{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T05:41:36Z","timestamp":1775108496867,"version":"3.50.1"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T00:00:00Z","timestamp":1775088000000},"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>The eye and brain share developmental and regulatory vascular similarities, and 3D vascular segmentation from Optical Coherence Tomography Angiography (OCTA) and Magnetic Resonance Angiography (MRA) is essential for neuro-ophthalmic assessment. However, vascular trees exhibit extreme multi-scale morphology and are vulnerable to topology disruptions caused by OCTA artifacts (e.g., noise and discontinuities) and MRA anatomical variants (e.g., Circle of Willis incompleteness), which often lead to fragmented vessels and unstable segment-wise predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop a unified 3D vascular segmentation framework that transfers and shares structural priors across OCTA and MRA, enabling accurate parsing under extreme scale imbalance and topology disruptions, and producing anatomically plausible predictions that remain robust to imaging artifacts in OCTA and Circle-of-Willis variants in MRA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose GA-TAN, a Graph Aggregation and Topology-Aware Network for unified ocular\u2013cerebral vascular segmentation. GA-TAN employs a variable-window hybrid CNN\u2013Transformer backbone to adapt receptive fields across vessel scales, an Efficient Multi-Scale Attention (EMA) module to enhance volumetric spatial\u2013channel interactions, and a Multi-Scale Graph Aggregation (MSGA) module to perform global topological reasoning and hierarchical feature fusion. A topology-aware training objective further supervises segment existence and connectivity to penalize structural discontinuities beyond pixel-wise losses. Experiments were conducted on Retina3D for binary 3D OCTA vessel segmentation and on TopCow for 13-class CoW artery segmentation from MRA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>GA-TAN achieved the best overall performance on Retina3D, with a DSC of 0.684 and a clDice of 0.667, indicating improved overlap accuracy and centerline connectivity preservation. On TopCow, GA-TAN obtained a mean Dice of 0.814 across 13 arterial categories and produced more anatomically consistent segment-wise predictions, showing clear advantages on thin communicating and variant-related segments. Ablation studies further validated the complementary contributions of EMA, MSGA, and topology-aware supervision.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>GA-TAN provides a unified and topology-aware solution for 3D vascular segmentation across OCTA and MRA. By integrating adaptive multi-scale modeling, graph-based global aggregation, and explicit topology supervision, the proposed framework improves both segmentation accuracy and vascular ontinuity, enhancing robustness to imaging artifacts and anatomical variants for ocular\u2013cerebral vascular analysis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1812113","type":"journal-article","created":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T04:15:33Z","timestamp":1775103333000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["GA-TAN: a graph aggregation and topology-aware network for unified 3D ocular\u2013cerebral vascular segmentation"],"prefix":"10.3389","volume":"13","author":[{"given":"Jianming","family":"Zheng","sequence":"first","affiliation":[{"name":"Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences","place":["Ningbo, China"]},{"name":"University of Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinxian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianing","family":"Ying","sequence":"additional","affiliation":[{"name":"The Affiliated Ningbo Eye Hospital, Ningbo University","place":["Ningbo, China"]},{"name":"Ningbo Eye Hospital, Wenzhou Medical University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology","place":["Eindhoven, Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quanyong","family":"Yi","sequence":"additional","affiliation":[{"name":"The Affiliated Ningbo Eye Hospital, Ningbo University","place":["Ningbo, China"]},{"name":"Ningbo Eye Hospital, Wenzhou Medical University","place":["Ningbo, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Laboratory of Advanced Theranostic Materials and Technology, Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences","place":["Ningbo, China"]},{"name":"Ningbo Cixi Institute of Biomedical