retinal vascular lesion segmentation"],"prefix":"10.3389","volume":"13","author":[{"given":"Ziwei","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Research Center for SHARP Vision, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoujin","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen Technology University","place":["Shenzhen, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Song","sequence":"additional","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Research Center for SHARP Vision, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Research Center for SHARP Vision, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Foshan Second People's Hospital","place":["Foshan, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwen","family":"Shang","sequence":"additional","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingfeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Ophthalmology, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Zhongshan Ophthalmic Center, Guangdong Provincial Clinical Research Center for Ocular Diseases, Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danli","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Research Center for SHARP Vision, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingguang","family":"He","sequence":"additional","affiliation":[{"name":"School of Optometry, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Research Center for SHARP Vision, The Hong Kong Polytechnic University","place":["Hong Kong, Hong Kong SAR, China"]},{"name":"Center for Eye and Vision Research","place":["Hong Kong, Hong Kong SAR, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"349","DOI":"10.3109\/09286586.2015.1066394","article-title":"A simple method for estimating the economic cost of productivity loss due to blindness and moderate to severe visual impairment","volume":"22","author":"Eckert","year":"2015","journal-title":"Ophthalmic Epidemiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"107840","DOI":"10.1016\/j.diabres.2019.107840","article-title":"IDF diabetes atlas: a review of studies utilising retinal photography on the global prevalence of diabetes related retinopathy between 2015 and 2018","volume":"157","author":"Thomas","year":"2019","journal-title":"Diabetes Res Clin Pract."},{"key":"B3","doi-asserted-by":"publisher","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":"B4","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1001\/jamaophthalmol.2019.0440","article-title":"Retinal nonperfusion characteristics on ultra-widefield angiography in eyes with severe nonproliferative diabetic retinopathy and proliferative diabetic retinopathy","volume":"137","author":"Nicholson","year":"2019","journal-title":"JAMA Ophthalmol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1167\/iovs.13-13122","article-title":"Classification of human retinal microaneurysms using adaptive optics scanning light ophthalmoscope fluorescein angiography","volume":"55","author":"Dubow","year":"2014","journal-title":"Invest Ophthalmol Vis Sci."},{"key":"B6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.patcog.2012.07.002","article-title":"A Identification and classification of microaneurysms for early detection of diabetic retinopathy","volume":"46","author":"Akram","year":"2013","journal-title":"Pattern Recognit"},{"key":"B7","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1136\/bjophthalmol-2018-311887","article-title":"Microaneurysm turnover is a predictor of diabetic retinopathy progression","volume":"103","author":"Pappuru","year":"2019","journal-title":"Br J Ophthalmol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"9632","DOI":"10.1109\/ACCESS.2018.2808160","article-title":"Automatic analysis of microaneurysms turnover to diagnose the progression of diabetic retinopathy","volume":"6","author":"Xu","year":"2018","journal-title":"IEEE Access."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1097\/IAE.0000000000001703","article-title":"Clinical findings of eyes with macular edema associated with branch retinal vein occlusion refractory to ranibizumab","volume":"38","author":"Hasegawa","year":"2018","journal-title":"Retina."},{"key":"B10","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s10384-016-0425-5","article-title":"Effect of leaking capillaries and microaneurysms in the perifoveal capillary network on resolution of macular edema by anti-vascular endothelial growth factor treatment","volume":"60","author":"lesato","year":"2016","journal-title":"Jpn J Ophthalmol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.2147\/OPTH.S258958","article-title":"Morphologic classifications and locations of microaneurysms and clinical relevance in branch retinal vein occlusion","volume":"14","author":"Esaki","year":"2020","journal-title":"Clin Ophthalmol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"3948","DOI":"10.3390\/jcm12123948","article-title":"Quantification of microvascular lesions in the central retinal field: could it predict the severity of diabetic retinopathy?","volume":"12","author":"Fern\u00e1ndez-Carneado","year":"2023","journal-title":"J Clin Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1136\/bjophthalmol-2011-301378","article-title":"The number of ophthalmologists in practice and training worldwide: a growing gap despite more than 200 000 practitioners","volume":"96","author":"Resnikoff","year":"2012","journal-title":"Br J Ophthalmol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1016\/S0161-6420(95)30848-2","article-title":"The central vein occlusion study group N report","volume":"102","year":"1995","journal-title":"Ophthalmol."