{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T09:08:20Z","timestamp":1780564100554,"version":"3.54.1"},"reference-count":47,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T00:00:00Z","timestamp":1780531200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100020084","name":"Guangzhou Municipal Science and Technology Bureau","doi-asserted-by":"crossref","award":["202206010130"],"award-info":[{"award-number":["202206010130"]}],"id":[{"id":"10.13039\/501100020084","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2026A1515010616"],"award-info":[{"award-number":["2026A1515010616"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>\n                    Digital Subtraction Angiography (DSA) is widely regarded as the clinical gold standard for cerebrovascular disease diagnosis, but cerebrovascular segmentation in DSA sequences remains challenging due to complex vascular morphology and strong spatiotemporal dependencies. Existing methods, including Convolutional Neural Networks (CNNs) and Transformers, struggle with spatiotemporal coupling and computational inefficiency\u2014especially Transformers, which suffer from quadratic complexity (O(N\n                    <jats:sup>2<\/jats:sup>\n                    )) when processing long sequences. To address these issues, we propose BTSANet, a novel spatiotemporal segmentation network based on the Mamba architecture that enables efficient long-range temporal dependency modeling with linear complexity O(N) at the network bottleneck, avoiding the quadratic cost of full-sequence self-attention. Our network features a dual-branch encoder: one processes raw DSA sequences to capture hemodynamics, while the other takes Minimum Intensity Projection (MinIP) images to extract enhanced vascular structural priors. At the bottleneck, we introduce a Bidirectional Temporal-Spatial Attention (BTSA) module with an asymmetric cross-attention strategy that operates on compressed bottleneck features, introducing only an O(T \u00d7 hw) interaction cost rather than the O(N\n                    <jats:sup>2<\/jats:sup>\n                    ) self-attention. This module prioritizes spatial structural information, enabling adaptive alignment of temporal dynamics with spatial features to enhance the delineation of vascular boundaries, particularly for fine branches. Extensive experiments on the public DIAS dataset demonstrate that BTSANet outperforms state-of-the-art models based on CNNs, Transformers, and Mamba across multiple metrics, achieving a Dice score of 94.39 \u00b1 1.40% and an Intersection over Union (IoU) of 89.41 \u00b1 2.51%. Systematic ablation studies confirm the synergistic effects between structural priors and temporal dynamics, underscoring the efficacy of each core component. This work offers a robust technical solution for intelligent DSA sequence analysis, with promising clinical translation value.\n                  <\/jats:p>","DOI":"10.7717\/peerj-cs.3897","type":"journal-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T08:43:52Z","timestamp":1780562632000},"page":"e3897","source":"Crossref","is-referenced-by-count":0,"title":["BTSANet: integrating structural prior and temporal dynamics with Mamba for accurate cerebrovascular segmentation in DSA sequences"],"prefix":"10.7717","volume":"12","author":[{"given":"Weihuang","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqing","family":"Mo","sequence":"additional","affiliation":[{"name":"School of Art and Design, Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"10.7717\/peerj-cs.3897\/ref-1","first-page":"205","article-title":"Swin-Unet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.7717\/peerj-cs.3897\/ref-2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04306","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"10.7717\/peerj-cs.3897\/ref-3","doi-asserted-by":"publisher","first-page":"3741","DOI":"10.1109\/tmi.2025.3564765","article-title":"Mamba-Sea: a Mamba-based framework with global-to-local sequence augmentation for generalizable medical image segmentation","volume":"44","author":"Cheng","year":"2025","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3897\/ref-4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16 \u00d7 16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2010"},{"key":"10.7717\/peerj-cs.3897\/ref-5","first-page":"375","article-title":"Vessel segmentation in low contrast X-ray angiogram images","author":"Felfelian","year":"2016"},{"key":"10.7717\/peerj-cs.3897\/ref-6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2025.3535622","article-title":"MSFMamba: multi-scale feature fusion state space model for multi-source remote sensing image classification","volume":"63","author":"Gao","year":"2025","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"10.7717\/peerj-cs.3897\/ref-7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.00752","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023"},{"key":"10.7717\/peerj-cs.3897\/ref-8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2111.00396","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021"},{"key":"10.7717\/peerj-cs.3897\/ref-9","first-page":"572","article-title":"Combining recurrent, convolutional, and continuous-time models with linear state-space