{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T12:25:48Z","timestamp":1777551948267,"version":"3.51.4"},"reference-count":55,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To address the reliance of task-specific deep learning models on large annotated datasets, this study investigates a Vector Quantized Variational Autoencoder (VQ-VAE) based few-shot learning framework for retinal vessel segmentation and disease classification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A compact VQ-VAE was pretrained on unlabeled fundus photographs to learn transferable discrete representations. The pretrained encoder was used to initialize multiple downstream models, including segmentation networks (U-Net, SegNet, ERFNet) and three additional architectures (FR-UNet, Swin-Res-Net, RV-GAN), as well as classification networks (VGG-16, ResNet-50, EfficientNet-B0). Retinal vessel segmentation was evaluated on three public datasets (DRIVE, STructured Analysis of the Retina [STARE], and CHASE), while disease classification was assessed on the Retina and Ocular Disease Intelligent Recognition (ODIR) datasets. Segmentation performance was evaluated using Dice coefficient, Recall, Accuracy, Intersection over Union (IoU), mean IoU, and Average Offset Distance. Classification performance was assessed using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC), with additional validation on the heterogeneous ODIR dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The VQ-VAE pretraining consistently improved performance under small-sample conditions. On the DRIVE dataset, Dice scores increased by approximately 2 percentage points across all segmentation backbones, with U-Net improving from 0.780 to 0.796 and SegNet from 0.670 to 0.692. Consistent performance improvements were also observed on the STARE and CHASE datasets. For disease classification on the Retina dataset, accuracy increased from 20% to 60% using only 70 labeled images. On the ODIR dataset, mean AUC improved across architectures, from 0.677 to 0.724 for VGG-16, 0.684 to 0.745 for ResNet-50, and 0.664 to 0.726 for EfficientNet-B0, indicating enhanced robustness across diverse disease categories and imaging conditions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed pretraining framework effectively reduces labeled data requirements while improving performance across multiple ophthalmic tasks, offering a scalable and resource-efficient solution for real-world clinical applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261433086","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T08:24:53Z","timestamp":1773822293000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["A unified VQ-VAE framework for few-shot retinal vessel segmentation and multidisease classification"],"prefix":"10.1177","volume":"12","author":[{"given":"Haojun","family":"Yu","sequence":"first","affiliation":[{"name":"Chongqing Medical University-University of Leicester Joint Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongcai","family":"Tan","sequence":"additional","affiliation":[{"name":"Imperial College London"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhen","family":"Liu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1847-9913","authenticated-orcid":false,"given":"Xinyu","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(25)00143-3"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2214-109X(20)30425-3"},{"key":"e_1_3_3_4_2","first-page":"00","article-title":"Deep learning algorithms for screening and diagnosis of systemic diseases based on ophthalmic manifestations: a systematic review","volume":"13","author":"Iao WC","year":"2023","unstructured":"Iao WC, Zhang W, Wang X, et al. Deep learning algorithms for screening and diagnosis of systemic diseases based on ophthalmic manifestations: a systematic review. Diagnostics (Basel) 2023; 13: 00.","journal-title":"Diagnostics (Basel)"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-018-0195-0"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-25138-w"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3558425"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2025.1580502"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1177\/00220345241253186"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2024.108241"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.13.9.22"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2016.7493362"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2791488"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.medengphy.2023.104048"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2021.04.021"},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Butoi VI Ortiz JJG Ma T et al. UniverSeg: Universal Medical Image Segmentation. Epub ahead of print 12 April 2023. DOI: 10.48550\/arXiv.2304.06131","DOI":"10.1109\/ICCV51070.2023.01960"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2020.3269"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2020.3256"},{"key":"e_1_3_3_19_2","first-page":"8660","article-title":"A few-shot learning-based eye diseases screening method","volume":"26","author":"Han Z-K","year":"2022","unstructured":"Han Z-K, Xing H, Yang B, et al. A few-shot learning-based eye diseases screening method. Eur Rev Med Pharmacol Sci 2022; 26: 8660\u20138674.","journal-title":"Eur Rev Med Pharmacol Sci"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105639"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102059"},{"key":"e_1_3_3_22_2","volume-title":"Advances in neural information processing systems","author":"Goodfellow IJ","year":"2006","unstructured":"Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial netsAdvances in neural information processing systems. Universite\u00b4 de Montre\u00b4al, Montre\u00b4al, QC: Curran Associates, Inc., 2006. https:\/\/papers.nips.cc\/paper_files\/paper\/2014\/hash\/f033ed80deb0234979a61f95710dbe25-Abstract.html (2014, accessed 7 July 2025)."