EUVIMEDEUVIMED entdecken
Open Access

PelviNet: A Collaborative Multi-agent Convolutional Network for Enhanced Pelvic Image Registration

Rguibi Zakaria, Hajami Abdelmajid, Zitouni Dya, Allali Hakim

Journal of Imaging Informatics in Medicine · 2024

DOI: 10.1007/s10278-024-01249-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2024. Verfasst von Rguibi Zakaria und 3 weiteren Autor:innen. Beteiligte Einrichtung: LAVETE Laboratory, Hassan First University, Settat, Morocco. rguibi.fst@uhp.ac.ma. Hauptthemen laut MEDLINE: Pelvis, Image Processing, Computer-Assisted, Imaging, Three-Dimensional, Neural Networks, Computer. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PelviNet introduces a groundbreaking multi-agent convolutional network architecture tailored for enhancing pelvic image registration. This innovative framework leverages shared convolutional layers, enabling synchronized learning among agents and ensuring an exhaustive analysis of intricate 3D pelvic structures. The architecture combines max pooling, parametric ReLU activations, and agent-specific layers to optimize both individual and collective decision-making processes. A communication mechanism efficiently aggregates outputs from these shared layers, enabling agents to make well-informed decisions by harnessing combined intelligence. PelviNet's evaluation centers on both quantitative accuracy metrics and visual representations to elucidate agents' performance in pinpointing optimal landmarks. Empirical results demonstrate PelviNet's superiority over traditional methods, achieving an average image-wise error of 2.8 mm, a subject-wise error of 3.2 mm, and a mean Euclidean distance error of 3.0 mm. These quantitative results highlight the model's efficiency and precision in landmark identification, crucial for medical contexts such as radiation therapy, where exact landmark identification significantly influences treatment outcomes. By reliably identifying critical structures, PelviNet advances pelvic image analysis and offers potential enhancements for broader medical imaging applications, marking a significant step forward in computational healthcare.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PelvisImage Processing, Computer-AssistedImaging, Three-DimensionalNeural Networks, ComputerHumansTomography, X-Ray Computed

Stichwörter der Autor:innen

Medical image analysisMulti-agent reinforcement learningPelvic image registration

Autor:innen und Institutionen

  • LAVETE Laboratory, Hassan First University, Settat, Morocco. rguibi.fst@uhp.ac.ma.
  • LAVETE Laboratory, Hassan First University, Settat, Morocco.

Zitieren

APA

Zakaria, R., Abdelmajid, H., Dya, Z., & Hakim, A. (2024). PelviNet: A Collaborative Multi-agent Convolutional Network for Enhanced Pelvic Image Registration. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01249-w

Vancouver

Zakaria R, Abdelmajid H, Dya Z, Hakim A. PelviNet: A Collaborative Multi-agent Convolutional Network for Enhanced Pelvic Image Registration. Journal of Imaging Informatics in Medicine. 2024. doi:10.1007/s10278-024-01249-w

BibTeX
@article{Zakaria2024,
  author = {Zakaria, Rguibi and Abdelmajid, Hajami and Dya, Zitouni and Hakim, Allali},
  title = {PelviNet: A Collaborative Multi-agent Convolutional Network for Enhanced Pelvic Image Registration},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  doi = {10.1007/s10278-024-01249-w}
}
Kostenlos starten →