layers","volume":"34","author":"Gu","year":"2021","journal-title":"NeurIPS"},{"key":"10.7717\/peerj-cs.3897\/ref-10","first-page":"1748","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022"},{"issue":"1","key":"10.7717\/peerj-cs.3897\/ref-11","doi-asserted-by":"publisher","first-page":"102762","DOI":"10.1016\/j.media.2023.102762","article-title":"Transforming medical imaging with transformers? A comparative review of key properties, current progresses, and future perspectives","volume":"85","author":"He","year":"2023","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3897\/ref-12","first-page":"12","article-title":"LocalMamba: visual state space model with windowed selective scan","author":"Huang","year":"2024"},{"key":"10.7717\/peerj-cs.3897\/ref-13","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":"Nature Methods"},{"issue":"10","key":"10.7717\/peerj-cs.3897\/ref-14","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1136\/neurintsurg-2020-015824","article-title":"Fully automated intracranial aneurysm detection and segmentation from digital subtraction angiography series using an end-to-end spatiotemporal deep neural network","volume":"12","author":"Jin","year":"2020","journal-title":"Journal of NeuroInterventional Surgery"},{"issue":"5","key":"10.7717\/peerj-cs.3897\/ref-15","doi-asserted-by":"publisher","first-page":"129580","DOI":"10.1016\/j.neucom.2025.129580","article-title":"Gl-MambaNet: a global-local hybrid mamba network for medical image segmentation","volume":"626","author":"Kui","year":"2025","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3897\/ref-16","first-page":"4652","article-title":"U-KAN makes strong backbone for medical image segmentation and generation","author":"Li","year":"2025"},{"issue":"24","key":"10.7717\/peerj-cs.3897\/ref-17","doi-asserted-by":"publisher","first-page":"103247","DOI":"10.1016\/j.media.2024.103247","article-title":"DIAS: a dataset and benchmark for intracranial artery segmentation in DSA sequences","volume":"97","author":"Liu","year":"2024","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3897\/ref-18","first-page":"615","article-title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","author":"Liu","year":"2024"},{"issue":"11","key":"10.7717\/peerj-cs.3897\/ref-19","doi-asserted-by":"publisher","first-page":"102035","DOI":"10.1016\/j.media.2021.102035","article-title":"Loss Odyssey in medical image segmentation","volume":"71","author":"Ma","year":"2021","journal-title":"Medical Image Analysis"},{"key":"10.7717\/peerj-cs.3897\/ref-20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.04722","article-title":"U-Mamba: enhancing long-range dependency for biomedical image segmentation","author":"Ma","year":"2024"},{"key":"10.7717\/peerj-cs.3897\/ref-21","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.neucom.2019.10.035","article-title":"Multiscale dense convolutional neural network for DSA cerebrovascular segmentation","volume":"373","author":"Meng","year":"2020","journal-title":"Neurocomputing"},{"key":"10.7717\/peerj-cs.3897\/ref-22","first-page":"677","article-title":"Multi-resolution CNN for brain vessel segmentation from cerebrovascular images of intracranial aneurysm: a comparison of U-Net and DeepMedic","author":"Patel","year":"2020"},{"key":"10.7717\/peerj-cs.3897\/ref-23","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.7717\/peerj-cs.3897\/ref-24","doi-asserted-by":"publisher","first-page":"2982","DOI":"10.1016\/j.jacc.2019.10.009","article-title":"Global burden of cardiovascular diseases and risk factors, 1990\u20132019","volume":"76","author":"Roth","year":"2020","journal-title":"Journal of the American College of Cardiology"},{"key":"10.7717\/peerj-cs.3897\/ref-25","doi-asserted-by":"publisher","first-page":"108205","DOI":"10.1145\/3767748","article-title":"VM-UNet: vision Mamba UNet for medical image segmentation","volume":"10","author":"Ruan","year":"2025","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications"},{"key":"10.7717\/peerj-cs.3897\/ref-26","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-59745-002-7","volume-title":"Cerebrovascular angiography: handbook of complex percutaneous carotid intervention","author":"Saw","year":"2007"},{"issue":"1","key":"10.7717\/peerj-cs.3897\/ref-27","doi-asserted-by":"publisher","first-page":"102392","DOI":"10.1016\/j.compmedimag.2024.102392","article-title":"CAVE: cerebral artery-vein segmentation in digital subtraction angiography","volume":"115","author":"Su","year":"2024","journal-title":"Computerized Medical Imaging and Graphics"},{"issue":"6","key":"10.7717\/peerj-cs.3897\/ref-28","doi-asserted-by":"publisher","first-page":"128241","DOI":"10.1016\/j.eswa.2025.128241","article-title":"MSM-UNet: a medical image segmentation method based on wavelet transform and multi-scale Mamba-UNet","volume":"288","author":"Sun","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3897\/ref-29","first-page":"36","article-title":"Medical transformer: gated axial-attention for medical image segmentation","author":"Valanarasu","year":"2021"},{"key":"10.7717\/peerj-cs.3897\/ref-30","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.7717\/peerj-cs.3897\/ref-31","first-page":"3220","article-title":"Weakly-supervised convolutional neural networks for vessel segmentation in cerebral