EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Graph Neural Networks in Medical Imaging: Methods, Applications and Future Directions

Ibomoiye Domor Mienye, Serestina Viriri

Information · 01.12.2025 · 16 (12) · 1051

DOI: 10.3390/info16121051 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 01.12.2025. Verfasst von Ibomoiye Domor Mienye und 1 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 109 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph neural networks (GNNs) extend deep learning to non-Euclidean domains, offering a robust framework for modeling the spatial, structural, and functional relationships inherent in medical imaging. This paper reviews recent progress in GNN architectures, including recurrent, convolutional, attention-based, autoencoding, and spatiotemporal designs, and examines how these models have been applied to core medical imaging tasks, such as segmentation, classification, registration, reconstruction, and multimodal fusion. The review further identifies current challenges and limitations in applying GNNs to medical imaging and discusses emerging trends, including graph–transformer integration, self-supervised graph learning, and federated GNNs. This paper provides a concise and comprehensive reference for advancing reliable and generalizable GNN-based medical imaging systems.

Zitieren

APA

Mienye, I. D., & Viriri, S. (2025). Graph Neural Networks in Medical Imaging: Methods, Applications and Future Directions. Information, 16(12), 1051. https://doi.org/10.3390/info16121051

Vancouver

Mienye ID, Viriri S. Graph Neural Networks in Medical Imaging: Methods, Applications and Future Directions. Information. 2025;16(12):1051. doi:10.3390/info16121051

BibTeX
@article{Mienye2025,
  author = {Mienye, Ibomoiye Domor and Viriri, Serestina},
  title = {Graph Neural Networks in Medical Imaging: Methods, Applications and Future Directions},
  journal = {Information},
  year = {2025},
  volume = {16},
  number = {12},
  pages = {1051},
  doi = {10.3390/info16121051}
}
Kostenlos starten →