Engineering","place":["Cixi, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"482","DOI":"10.1109\/JBHI.2024.3467256","volume":"29","author":"Mao","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"key":"B2","doi-asserted-by":"publisher","first-page":"105402","DOI":"10.1016\/j.pdpdt.2026.105402","article-title":"Advancements in OCT and OCTA imaging for AMD: an in-depth analysis of research hotspots, emerging trends, and technological innovations","volume":"17","author":"Liao","year":"2026","journal-title":"Photodiagnosis Photodyn Ther"},{"key":"B3","doi-asserted-by":"publisher","first-page":"103311","DOI":"10.1016\/j.media.2024.103311","article-title":"Vessel-promoted OCT to OCTA image translation by heuristic contextual constraints","volume":"98","author":"Li","year":"2024","journal-title":"Med Image Anal"},{"key":"B4","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1001\/archneur.1963.00460040068006","article-title":"Circle of Willis in cerebral vascular disorders: the anatomical structure","volume":"8","author":"Alpers","year":"1963","journal-title":"Arch Neurol"},{"key":"B5","first-page":"1","article-title":"A deep-learning-based framework for automatic segmentation and labelling of intracranial artery","volume-title":"2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)","author":"Lv","year":"2023"},{"key":"B6","first-page":"76","article-title":"Automated intracranial artery labeling using a graph neural network and hierarchical refinement","volume-title":"Medical Image Computing and Computer Assisted Intervention-MICCAI 2020: 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part VI 23","author":"Chen","year":"2020"},{"key":"B7","article-title":"Benchmarking the cow with the topcow challenge: Topology-aware anatomical segmentation of the circle of willis for cta and mra","author":"Yang","year":"2024","journal-title":"ArXiv, arXiv-2312"},{"key":"B8","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1136\/bjo-2022-321399","article-title":"Deep segmentation of OCTA for evaluation and association of changes of retinal microvasculature with Alzheimer's disease and mild cognitive impairment","volume":"108","author":"Xie","year":"2023","journal-title":"Br J Ophthalmol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1109\/TMI.2020.2992244","article-title":"Image projection network: 3D to 2D image segmentation in OCTA images","volume":"39","author":"Li","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"B10","doi-asserted-by":"crossref","first-page":"1579","DOI":"10.1109\/BIBM52615.2021.9669490","article-title":"PAENet: a progressive attention-enhanced network for 3D to 2D retinal vessel segmentation","volume-title":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Wu","year":"2021"},{"key":"B11","doi-asserted-by":"publisher","first-page":"107455","DOI":"10.1016\/j.bspc.2024.107455","article-title":"Direction-guided network for retinal vessel segmentation in OCTA images","volume":"103","author":"Li","year":"2025","journal-title":"Biomed Signal Process Control"},{"key":"B12","first-page":"424","article-title":"3D U-Net: Learning dense volumetric segmentation from sparse annotation","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2016","author":"\u00c7i\u00e7ek","year":"2016"},{"key":"B13","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1007\/978-3-031-54605-1_19","article-title":"3D retinal vessel segmentation in OCTA volumes: annotated dataset More3D and hybrid U-Net with flattening transformation","volume-title":"Pattern Recognition","author":"Kuhlmann","year":"2024"},{"key":"B14","doi-asserted-by":"publisher","first-page":"103988","DOI":"10.1016\/j.media.2026.103988","article-title":"Artifact-suppressed 3D retinal microvascular segmentation via multi-scale topology regulation","volume":"110","author":"Luo","year":"2026","journal-title":"Med Image Anal"},{"key":"B15","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","journal-title":"Proceedings of the Fourth International Conference on 3D Vision (3DV)"},{"key":"B16","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"B17","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1109\/WACV51458.2022.00181","article-title":"Unetr: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"B18","first-page":"272","article-title":"Swin unetr: Swin transformers for semantic segmentation of brain tumors in MRI images","volume-title":"International MICCAI Brainlesion Workshop","author":"Hatamizadeh","year":"2021"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73284-3_28","article-title":"Accurate delineation of cerebrovascular structures from TOF-MRA with connectivity-reinforced deep learning","author":"Yu","year":"2024","journal-title":"MLMI@MICCAI"},{"key":"B20","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1186\/s13244-024-01657-0","article-title":"Deep