angiography","author":"Vepa","year":"2022"},{"key":"10.7717\/peerj-cs.3897\/ref-32","first-page":"106","article-title":"JointVesselNet: joint volume-projection convolutional embedding networks for 3D cerebrovascular segmentation","author":"Wang","year":"2020"},{"key":"10.7717\/peerj-cs.3897\/ref-33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.05079","article-title":"Mamba-UNet: UNet-like pure visual mamba for medical image segmentation","author":"Wang","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3897\/ref-34","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1016\/j.neucom.2025.129447","article-title":"H-vmunet: high-order vision Mamba UNet for medical image segmentation","volume":"624","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"issue":"11","key":"10.7717\/peerj-cs.3897\/ref-35","doi-asserted-by":"publisher","first-page":"101298","DOI":"10.1016\/j.patter.2025.101298","article-title":"Ultralight VM-UNet: parallel vision mamba significantly reduces parameters for skin lesion segmentation","volume":"6","author":"Wu","year":"2024","journal-title":"Patterns"},{"key":"10.7717\/peerj-cs.3897\/ref-36","first-page":"199","article-title":"DSNet: a spatio-temporal consistency network for cerebrovascular segmentation in digital subtraction angiography sequences","author":"Xie","year":"2024"},{"issue":"2","key":"10.7717\/peerj-cs.3897\/ref-37","doi-asserted-by":"publisher","first-page":"103564","DOI":"10.1016\/j.media.2025.103564","article-title":"Bi-variational physics-informed operator network for fractional flow reserve curve assessment from coronary angiography","volume":"103","author":"Xie","year":"2025","journal-title":"Medical Image Analysis"},{"issue":"1","key":"10.7717\/peerj-cs.3897\/ref-38","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TMI.2025.3589797","article-title":"Segmamba-v2: long-range sequential modeling Mamba for general 3d medical image segmentation","volume":"45","author":"Xing","year":"2025","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.7717\/peerj-cs.3897\/ref-39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2404.18861","article-title":"Visual Mamba: a survey and new outlooks","author":"Xu","year":"2024a"},{"key":"10.7717\/peerj-cs.3897\/ref-40","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1109\/jbhi.2023.3342195","article-title":"ERNet: edge regularization network for cerebral vessel segmentation in digital subtraction angiography images","volume":"28","author":"Xu","year":"2024b","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"10.7717\/peerj-cs.3897\/ref-41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2401.14168","article-title":"Vivim: a video vision mamba for medical video object segmentation","author":"Yang","year":"2024"},{"issue":"3","key":"10.7717\/peerj-cs.3897\/ref-42","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1109\/tmi.2022.3219126","article-title":"Progressive perception learning for main coronary segmentation in X-ray angiography","volume":"42","author":"Zhang","year":"2025a","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"10","key":"10.7717\/peerj-cs.3897\/ref-43","doi-asserted-by":"publisher","first-page":"103792","DOI":"10.1016\/j.media.2025.103792","article-title":"Switch-UMamba: dynamic scanning vision Mamba UNet for medical image segmentation","volume":"107","author":"Zhang","year":"2026","journal-title":"Medical Image Analysis"},{"issue":"44","key":"10.7717\/peerj-cs.3897\/ref-44","doi-asserted-by":"publisher","first-page":"2515","DOI":"10.1109\/tmi.2025.3540886","article-title":"DSCA: a digital subtraction angiography sequence dataset and spatio-temporal model for cerebral artery segmentation","volume":"2025","author":"Zhang","year":"2025b","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"1","key":"10.7717\/peerj-cs.3897\/ref-45","doi-asserted-by":"publisher","first-page":"105159","DOI":"10.1016\/j.cmpb.2019.105159","article-title":"A neural network approach to segment brain blood vessels in digital subtraction angiography","volume":"185","author":"Zhang","year":"2020","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"10","key":"10.7717\/peerj-cs.3897\/ref-46","doi-asserted-by":"publisher","first-page":"131448","DOI":"10.1016\/j.neucom.2025.131448","article-title":"Wavelet attention is all you need in multimodal medical image fusion","volume":"656","author":"Zhou","year":"2025","journal-title":"Neurocomputing"},{"issue":"14","key":"10.7717\/peerj-cs.3897\/ref-47","doi-asserted-by":"publisher","first-page":"4748","DOI":"10.3390\/s24144748","article-title":"DeMambaNet: deformable convolution and Mamba integration network for high-precision segmentation of ambiguously defined dental radicular boundaries","volume":"24","author":"Zou","year":"2024","journal-title":"Sensors"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3897.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3897.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3897.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3897.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T08:43:57Z","timestamp":1780562637000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,4]]},"references-count":47,"alternative-id":["10.7717\/peerj-cs.3897"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3897","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,4]]},"article-number":"e3897"}}