{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T06:58:23Z","timestamp":1785221903657,"version":"3.55.0"},"reference-count":47,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"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":["62461048"],"award-info":[{"award-number":["62461048"]}],"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":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate segmentation of retinal vessels is a key task in fundus image analysis and is crucial for the early screening and diagnosis of various ophthalmic and systemic diseases. However, existing methods still struggle to simultaneously address scale variation, contextual fusion, and the recovery of directional structures when dealing with retinal vessels, which easily leads to missed detection of thin vessels and structural discontinuities. To tackle these issues, we propose a retinal vessel segmentation network, MAF-Net. First, we design an adaptive multi-scale dilated residual block in the encoder, which performs branch-wise adaptive selection and reweighting over parallel dilated branches to dynamically adjust scale responses, thereby enabling adaptive modeling of vessel features with different calibers. Second, to enhance the network\u2019s ability to understand context, we introduce a windowed hierarchical cross-scale attention fusion module at the bottleneck layer, which enables cross-scale interaction of multi-level features within local windows, thereby efficiently aggregating contextual information while reducing computational complexity. Finally, in the skip connections, we propose a semantically guided tri-axis fusion module, which extracts directional information along the horizontal, vertical, and spatial axes, and uses progressively guided features from lower-resolution layers to generate a spatial confidence map for gated selection, thereby suppressing shallow noise and reducing discontinuities and adhesion. On three public datasets, DRIVE, STARE, and CHASE-DB1, MAF-Net achieves accuracies of 97.14%, 97.99%, and 97.82%, respectively. These results indicate that MAF-Net improves vessel structure recovery while better preserving vascular connectivity and structural consistency.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae8af7","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T22:48:07Z","timestamp":1784155687000},"page":"045045","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A retinal vessel segmentation network with multi-scale feature extraction and cross-layer attention fusion (MAF-Net)"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7243-1376","authenticated-orcid":true,"given":"Yueda","family":"Gong","sequence":"first","affiliation":[{"name":"Inner Mongolia University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoshan","family":"Li","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1518-962X","authenticated-orcid":true,"given":"Yongxing","family":"Du","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4950-8225","authenticated-orcid":true,"given":"Qi","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0650-8396","authenticated-orcid":true,"given":"Weijian","family":"Hu","sequence":"additional","affiliation":[{"name":"Inner Mongolia University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang","family":"Duan","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"bpexae8af7bib1","doi-asserted-by":"publisher","first-page":"994","DOI":"10.3969\/j.issn.1002-7386.2025.06.024","type":"journal-article","article-title":"Clinical application and research progress of artificial intelligence in fundus diseases","volume":"47","author":"Yang","year":"2025","journal-title":"Hebei Med. J."},{"key":"bpexae8af7bib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107454","type":"journal-article","article-title":"A review of retinal vessel segmentation for fundus image analysis","volume":"128","author":"Qin","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"bpexae8af7bib3","doi-asserted-by":"publisher","first-page":"4176","DOI":"10.1038\/s41598-021-83720-0","type":"journal-article","article-title":"Nasal displacement of retinal vessels on the optic disc in glaucoma associated with a nasally angled passage through lamina cribrosa","volume":"11","author":"Sawada","year":"2021","journal-title":"Sci. Rep."},{"key":"bpexae8af7bib4","doi-asserted-by":"publisher","first-page":"111985","DOI":"10.1109\/ACCESS.2021.3102176","type":"journal-article","article-title":"Retinal vessel segmentation using deep learning: a review","volume":"9","author":"Chen","year":"2021","journal-title":"IEEE Access"},{"key":"bpexae8af7bib5","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.media.2014.08.002","type":"journal-article","article-title":"Trainable COSFIRE filters for vessel delineation with application to retinal images","volume":"19","author":"Azzopardi","year":"2015","journal-title":"Med. Image Anal."},{"key":"bpexae8af7bib6","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1016\/j.patcog.2011.09.019","type":"journal-article","article-title":"Retinal vessel segmentation using a probabilistic tracking method","volume":"45","author":"Yin","year":"2012","journal-title":"Pattern Recognit."},{"key":"bpexae8af7bib7","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1109\/TMI.2009.2017941","type":"journal-article","article-title":"An active contour model for segmenting and measuring retinal vessels","volume":"28","author":"Al-Diri","year":"2009","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae8af7bib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104525","type":"journal-article","article-title":"Retinal blood vessel segmentation using root-guided decision tree-assisted enhanced fuzzy C-means clustering for disease identification","volume":"82","author":"Sindhusaranya","year":"2023","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib9","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1016\/j.patcog.2011.01.007","type":"journal-article","article-title":"Segmentation of retinal blood vessels using the radial projection and semi-supervised approach","volume":"44","author":"You","year":"2011","journal-title":"Pattern Recognit."