{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T00:06:08Z","timestamp":1752192368372,"version":"3.41.2"},"reference-count":42,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/page\/copyright"},{"start":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T00:00:00Z","timestamp":1752019200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 61961037"],"award-info":[{"award-number":["No. 61961037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective<\/jats:italic>. Retinal image registration improves the accuracy and validity of a doctor\u2019s diagnosis and holds a crucial role in the monitoring and treatment of associated diseases. However, most existing image registration methods have limitations in identifying retinal vascular features, making it difficult to achieve desirable results in retinal image registration tasks. To solve this problem, a fusion network of Swin Transformer and U-Net, improved by Differential Multi-scale Convolutional Block Attention Module with Residual Mechanism (DMCR), named D-STUNet, is proposed in conjunction with the designed Progressive Keypoint Screening (PKS) strategy. Approach. The D-STUNet network is primarily based on an encoder-decoder framework, and employs DMCR for the improvement and fusion of the Swin Transformer and U-Net networks. Among them, the DMCR module enhances the ability to focus on retinal vascular features, which effectively improves the accuracy of retinal image registration in the event of limited data. Simultaneously, the network introduces the PKS strategy to enable the gradual accumulation of effective keypoint information in the course of the training, which ensures that the keypoints are more concentrated in the retinal vascular region, thus enhancing the matching rate and overall detection effect. Main results. The registration validation is conducted on the publicly accessible dataset Fundus Image Registration Dataset (FIRE) and compare it with nine algorithms. The experimental results show that the algorithm achieves an acceptance rate of 98.50%, a failure rate of 0, and an inaccuracy rate of 1.50%. In the area under the curve (AUC) metric, AUC for the Easy group is 0.929, while the AUC for the Mod and Hard groups are 0.883 and 0.724, respectively. The mean area under the curve (mAUC) across all comparison algorithms is the highest, outperforming the second-best algorithm by 0.09. Although it did not reach the optimum in certain subcategories (such as AUC-easy), its overall performance is significantly superior to existing methods. Significance. The proposed network is able to effectively capture local features such as complex vascular structures in retinal images, providing a new method to improve the registration accuracy of retinal images.<\/jats:p>","DOI":"10.1088\/2057-1976\/ade9c6","type":"journal-article","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T18:47:51Z","timestamp":1751309271000},"page":"045023","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised retinal image registration based on D-STUNet and progressive keypoint screening strategy"],"prefix":"10.1088","volume":"11","author":[{"given":"Xiangyu","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8363-2107","authenticated-orcid":true,"given":"Jiayi","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,7,9]]},"reference":[{"key":"bpexade9c6bib1","doi-asserted-by":"publisher","first-page":"2911","DOI":"10.1109\/CVPR.2012.6248018","article-title":"Three things everyone should know to improve object retrieval","author":"Arandjelovi\u0107","year":"2012"},{"key":"bpexade9c6bib2","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TMI.2019.2897538","article-title":"VoxelMorph: A learning framework for deformable medical image registration","volume":"38","author":"Balakrishnan","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexade9c6bib3","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/978-3-031-25066-8_9","article-title":"Swin-Unet: unet-Like pure transformer for medical image segmentation","volume":"13803","author":"Cao","year":"2023"},{"key":"bpexade9c6bib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102615","article-title":"TransMorph: transformer for unsupervised medical image registration","volume":"82","author":"Chen","year":"2022","journal-title":"Med. Image Anal."