{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T01:13:21Z","timestamp":1784855601160,"version":"3.55.0"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T00:00:00Z","timestamp":1742342400000},"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><jats:title>Background<\/jats:title><jats:p>Macular edema (ME) is an ophthalmic disease that poses a serious threat to human vision. Anti-vascular endothelial growth factor (anti-VEGF) therapy has become the first-line treatment for ME due to its safety and high efficacy. However, there are still cases of refractory macular edema and non-responding patients. Therefore, it is crucial to develop automated and efficient methods for predicting therapeutic outcomes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We have developed a predictive model for the surgical efficacy in ME patients based on deep learning and optical coherence tomography (OCT) imaging, aimed at predicting the treatment outcomes at different time points. This model innovatively introduces group convolution and multiple convolutional kernels to handle multidimensional features based on traditional attention mechanisms for visual recognition tasks, while utilizing spatial pyramid pooling (SPP) to combine and extract the most useful features. Additionally, the model uses ResNet50 as a pre-trained model, integrating multiple knowledge through model fusion.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our proposed model demonstrated the best performance across various experiments. In the ablation study, the model achieved an F1 score of 0.9937, an MCC of 0.7653, an AUC of 0.9928, and an ACC of 0.9877 in the test conducted on the first day after surgery. In comparison experiments, the ACC of our model was 0.9930 and 0.9915 in the first and the third months post-surgery, respectively, with AUC values of 0.9998 and 0.9996, significantly outperforming other models. In conclusion, our model consistently exhibited superior performance in predicting outcomes at various time points, validating its excellence in processing OCT images and predicting postoperative efficacy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Through precise prediction of the response to anti-VEGF therapy in ME patients, deep learning technology provides a revolutionary tool for the treatment of ophthalmic diseases, significantly enhancing treatment outcomes and improving patients\u2019 quality of life.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1505530","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T07:07:41Z","timestamp":1742368061000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Construction of a predictive model for the efficacy of anti-VEGF therapy in macular edema patients based on OCT imaging: a retrospective study"],"prefix":"10.3389","volume":"12","author":[{"given":"Tingting","family":"Song","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyang","family":"Zang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chui","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xifang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huihui","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"982","DOI":"10.3390\/medicina59050982","article-title":"Combined treatment of persistent diabetic macular edema with Aflibercept and triamcinolone Acetonide in Pseudophakic eyes","volume":"59","author":"Petrovic","year":"2023","journal-title":"Medicina (Kaunas)"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.survophthal.2022.11.008","article-title":"Persistent diabetic macular edema: definition, incidence, biomarkers, and treatment methods","volume":"68","author":"Sorour","year":"2023","journal-title":"Surv Ophthalmol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"9424","DOI":"10.3390\/ijms23169424","article-title":"Aflibercept versus Faricimab in the treatment of Neovascular age-related macular degeneration and diabetic macular edema: a review","volume":"23","author":"Liberski","year":"2022","journal-title":"Int J Mol Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1016\/j.ophtha.2024.01.029","article-title":"Efficacy and safety of Faricimab for macular edema due to retinal vein occlusion: 24-week results from the BALATON and COMINO trials","volume":"131","author":"Tadayoni","year":"2024","journal-title":"Ophthalmology"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.3390\/ph16081140","article-title":"Intravitreal anti-vascular endothelial growth factor therapies for retinal disorders","volume":"16","author":"Hang","year":"2023","journal-title":"Pharmaceuticals (Basel)"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"2114","DOI":"10.3390\/medicina59122114","article-title":"Optical coherence tomography (OCT): a brief look at the uses and technological evolution of ophthalmology","volume":"59","author":"Zeppieri","year":"2023","journal-title":"Medicina (Kaunas)"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"101220","DOI":"10.1016\/j.preteyeres.2023.101220","article-title":"Optical