EUVIMEDEUVIMED entdecken
Open Access

VesMamba: Vessel Morphology‐Enhanced State Space Model for Cerebrovascular Delineation

Lei Xie, Jiangxu Zhang, Jiawei Zhang iD, Qingrun Zeng iD, Yuanjing Feng iD

NMR in Biomedicine · 2026-09 · 39 (9)

DOI: 10.1002/nbm.70339 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NMR in Biomedicine, online erschienen am 17.07.2026. Verfasst von Lei Xie und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Zhejiang University of Technology, Hangzhou, China. Hauptthemen laut MEDLINE: Deep Learning, Blood Vessels. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China, Post Doctoral Science Preferential Funding of Zhejiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate delineation of cerebrovascular structures from Time‐Of‐Flight Magnetic Resonance Angiography (TOF‐MRA) and Computed Tomography Angiography (CTA) is essential for the clinical diagnosis and treatment of cerebrovascular diseases. However, the intricate topology and fine‐scale nature of cerebral vessels pose significant challenges for deep learning methods, which often struggle to capture long‐range dependencies and precise morphological details. In this work, we propose VesMamba, a deep learning framework that integrates explicit vascular morphological priors into a state‐space model. Unlike generic SSM‐based methods that rely on fixed scanning patterns, we introduce a Tri‐oriented Vessel‐aware Mamba (ToVM) module, which dynamically reorders input 1D sequences using cerebrovascular edge features to better model complex vascular structures. Complementarily, we present the 3D Large‐Small Gated Convolution (LSGC) module after the ToVM module to preserve critical spatial information. We conducted extensive experiments on two TOF‐MRA and one CTA dataset, comparing our method with eight state‐of‐the‐art approaches. Our results show that VesMamba achieves superior performance on the majority of evaluation metrics relative to all competing methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBlood VesselsHumansMagnetic Resonance AngiographyComputed Tomography AngiographyAlgorithmsImaging, Three-Dimensional

Stichwörter der Autor:innen

cerebrovascular delineationdeep Learningmedical image analysisstate space models

Autor:innen und Institutionen

  • College of Information Engineering, Zhejiang University of Technology, Hangzhou, China.
  • Institute for Frontiers and Interdisciplinary Science, Zhejiang University of Technology, Hangzhou, China.

ORCID-Profile: Jiawei Zhang, Qingrun Zeng, Yuanjing Feng

Förderung

  • Natural Science Foundation of Zhejiang Province
  • National Natural Science Foundation of China
  • Post Doctoral Science Preferential Funding of Zhejiang Province
  • Natural Science Foundation of Hangzhou
  • China Postdoctoral Science Foundation

Zitieren

APA

Xie, L., Zhang, J., Zhang, J., Zeng, Q., & Feng, Y. (2026). VesMamba: Vessel Morphology‐Enhanced State Space Model for Cerebrovascular Delineation. NMR in Biomedicine, 39(9). https://doi.org/10.1002/nbm.70339

Vancouver

Xie L, Zhang J, Zhang J, Zeng Q, Feng Y. VesMamba: Vessel Morphology‐Enhanced State Space Model for Cerebrovascular Delineation. NMR in Biomedicine. 2026;39(9). doi:10.1002/nbm.70339

BibTeX
@article{Xie2026,
  author = {Xie, Lei and Zhang, Jiangxu and Zhang, Jiawei and Zeng, Qingrun and Feng, Yuanjing},
  title = {VesMamba: Vessel Morphology‐Enhanced State Space Model for Cerebrovascular Delineation},
  journal = {NMR in Biomedicine},
  year = {2026},
  volume = {39},
  number = {9},
  doi = {10.1002/nbm.70339}
}
Kostenlos starten →