},{"key":"bpexae8af7bib10","volume":"9351","author":"Ronneberger","year":"2015","type":"book"},{"key":"bpexae8af7bib11","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1016\/j.bbe.2022.05.003","type":"journal-article","article-title":"Dual-channel asymmetric convolutional neural network for an efficient retinal blood vessel segmentation in eye fundus images","volume":"42","author":"Xu","year":"2022","journal-title":"Biocybern. Biomed. Eng."},{"key":"bpexae8af7bib12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.3991\/ijoe.v19i15.41969","type":"journal-article","article-title":"Segmentation of retinal images using improved segmentation network","volume":"19","author":"Nair","year":"2023","journal-title":"MesU-Net Int. J. Online Biomed. Eng."},{"key":"bpexae8af7bib13","doi-asserted-by":"publisher","first-page":"14767","DOI":"10.1007\/s11042-021-10580-1","type":"journal-article","article-title":"MES-Net: a new network for retinal image segmentation","volume":"80","author":"Guo","year":"2021","journal-title":"Multimed. Tools Appl."},{"key":"bpexae8af7bib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106198","type":"journal-article","article-title":"Do you need sharpened details? Asking MMDC-Net: multi-layer multi-scale dilated convolution network for retinal vessel segmentation","volume":"150","author":"Zhong","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"bpexae8af7bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.112316","type":"journal-article","article-title":"MAGF-Net: a multiscale attention-guided fusion network for retinal vessel segmentation","volume":"206","author":"Li","year":"2023","journal-title":"Measurement"},{"key":"bpexae8af7bib16","doi-asserted-by":"publisher","first-page":"79607","DOI":"10.1007\/s11042-024-18757-0","type":"journal-article","article-title":"An improved method for retinal vessel segmentation in U-Net","volume":"83","author":"Li","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"bpexae8af7bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106296","type":"journal-article","article-title":"RVS-FDSC: a retinal vessel segmentation method with four-directional strip convolution to enhance feature extraction","volume":"95","author":"Kong","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib18","doi-asserted-by":"publisher","first-page":"5347","DOI":"10.1109\/JBHI.2024.3394151","type":"journal-article","article-title":"Retinal vessel segmentation by a transformer-U-Net hybrid model with dual-path decoder","volume":"28","author":"Zhang","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexae8af7bib19","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1007\/s11517-024-03223-8","type":"journal-article","article-title":"A multi-scale feature extraction and fusion-based model for retinal vessel segmentation in fundus images","volume":"63","author":"Zhou","year":"2025","journal-title":"Med. Biol. Eng. Comput."},{"key":"bpexae8af7bib20","doi-asserted-by":"publisher","first-page":"5258","DOI":"10.21037\/qims-24-2267","type":"journal-article","article-title":"Diabetic retinal vessel segmentation algorithm based on MA-DUNet","volume":"15","author":"Deng","year":"2025","journal-title":"Quant. Imaging Med. Surg."},{"key":"bpexae8af7bib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104651","type":"journal-article","article-title":"DCNet: a lightweight retinal vessel segmentation network","volume":"153","author":"Shang","year":"2024","journal-title":"Digit. Signal Process."},{"key":"bpexae8af7bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108272","type":"journal-article","article-title":"MSVENet: multi-scale vascular enhancement network for retinal vessel segmentation","volume":"110","author":"Cao","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108611","type":"journal-article","article-title":"PMFSNet: polarized multi-scale feature self-attention network for lightweight medical image segmentation","volume":"261","author":"Zhong","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"bpexae8af7bib24","volume":"11211","author":"Chen","year":"2018","type":"book"},{"key":"bpexae8af7bib25","first-page":"510","type":"conference-proceedings","article-title":"Selective kernel networks","author":"Li","year":"2019"},{"key":"bpexae8af7bib26","first-page":"565","type":"conference-proceedings","article-title":"V-Net: fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"bpexae8af7bib27","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1109\/TMI.2004.825627","type":"journal-article","article-title":"Ridge-based vessel segmentation in color images of the retina","volume":"23","author":"Staal","year":"2004","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae8af7bib28","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/42.845178","type":"journal-article","article-title":"Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response","volume":"19","author":"Hoover","year":"2000","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae8af7bib29","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1167\/iovs.08-3018","type":"journal-article","article-title":"Measuring retinal vessel tortuosity in 10-year-old children: validation of the computer-assisted image analysis of the retina (CAIAR) program","volume":"50","author":"Owen","year":"2009","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"bpexae8af7bib30","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106842","type":"journal-article","article-title":"Thin vessel