},{"key":"e_1_3_3_23_2","unstructured":"Kingma DP Welling M. Auto-Encoding Variational Bayes. Epub ahead of print 10 December 2022. DOI: 10.48550\/arXiv.1312.6114."},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-024-01370-x"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.102006"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3345179"},{"key":"e_1_3_3_27_2","unstructured":"Joy T Schmon SM Torr PHS et al. Capturing Label Characteristics in VAEs. Epub ahead of print 16 December 2022. DOI: 10.48550\/arXiv.2006.10102."},{"key":"e_1_3_3_28_2","unstructured":"Zhao S Song J Ermon S. Learning Hierarchical Features from Generative Models. Epub ahead of print 9 June 2017. DOI: 10.48550\/arXiv.1702.08396."},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-46903-5"},{"key":"e_1_3_3_30_2","unstructured":"Kuka\u010dka J Zenz A Kollovieh M et al. Self-Supervised Learning from Unlabeled Fundus Photographs Improves Segmentation of the Retina. Epub ahead of print 5 August 2021. DOI: 10.48550\/arXiv.2108.02798."},{"key":"e_1_3_3_31_2","unstructured":"Oord Avd Vinyals O Kavukcuoglu K. Neural Discrete Representation Learning. Epub ahead of print 30 May 2018. DOI: 10.48550\/arXiv.1711.00937."},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2004.825627"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/42.845178"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1161\/ATVBAHA.111.225219"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-71058-3_11"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3188710"},{"key":"e_1_3_3_40_2","unstructured":"Yang R Zhang S. Enhancing Retinal Vascular Structure Segmentation in Images With a Novel Design Two-Path Interactive Fusion Module Model. Epub ahead of print 3 March 2024. DOI: 10.48550\/arXiv.2403.01362"},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_4"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102837"},{"key":"e_1_3_3_43_2","unstructured":"Chen T Kornblith S Norouzi M et al. A Simple Framework for Contrastive Learning of Visual Representations. Epub ahead of print 1 July 2020. DOI: 10.48550\/arXiv.2002.05709."},{"key":"e_1_3_3_44_2","unstructured":"Grill J-B Strub F Altch\u00e9 F et al. Bootstrap your own latent: A new approach to self-supervised Learning. Epub ahead of print 10 September 2020. DOI: 10.48550\/arXiv.2006.07733."},{"key":"e_1_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.21037\/qims-23-567"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107148"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-021-02321-1"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2023.3298710"},{"key":"e_1_3_3_49_2","unstructured":"Li L Qiu J Saha A et al. Artificial Intelligence for Biomedical Video Generation. Epub ahead of print 12 November 2024. DOI: 10.48550\/arXiv.2411.07619."},{"key":"e_1_3_3_50_2","first-page":"82","article-title":"Anomaly detection in optical coherence tomography angiography (OCTA) with a vector-quantized variational auto-encoder (VQ-VAE)","volume":"11","author":"Jebril H","year":"2024","unstructured":"Jebril H, Eseng\u00f6n\u00fcl M, Bogunovi\u0107 H. Anomaly detection in optical coherence tomography angiography (OCTA) with a vector-quantized variational auto-encoder (VQ-VAE). Bioengineering (Basel) 2024; 11: 82.","journal-title":"Bioengineering (Basel)"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0313549"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA60407.2023.00045"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41456-5_57"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.08.059"},{"key":"e_1_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2903434"},{"key":"e_1_3_3_56_2","first-page":"2","article-title":"Generative modeling for retinal Fundus image synthesis","volume":"5","author":"Sengupta S","year":"2019","unstructured":"Sengupta S, Zelek J, Lakhsminarayanan V. Generative modeling for retinal Fundus image synthesis. J Comput Vis Imaging Syst 2019; 5: 2\u20132.","journal-title":"J Comput Vis Imaging Syst"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433086","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261433086","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261433086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:24Z","timestamp":1777398984000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261433086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":55,"alternative-id":["10.1177\/20552076261433086"],"URL":"https:\/\/doi.org\/10.1177\/20552076261433086","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261433086"}}