},{"key":"B15","doi-asserted-by":"publisher","first-page":"101197","DOI":"10.1016\/j.xcrm.2023.101197","article-title":"An artificial intelligence system for the whole process from diagnosis to treatment suggestion of ischemic retinal diseases Cell Rep Med","volume":"4","author":"Zhao","year":"2023"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1663","DOI":"10.1007\/s00417-021-05503-7","article-title":"End-to-end diabetic retinopathy grading based on fundus fluorescein angiography images using deep learning","volume":"260","author":"Gao","year":"2022","journal-title":"Graefes Arch Clin Exp Ophthalmol."},{"key":"B17","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1007\/s00417-019-04575-w","article-title":"Multi-label classification of retinal lesions in diabetic retinopathy for automatic analysis of fundus fluorescein angiography based on deep learning","volume":"258","author":"Pan","year":"2020","journal-title":"Graefes Arch Clin Exp Ophthalmol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2537","DOI":"10.3390\/jcm9082537","article-title":"Deep learning-based segmentation and quantification of retinal capillary non-perfusion on ultra-wide-field retinal fluorescein angiography","volume":"9","author":"Nunez do Rio","year":"2020","journal-title":"J Clin Med."},{"key":"B19","doi-asserted-by":"publisher","first-page":"15138","DOI":"10.1038\/s41598-020-71622-6","article-title":"Automatic detection of non-perfusion areas in diabetic macular edema from fundus fluorescein angiography for decision making using deep learning","volume":"10","author":"Jin","year":"2020","journal-title":"Sci Rep."},{"key":"B20","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1002\/mp.14640","article-title":"Automated segmentation of retinal nonperfusion area in fluorescein angiography in retinal vein occlusion using convolutional neural networks","volume":"48","author":"Tang","year":"2021","journal-title":"Med Phys."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2401","DOI":"10.1007\/s00417-021-05151-x","article-title":"Automatic detection of leakage point in central serous chorioretinopathy of fundus fluorescein angiography based on time sequence deep learning","volume":"259","author":"Chen","year":"2021","journal-title":"Graefes Arch Clin Exp Ophthalmol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"101060","DOI":"10.1016\/j.imu.2022.101060","article-title":"Automatic segmentation of non-perfusion area from fluorescein angiography using deep learning with uncertainty estimation","volume":"32","author":"Masayoshi","year":"2022","journal-title":"Inform Med."},{"key":"B23","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1109\/TMI.2022.3215580","article-title":"Semi-supervised dual stream segmentation network for fundus lesion segmentation","volume":"42","author":"Xiang","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1136\/bjo-2022-321063","article-title":"Automated segmentation of ultra-widefield fluorescein angiography of diabetic retinopathy using deep learning","volume":"107","author":"Lee","year":"2023","journal-title":"Br J Ophthalmol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1038\/s41433-022-02156-6","article-title":"Segmentation of macular neovascularization and leakage in fluorescein angiography images in neovascular age-related macular degeneration using deep learning","volume":"37","author":"Holomcik","year":"2023","journal-title":"Eye."},{"key":"B26","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5\u20139, proceedings, part III","author":"Ronneberger","year":"2015"},{"key":"B27","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14","author":"He","year":"2016"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.1097\/IAE.0000000000002126","article-title":"USE OF THE ISCHEMIC INDEX ON WIDEFIELD FLUORESCEIN ANGIOGRAPHY TO CHARACTERIZE A CENTRAL RETINAL VEIN OCCLUSION AS ISCHEMIC OR NONISCHEMIC","volume":"39","author":"Thomas","year":"2019","journal-title":"Retina."},{"key":"B29","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1016\/j.ajo.2017.07.015","article-title":"Retinal nonperfusion in the posterior pole is associated with increased risk of neovascularization in central retinal vein occlusion","volume":"182","author":"Nicholson","year":"2017","journal-title":"Am J Ophthalmol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1762735\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T04:22:30Z","timestamp":1775535750000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1762735\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,7]]},"references-count":29,"alternative-id":["10.3389\/fmed.2026.1762735"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1762735","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,7]]},"article-number":"1762735"}}