segmentation in fundus images using attention UNet and modified Frangi filtering","volume":"99","author":"Varma","year":"2025","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib31","first-page":"5657","type":"journal-article","article-title":"Topology-preserving deep image segmentation","volume":"32","author":"Hu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"bpexae8af7bib32","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1109\/JBHI.2021.3089201","type":"journal-article","article-title":"Multi-level attention network for retinal vessel segmentation","volume":"26","author":"Yuan","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexae8af7bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118313","type":"journal-article","article-title":"Width attention-based convolutional neural network for retinal vessel segmentation","volume":"209","author":"Alvarado-carrillo","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"bpexae8af7bib34","doi-asserted-by":"publisher","first-page":"3699","DOI":"10.1109\/TMI.2022.3193146","type":"journal-article","article-title":"AADG: automatic augmentation for domain generalization on retinal image segmentation","volume":"41","author":"Lyu","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae8af7bib35","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.116526","type":"journal-article","article-title":"Bridge-Net: context-involved U-Net with patch-based loss weight mapping for retinal blood vessel segmentation","volume":"195","author":"Zhang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"bpexae8af7bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119443","type":"journal-article","article-title":"Orientation and context entangled network for retinal vessel segmentation","volume":"217","author":"Wei","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"bpexae8af7bib37","doi-asserted-by":"publisher","first-page":"4551","DOI":"10.1109\/JBHI.2022.3182471","type":"journal-article","article-title":"MFI-Net: multiscale feature interaction network for retinal vessel segmentation","volume":"26","author":"Ye","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"bpexae8af7bib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105861","type":"journal-article","article-title":"FSE-Net: rethinking the up-sampling operation in encoder\u2013decoder structure for retinal vessel segmentation","volume":"90","author":"Ni","year":"2024","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107770","type":"journal-article","article-title":"An improved supervised and attention mechanism-based U-Net algorithm for retinal vessel segmentation","volume":"168","author":"Ma","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"bpexae8af7bib40","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1007\/s40747-024-01714-7","type":"journal-article","article-title":"MSM-TDE: multi-scale semantics mining and tiny details enhancement network for retinal vessel tortuosity segmentation","volume":"11","author":"Zhang","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"bpexae8af7bib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108465","type":"journal-article","article-title":"D2PF-net: a dual-decoder progressive fusion network for retinal vessel segmentation","volume":"112","author":"Zhang","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib42","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108881","type":"journal-article","article-title":"SDHM2T: a scale direction heteroid micro to macro transition network for retinal vessel segmentation","volume":"113","author":"Zhang","year":"2026","journal-title":"Biomed. Signal Process. Control."},{"key":"bpexae8af7bib43","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128124","type":"journal-article","article-title":"FreqUNet: a lightweight dual-branch network with frequency-aware decomposition for retinal vessel segmentation","volume":"287","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"bpexae8af7bib44","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105729","type":"preprint","article-title":"Novel extraction of discriminative fine-grained feature to improve retinal vessel segmentation","author":"Zeng","year":"2025"},{"key":"bpexae8af7bib45","type":"dataset","article-title":"DRIVE: Digital Retinal Images for Vessel Extraction","author":"Staal","year":"2004","unstructured":"Staal J Abr\u00e0moff M D Niemeijer M Viergever M A Van Ginneken B 2004 DRIVE: Digital Retinal Images for Vessel Extraction Grand Challenge (available at: https:\/\/drive.grand-challenge.org\/ )"},{"key":"bpexae8af7bib46","type":"dataset","article-title":"STARE: Vessel Network Segmentation","author":"Hoover","year":"2000","unstructured":"Hoover A Kouznetsova V Goldbaum M 2000 STARE: Vessel Network Segmentation The STARE Project (available at: https:\/\/cecas.clemson.edu\/~ahoover\/stare\/probing\/index.html )"},{"key":"bpexae8af7bib47","type":"journal-article","article-title":"CHASE_DB1 retinal vessel reference dataset","author":"Barman","year":"2012","journal-title":"Kingston University"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:59:21Z","timestamp":1785218361000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae8af7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,7,28]]},"published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae8af7","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,28]]},"assertion":[{"value":"A retinal vessel segmentation network with multi-scale feature extraction and cross-layer attention fusion (MAF-Net)","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 2026 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":"2026-01-16","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-15","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-28","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}