},{"key":"bpexade9c6bib5","doi-asserted-by":"publisher","first-page":"337","DOI":"10.48550\/arXiv.1712.07629","article-title":"SuperPoint: self-supervised interest point detection and description","author":"DeTone","year":"2017"},{"article-title":"An image is worth 16x16 words: transformers for image recognition at Scale","year":"2020","author":"Dosovitskiy","key":"bpexade9c6bib6"},{"key":"bpexade9c6bib7","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad9e69","article-title":"Unsupervised deep learning-based medical image registration: a survey","volume":"70","author":"Duan","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"bpexade9c6bib8","doi-asserted-by":"publisher","first-page":"3362","DOI":"10.1109\/JBHI.2020.2984483","article-title":"REMPE: registration of retinal images through eye modelling and pose estimation","volume":"24","author":"Hernandez-Matas","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexade9c6bib9","doi-asserted-by":"publisher","first-page":"3362","DOI":"10.1109\/JBHI.2020.2984483","article-title":"REMPE: registration of retinal images through eye modelling and pose estimation","volume":"24","author":"Hernandez-Matas","year":"2020b","journal-title":"IEEE J. Biomed. Health Informat."},{"key":"bpexade9c6bib10","doi-asserted-by":"publisher","DOI":"10.35119\/maio.v1i4.42","article-title":"Fundus image registration dataset","author":"Hernandez-Matas","year":"2017a","unstructured":"Hernandez-Matas C Zabulis X Triantafyllou A Anyfanti P Douma S FIRE A A A 2017a Fundus image registration dataset (Accessed 7 July 2017) 10.35119\/maio.v1i4.42"},{"key":"bpexade9c6bib11","doi-asserted-by":"publisher","first-page":"176630","DOI":"10.1109\/ACCESS.2024.3477420","article-title":"Retinal health screening using artificial intelligence with digital fundus images: a review of the last decade","volume":"12","author":"Islam","year":"2024","journal-title":"IEEE Access"},{"key":"bpexade9c6bib12","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1007\/s10462-025-11153-6","article-title":"Current and future roles of artificial intelligence in retinopathy of prematurity","volume":"58","author":"Jafarizadeh","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"bpexade9c6bib13","doi-asserted-by":"publisher","first-page":"19865","DOI":"10.1109\/CVPR52733.2024.01878","article-title":"OmniGlue: generalizable feature matching with foundation model guidance","author":"Jiang","year":"2024"},{"key":"bpexade9c6bib14","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft COCO: common objects in context","volume":"8693","author":"Lin","year":"2014"},{"key":"bpexade9c6bib15","doi-asserted-by":"publisher","first-page":"9522","DOI":"10.1109\/ICCV51070.2023.00876","article-title":"Geometrized transformer for self-supervised homography estimation","author":"Liu","year":"2023"},{"key":"bpexade9c6bib16","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-031-19803-8_35","article-title":"Semi-supervised keypoint detector and descriptor for retinal image matching","volume":"13681","author":"Liu","year":"2022"},{"key":"bpexade9c6bib17","doi-asserted-by":"publisher","first-page":"9992","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"bpexade9c6bib18","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"bpexade9c6bib19","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"bpexade9c6bib20","doi-asserted-by":"publisher","first-page":"7763","DOI":"10.1109\/WACV57701.2024.00760","article-title":"Reverse knowledge distillation: training a large model using a small one for retinal image matching on limited data","author":"Nasser","year":"2024"},{"key":"bpexade9c6bib21","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/s42492-024-00173-8","article-title":"Medical image registration and its application in retinal images:a review","volume":"7","author":"Nie","year":"2024","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"year":"2019","author":"ODIR-5K Ophthalmic Dataset","key":"bpexade9c6bib22"},{"key":"bpexade9c6bib23","doi-asserted-by":"publisher","first-page":"4089","DOI":"10.1109\/ICIP.2010.5650657","article-title":"Identity verification based on vessel matching from fundus images","author":"Oinonen","year":"2010"},{"article-title":"DINOv2: learning robust visual features without supervision","year":"2024","author":"Oquab","key":"bpexade9c6bib24"},{"key":"bpexade9c6bib25","doi-asserted-by":"publisher","first-page":"6047","DOI":"10.1109\/ICCV51070.2023.00558","article-title":"Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation","author":"Qi","year":"2023"},{"key":"bpexade9c6bib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105209","article-title":"UTR: a UNet-like transformer for efficient unsupervised medicalimage registration","volume":"150","author":"Qiu","year":"2024","journal-title":"Image Vis. Comput."