{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T17:18:09Z","timestamp":1793121489241,"version":"4.5.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T00:00:00Z","timestamp":1731456000000},"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>Pathologic myopia (PM) associated with myopic maculopathy (MM) is a significant cause of visual impairment, especially in East Asia, where its prevalence has surged. Early detection and accurate classification of myopia-related fundus lesions are critical for managing PM. Traditional clinical analysis of fundus images is time-consuming and dependent on specialist expertise, driving the need for automated, accurate diagnostic tools.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study developed a deep learning-based system for classifying five types of MM using color fundus photographs. Five architectures\u2014ResNet50, EfficientNet-B0, Vision Transformer (ViT), Contrastive Language-Image Pre-Training (CLIP), and RETFound\u2014were utilized. An ensemble learning approach with weighted voting was employed to enhance model performance. The models were trained on a dataset of 2,159 annotated images from Shenzhen Eye Hospital, with performance evaluated using accuracy, sensitivity, specificity, F1-Score, Cohen\u2019s Kappa, and area under the receiver operating characteristic curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The ensemble model achieved superior performance across all metrics, with an accuracy of 95.4% (95% CI: 93.0\u201397.0%), sensitivity of 95.4% (95% CI: 86.8\u201397.5%), specificity of 98.9% (95% CI: 97.1\u201399.5%), F1-Score of 95.3% (95% CI: 93.2\u201397.2%), Kappa value of 0.976 (95% CI: 0.957\u20130.989), and AUC of 0.995 (95% CI: 0.992\u20130.998). The voting ensemble method demonstrated robustness and high generalization ability in classifying complex lesions, outperforming individual models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The ensemble deep learning system significantly enhances the accuracy and reliability of MM classification. This system holds potential for assisting ophthalmologists in early detection and precise diagnosis, thereby improving patient outcomes. Future work could focus on expanding the dataset, incorporating image quality assessment, and optimizing the ensemble algorithm for better efficiency and broader applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2024.1492808","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T06:34:24Z","timestamp":1731479664000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Effective automatic classification methods via deep learning for myopic maculopathy"],"prefix":"10.3389","volume":"11","author":[{"given":"Zheming","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alfira","family":"Mijit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangting","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yantao","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,11,13]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1038\/519276a","article-title":"The myopia boom","volume":"519","author":"Dolgin","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1159\/000339893","article-title":"Myopic maculopathy: a review","volume":"228","author":"Silva","year":"2012","journal-title":"Ophthalmologica"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1136\/bjophthalmol-2015-307724","article-title":"Global variations and time trends in the prevalence of childhood myopia, a systematic review and quantitative meta-analysis: implications for aetiology and early prevention","volume":"100","author":"Rudnicka","year":"2016","journal-title":"Br J Ophthalmol"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1016\/j.ajo.2015.01.022","article-title":"International photographic classification and grading system for myopic maculopathy","volume":"159","author":"Ohno-Matsui","year":"2015","journal-title":"Am J Ophthalmol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1016\/j.ophtha.2009.11.003","article-title":"Long-term pattern of progression of myopic maculopathy: a natural history study","volume":"117","author":"Hayashi","year":"2010","journal-title":"Ophthalmology"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1038\/s41572-020-00231-4","article-title":"Myopia","volume":"6","author":"Baird","year":"2020","journal-title":"Nat Rev Dis Prim"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1136\/bjophthalmol-2019-314336","article-title":"Estimated number of ophthalmologists worldwide (International Council of Ophthalmology update): will we meet the needs?","volume":"104","author":"Resnikoff","year":"2020","journal-title":"Br J Ophthalmol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","article-title":"Recent advances and clinical applications of deep learning in medical image analysis","volume":"79","author":"Chen","year":"2022","journal-title":"Med Image Anal"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TTS.2023.3234203","article-title":"Challenges of deep learning in medical image analysis\u2014improving explainability and trust","volume":"4","author":"Dhar","year":"2023","journal-title":"IEEE Trans Technol