learning-based 3D cerebrovascular segmentation workflow on bright and black blood sequences magnetic resonance angiography","volume":"15","author":"Zhou","year":"2024","journal-title":"Insights Imaging"},{"key":"B21","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B22","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"B23","doi-asserted-by":"publisher","first-page":"101556","DOI":"10.1016\/j.media.2019.101556","article-title":"Deep vessel segmentation by learning graphical connectivity","volume":"58","author":"Shin","year":"2019","journal-title":"Med Image Anal"},{"key":"B24","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1109\/CVPR.2019.00052","article-title":"Graph-based global reasoning networks","author":"Chen","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"11107","DOI":"10.1109\/TPAMI.2025.3600335","article-title":"Neovascularization segmentation via a multilateral interaction-enhanced graph convolutional network","volume":"47","author":"Chen","year":"2025","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B26","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/978-3-032-04965-0_11","article-title":"Cross-modal graph learning for perivascular spaces segmentation","author":"Chen","year":"2025","journal-title":"Medical Image Computing and Computer Assisted Intervention"},{"key":"B27","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1016\/j.patrec.2025.01.024","article-title":"GViT-RSNet: a retinal vessel segmentation network using graph convolutional attention and multi-scale vision transformer","volume":"189","author":"Li","year":"2025","journal-title":"Pattern Recognit Lett"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1710343","DOI":"10.3389\/fcell.2025.1710343","article-title":"Image-text guided fundus vessel segmentation via attention mechanism and gated residual learning","volume":"13","author":"Xu","year":"2025","journal-title":"Front Cell Dev Biol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"16560","DOI":"10.1109\/CVPR46437.2021.01629","article-title":"clDice-a novel topology-preserving loss function for tubular structure segmentation","author":"Shit","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B30","article-title":"Topology-preserving deep image segmentation","author":"Hu","year":"2019","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"B31","doi-asserted-by":"publisher","first-page":"106060","DOI":"10.1016\/j.bspc.2024.106060","article-title":"Meta-tubular-net: a robust topology-aware re-weighting network for retinal vessel segmentation","volume":"91","author":"Huang","year":"2024","journal-title":"Biomed Signal Process Control"},{"key":"B32","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B33","doi-asserted-by":"publisher","first-page":"13713","DOI":"10.1109\/CVPR46437.2021.01350","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B34","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-030-00889-5_1","article-title":"Unet++: a nested u-net architecture for medical image segmentation","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4","author":"Zhou","year":"2018"},{"key":"B35","doi-asserted-by":"publisher","first-page":"4036","DOI":"10.1109\/TIP.2023.3293771","article-title":"nnformer: volumetric medical image segmentation via a 3d transformer","volume":"32","author":"Zhou","year":"2023","journal-title":"IEEE Trans Image Proc"},{"key":"B36","first-page":"235","article-title":"Phtrans: Parallelly aggregating global and local representations for medical image segmentation","volume-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Liu","year":"2022"},{"key":"B37","doi-asserted-by":"publisher","first-page":"103295","DOI":"10.1016\/j.media.2024.103295","article-title":"VSmTrans: A hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation","volume":"98","author":"Liu","year":"2024","journal-title":"Med Image Anal"},{"key":"B38","doi-asserted-by":"publisher","first-page":"108013","DOI":"10.1016\/j.compbiomed.2024.108013","article-title":"HmsU-Net: A hybrid multi-scale U-net based on a CNN and transformer for medical image segmentation","volume":"170","author":"Fu","year":"2024","journal-title":"Comput Biol Med"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1812113\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T04:15:39Z","timestamp":1775103339000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1812113\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,2]]},"references-count":38,"alternative-id":["10.3389\/fmed.2026.1812113"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1812113","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,2]]},"article-number":"1812113"}}