},{"key":"bpexade9c6bib27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.06195","article-title":"R2D2: reliable and repeatable detector and descriptor","volume":"32","author":"Revaud","year":"2019","journal-title":"Neural Inf. Process. Syst."},{"key":"bpexade9c6bib28","doi-asserted-by":"publisher","first-page":"3721","DOI":"10.1007\/s11517-024-03160-6","article-title":"ConKeD: multiview contrastive descriptor learning for keypoint-based retinal image registration","volume":"62","author":"Rivas-Villar","year":"2024","journal-title":"Med. Biol. Eng. Comput."},{"key":"bpexade9c6bib29","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer Assisted Intervention(MICCAI)"},{"key":"bpexade9c6bib30","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1201\/9781003464884","article-title":"Medical imaging technologies and their applications in diagnosis and treatment","author":"Roy","year":"2024"},{"key":"bpexade9c6bib31","doi-asserted-by":"publisher","first-page":"2564","DOI":"10.1109\/ICCV.2011.6126544","article-title":"ORB: An efficient alternative to SIFT or SURF","volume":"2011","author":"Rublee","year":"2011","journal-title":"International Conference on Computer Vision(ICCV)"},{"key":"bpexade9c6bib32","doi-asserted-by":"publisher","first-page":"4937","DOI":"10.48550\/arXiv.1911.11763","article-title":"SuperGlue: learning feature matching with graph neural networks","author":"Sarlin","year":"2019"},{"key":"bpexade9c6bib33","doi-asserted-by":"publisher","first-page":"87987","DOI":"10.1007\/s11042-024-18710-1","article-title":"An efficient similarity metric for 3D medical image registration","volume":"83","author":"Sengupta","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"bpexade9c6bib34","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/s40200-025-01596-7","article-title":"Artificial intelligence for early detection of diabetes mellitus complications via retinal imaging","volume":"24","author":"Sobhi","year":"2025","journal-title":"J. Diabetes Metab. Disord."},{"key":"bpexade9c6bib35","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1097\/APO.0000000000000509","article-title":"The new era of retinal imaging in hypertensive patients","volume":"11","author":"Tan","year":"2022","journal-title":"Asia Pac. J. Ophthalmol. (Phila.)"},{"key":"bpexade9c6bib36","doi-asserted-by":"publisher","first-page":"10731","DOI":"10.1109\/ICCV.2019.01083","article-title":"GLAMpoints: greedily learned accurate match points","author":"Truong","year":"2019"},{"key":"bpexade9c6bib37","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad120e","article-title":"SOLID: a novel similarity metric for mono-modal and multi-modal deformable image registration","volume":"69","author":"Tzitzimpasis","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"bpexade9c6bib38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Neural Inf. Process. Syst."},{"key":"bpexade9c6bib39","doi-asserted-by":"publisher","first-page":"14408","DOI":"10.48550\/arXiv.2211.05778","article-title":"InternImage: exploring large-scale vision foundation models with deformable convolutions","author":"Wang","year":"2022"},{"key":"bpexade9c6bib40","doi-asserted-by":"publisher","DOI":"10.1515\/biol-2022-0773","article-title":"Research progress on ocular complications caused by type 2 diabetes mellitus and the function of tears and blepharons","volume":"19","author":"Wang","year":"2024","journal-title":"Open Life Sci."},{"key":"bpexade9c6bib41","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"CBAM: convolutional block attention module","volume":"11211","author":"Woo","year":"2018"},{"key":"bpexade9c6bib42","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102286","article-title":"A transformer-based hierarchical registration framework for multimodality deformable image registration","volume":"108","author":"Zhao","year":"2023","journal-title":"Comput. Med. Imaging Graph."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T12:59:18Z","timestamp":1752152358000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ade9c6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,9]]},"references-count":42,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,7,9]]},"published-print":{"date-parts":[[2025,7,31]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ade9c6","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,7,9]]},"assertion":[{"value":"Unsupervised retinal image registration based on D-STUNet and progressive keypoint screening strategy","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-04-25","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-07-09","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}