EUVIMEDEUVIMED entdecken
Crossref

AV-NeXt: a topology-aware framework with interaction modeling and competitive gating for retinal artery/vein segmentation

Mingyang Sun, Xiaoyang He

Medical & Biological Engineering & Computing · 2026

DOI: 10.1007/s11517-026-03633-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2026. Verfasst von Mingyang Sun und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Dalian Polytechnic University, Qinggongyuan 1, Ganjingzi District, Liaoning, 116034, Dalian, China. Hauptthemen laut MEDLINE: Retinal Artery, Retinal Vein, Image Processing, Computer-Assisted. Die Arbeit nennt 31 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Automated segmentation and classification of retinal arteries and veins (A/V) are pivotal for the precise morphological characterization required in the early diagnosis of systemic cardiovascular and ophthalmic pathologies. However, existing deep learning paradigms exhibit limitations in resolving complex structural entanglement at A/V crossings, frequently resulting in vascular disconnection and classification ambiguity due to the insufficient modeling of local artery-vein interactions. To address these challenges, AV-NeXt, a topology-aware framework, is proposed to improve crossing-region recognition by integrating anatomically motivated A/V interaction modeling into deep feature representations. Constructed upon a ConvNeXt backbone, the framework incorporates two pivotal components: (1) an Interaction-conditioned Crossing Head, which exploits feature-level co-activation cues between artery and vein streams to assist crossing prediction; and (2) a Competitive Gating Mechanism, designed to dynamically reduce crossing-induced classification ambiguity through soft gating. Extensive experiments on Fundus-AVSeg demonstrated that AV-NeXt achieved the best overall performance among the compared methods, with an mDice of 76.72%, an mIoU of 63.64%, and a Crossing IoU of 44.85%. Paired statistical analysis further supported the reliability of the crossing-region gains, while zero-shot evaluation on RITE showed competitive crossing recognition under domain shift, with a Crossing IoU of 28.52%.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Retinal ArteryRetinal VeinImage Processing, Computer-AssistedHumansAlgorithmsDeep Learning

Stichwörter der Autor:innen

ConvNeXtMedical image analysisRetinal artery/vein segmentationTopology-aware learningZero-shot generalization

Autor:innen und Institutionen

  • School of Information Science and Engineering, Dalian Polytechnic University, Qinggongyuan 1, Ganjingzi District, Liaoning, 116034, Dalian, China.
  • School of Information Science and Engineering, Dalian Polytechnic University, Qinggongyuan 1, Ganjingzi District, Liaoning, 116034, Dalian, China. Hexy20260127@163.com.

Zitieren

APA

Sun, M., & He, X. (2026). AV-NeXt: a topology-aware framework with interaction modeling and competitive gating for retinal artery/vein segmentation. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-026-03633-w

Vancouver

Sun M, He X. AV-NeXt: a topology-aware framework with interaction modeling and competitive gating for retinal artery/vein segmentation. Medical & Biological Engineering & Computing. 2026. doi:10.1007/s11517-026-03633-w

BibTeX
@article{Sun2026,
  author = {Sun, Mingyang and He, Xiaoyang},
  title = {AV-NeXt: a topology-aware framework with interaction modeling and competitive gating for retinal artery/vein segmentation},
  journal = {Medical & Biological Engineering & Computing},
  year = {2026},
  doi = {10.1007/s11517-026-03633-w}
}
Kostenlos starten →