coherence tomography in the management of diabetic macular oedema","volume":"98","author":"Szeto","year":"2024","journal-title":"Prog Retin Eye Res"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1136\/bjophthalmol-2020-315933","article-title":"Visual acuity outcomes and anti-VEGF therapy intensity in diabetic macular oedema: a real-world analysis of 28 658 patient eyes","volume":"105","author":"Ciulla","year":"2021","journal-title":"Br J Ophthalmol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.survophthal.2022.08.004","article-title":"Artificial intelligence in screening, diagnosis, and classification of diabetic macular edema: a systematic review","volume":"68","author":"Shahriari","year":"2023","journal-title":"Surv Ophthalmol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"312","DOI":"10.3390\/diagnostics12020312","article-title":"Deep learning prediction of response to anti-VEGF among diabetic macular edema patients: treatment response analyzer system (TRAS)","volume":"12","author":"Alryalat","year":"2022","journal-title":"Diagnostics (Basel)"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"914964","DOI":"10.3389\/fbioe.2022.914964","article-title":"Predicting OCT images of short-term response to anti-VEGF treatment for retinal vein occlusion using generative adversarial network","volume":"10","author":"Xu","year":"2022","journal-title":"Front Bioeng Biotechnol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1111\/ceo.14258","article-title":"Deep learning in optical coherence tomography: where are the gaps?","volume":"51","author":"Li","year":"2023","journal-title":"Clin Experiment Ophthalmol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"106980","DOI":"10.1016\/j.neunet.2024.106980","article-title":"Lie group convolution neural networks with scale-rotation equivariance","volume":"183","author":"Qiao","year":"2024","journal-title":"Neural Netw"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/tvst.13.7.4","article-title":"Prediction of long-term treatment outcomes for diabetic macular edema using a generative adversarial network","volume":"13","author":"Baek","year":"2024","journal-title":"Transl Vis Sci Technol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s40662-024-00389-y","article-title":"Novel artificial intelligence algorithms for diabetic retinopathy and diabetic macular edema","volume":"11","author":"Yao","year":"2024","journal-title":"Eye Vision"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11892-019-1188-4","article-title":"Treatment of diabetic macular edema","volume":"19","author":"Kim","year":"2019","journal-title":"Curr Diab Rep"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1097\/IAE.0000000000000277","article-title":"Progressive retinal nonperfusion in ischemic central retinal vein occlusion","volume":"35","author":"Wykoff","year":"2015","journal-title":"Retina"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e34170","DOI":"10.1097\/MD.0000000000034170","article-title":"Efficacy of ranibizumab combined with photocoagulation for diabetic retinopathy: a meta-analysis study","volume":"102","author":"Yin","year":"2023","journal-title":"Medicine (Baltimore)"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s40123-023-00843-5","article-title":"Clinical trials and future outlooks of the port delivery system with Ranibizumab: a narrative review","volume":"13","author":"Lowater","year":"2024","journal-title":"Ophthalmol Ther"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/s12886-022-02303-3","article-title":"The efficacy and safety of intravitreal injection of Ranibizumab as pre-treatment for vitrectomy in proliferative diabetic retinopathy with vitreous hemorrhage","volume":"22","author":"Li","year":"2022","journal-title":"BMC Ophthalmol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1080\/14712598.2022.2100694","article-title":"Efficacy and safety of intravitreal anti-VEGF therapy in diabetic retinopathy: what we have learned and what should we learn further?","volume":"22","author":"Uludag","year":"2022","journal-title":"Expert Opin Biol Ther"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1280776","DOI":"10.3389\/fmed.2023.1280776","article-title":"The progress of assessment methods and treatments of neovascular glaucoma secondary to central retinal vein occlusion","volume":"10","author":"Qu","year":"2024","journal-title":"Front Med (Lausanne)"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1505530\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T07:07:42Z","timestamp":1742368062000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1505530\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,19]]},"references-count":23,"alternative-id":["10.3389\/fmed.2025.1505530"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1505530","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,19]]},"article-number":"1505530"}}