EUVIMEDEUVIMED entdecken
Crossref

AME-Net++: adaptive mixture-of-experts for intelligent intraoperative 3D reconstruction

Shi-Qi Liu, You-Jun Zhang, Xiao-Liang Xie, Lin-Sen Zhang, Xiao-Hu Zhou, Xi-Yao Ma, Zeng-Guang Hou, Xin-Kai Qu

Intelligence & Robotics · 05.11.2026 · 6 (4) · 891-918

DOI: 10.20517/ir.2026.39 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Intelligence & Robotics, online erschienen am 05.11.2026. Verfasst von Shi-Qi Liu und 7 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In minimally invasive vascular interventions, intraoperative 3D vascular reconstruction and accurate spatial characterization are crucial for safe and precise robotic surgical navigation. However, unlike conventional supervised learning tasks that rely on a fixed training/testing split, projection-based neural reconstruction aims to establish a patient-specific mapping between sparse X-ray observations and the corresponding 3D spatial representation. In this paper, we propose AME-Net++, an Adaptive Mixture-of-Experts Network that integrates feature perception, adaptive expert collaboration, and multi-scale optimization for 3D structural reconstruction from intraoperative multi-view X-ray projections. Specifically, AME-Net++ employs an adaptive feature-preservation strategy to suppress projection noise while preserving the geometric continuity of vascular structures. To address heterogeneous tissue attenuation and region-dependent structural variations, we design a parallel mixture-of-experts architecture with a learnable routing mechanism that dynamically assigns local features to appropriate expert subnetworks for region-adaptive, fine-grained representation learning. In addition, we propose a multi-scale information-aware composite loss function to jointly optimize global structural fidelity, local density consistency, and edge-detail preservation. Experimental results on both public datasets and our self-built animal interventional vascular dataset demonstrate that AME-Net++ achieves strong performance in both 2D projection synthesis and 3D voxel reconstruction tasks. Additional validation on this dataset shows that the reconstructed vascular centerline has an average error of 1.5 ± 0.67 mm, indicating that the proposed method can preserve the major vascular trajectory with clinically meaningful spatial accuracy. These results validate the effectiveness of the proposed reconstruction method and indicate its potential for 3D navigation in vascular interventional procedures.

Zitieren

APA

Liu, S., Zhang, Y., Xie, X., Zhang, L., Zhou, X., Ma, X., Hou, Z., & Qu, X. (2026). AME-Net++: adaptive mixture-of-experts for intelligent intraoperative 3D reconstruction. Intelligence & Robotics, 6(4), 891-918. https://doi.org/10.20517/ir.2026.39

Vancouver

Liu S, Zhang Y, Xie X, Zhang L, Zhou X, Ma X, et al. AME-Net++: adaptive mixture-of-experts for intelligent intraoperative 3D reconstruction. Intelligence & Robotics. 2026;6(4):891-918. doi:10.20517/ir.2026.39

BibTeX
@article{Liu2026,
  author = {Liu, Shi-Qi and Zhang, You-Jun and Xie, Xiao-Liang and Zhang, Lin-Sen and Zhou, Xiao-Hu and Ma, Xi-Yao and Hou, Zeng-Guang and Qu, Xin-Kai},
  title = {AME-Net++: adaptive mixture-of-experts for intelligent intraoperative 3D reconstruction},
  journal = {Intelligence & Robotics},
  year = {2026},
  volume = {6},
  number = {4},
  pages = {891--918},
  doi = {10.20517/ir.2026.39}
}
Kostenlos starten →