Soc"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41746-024-01174-w","article-title":"Deep learning for multi-type infectious keratitis diagnosis: a nationwide, cross-sectional, multicenter study","volume":"7","author":"Li","year":"2024","journal-title":"NPJ Digit Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1136\/bjophthalmol-2021-320926","article-title":"Pathologic myopia: advances in imaging and the potential role of artificial intelligence","volume":"107","author":"Li","year":"2023","journal-title":"Br J Ophthalmol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1038\/s41433-023-02680-z","article-title":"Performance of artificial intelligence for the detection of pathological myopia from colour fundus images: a systematic review and meta-analysis","volume":"38","author":"Prashar","year":"2024","journal-title":"Eye"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/s11517-023-02952-6","article-title":"Deep learning prediction of steep and flat corneal curvature using fundus photography in post-COVID telemedicine era","volume":"62","author":"Choi","year":"2024","journal-title":"Med Biol Eng Comput"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"4828","DOI":"10.1038\/s41467-021-25138-w","article-title":"Automatic detection of 39 fundus diseases and conditions in retinal photographs using deep neural networks","volume":"12","author":"Cen","year":"2021","journal-title":"Nat Commun"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1130609","DOI":"10.3389\/fnins.2023.1130609","article-title":"MyopiaDETR: end-to-end pathological myopia detection based on transformer using 2D fundus images","volume":"17","author":"Li","year":"2023","journal-title":"Front Neurosci"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1038\/s41746-023-00811-0","article-title":"Self-supervised learning for medical image classification: a systematic review and implementation guidelines","volume":"6","author":"Huang","year":"2023","journal-title":"NPJ Digit. Med."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s13198-021-01552-7","article-title":"Effective ensemble learning approach for large-scale medical data analytics","volume":"15","author":"Namamula","year":"2022","journal-title":"Int J Syst Assur Eng Manag"},{"key":"ref19","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"ref20","first-page":"6105","article-title":"International Conference on Machine Learning","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","author":"Tan","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"6000","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"ref22","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","article-title":"A survey on ensemble learning","volume":"14","author":"Dong","year":"2020","journal-title":"Front Comput Sci"},{"key":"ref24","volume-title":"An image is worth 16x16 words: transformers for image recognition at scaleICLR 2021 (International Conference on Learning Representations)","author":"Dosovitskiy","year":"2021"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"Imagenet: a large-scale hierarchical image database","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"8026","DOI":"10.48550\/arXiv.1912.01703","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Proces Syst"},{"key":"ref27","volume-title":"Decoupled weight decay regularizationconference is ICLR 2017","author":"Loshchilov","year":"2019"},{"key":"ref28","volume-title":"Asymptotics of the empirical bootstrap method beyond asymptotic normality","author":"Austern","year":"2020"},{"key":"ref29","first-page":"618","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Selvaraju","year":"2017"},{"key":"ref30","first-page":"839","article-title":"Rad-CAM++: improved visual explanations for deep convolutional networks","author":"Chattopadhyay","year":"2018"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1007\/978-3-030-32239-7_6","article-title":"Evaluation of retinal image quality assessment networks in different color-spaces","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2019","author":"Fu","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"101654","DOI":"10.1016\/j.media.2020.101654","article-title":"Domain-invariant interpretable fundus image quality assessment","volume":"61","author":"Shen","year":"2020","journal-title":"Med Image Anal"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.02914","article-title":"The more the merrier? Navigating accuracy vs. energy efficiency design trade-offs in ensemble learning systems","author":"Omar","year":"2024","journal-title":"arXiv preprint arXiv:240702914"},{"key":"ref34","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"JMLR"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2024.1492808\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T06:34:29Z","timestamp":1731479669000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2024.1492808\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,13]]},"references-count":34,"alternative-id":["10.3389\/fmed.2024.1492808"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2024.1492808","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,13]]},"article-number":"1492808"}}