EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Soft Tissue Simulation and Force Estimation From Heterogeneous Structures Using Equivariant Graph Neural Networks

Madina Kojanazarova iD, Sidaty El Hadramy, Jack Wilkie, Georg Rauter, Philippe C Cattin iD

Healthcare Technology Letters · 2025-01 · 12 (1)

DOI: 10.1049/htl2.70042 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 06.12.2025. Verfasst von Madina Kojanazarova und 4 weiteren Autor:innen. Beteiligte Einrichtung: Center for Medical Image Analysis & Navigation, Department of Biomedical Engineering University of Basel Basel Switzerland. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Werner Siemens-Stiftung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurately simulating soft tissue deformation is crucial for surgical training, pre‐operative planning, and real‐time haptic feedback systems. While physics‐based models such as the finite element method (FEM) provide high‐fidelity results, they are often computationally expensive and require extensive preprocessing. We propose a graph neural network (GNN) architecture that predicts both tissue surface deformation and applied force from sparse point clouds. The model incorporates internal anatomical information through binary tissue profiles beneath each point and leverages E(n)‐equivariant message passing to improve robustness. We collected experimental data that comprises a real silicone and bone‐like phantom, and complemented it with synthetic simulations generated using FEM. Our model achieves a comparable performance to a baseline GNN on standard test cases and significantly outperforms it in rotated and cross‐resolution scenarios, showing a strong generalization to unseen orientations and point densities. It also achieves a significant speed improvement, offering a solution for real‐time applications. When fine‐tuned on experimental data, the model maintains sub‐millimeter deformation accuracy despite limited sample size and measurement noise. The results demonstrate that our approach offers an efficient, data‐driven alternative to traditional simulations, capable of generalizing across anatomical configurations and supporting interactive surgical environments.

Schlagwörter

Stichwörter der Autor:innen

biomechanicsfinite element analysislearning (artificial intelligence)medical roboticsneural netsvirtual reality

Autor:innen und Institutionen

  • Center for Medical Image Analysis & Navigation, Department of Biomedical Engineering University of Basel Basel Switzerland.
  • Bio-Inspired RObots for MEDicine-Laboratory (BIROMED-lab), Department of Biomedical Engineering University of Basel Basel Switzerland.
  • Institute for Technical Medicine Furtwangen University of Applied Sciences Schwenningen Germany.

ORCID-Profile: Madina Kojanazarova, Philippe C Cattin

Förderung

  • Werner Siemens-Stiftung

Zitieren

APA

Kojanazarova, M., Hadramy, S. E., Wilkie, J., Rauter, G., & Cattin, P. C. (2025). Soft Tissue Simulation and Force Estimation From Heterogeneous Structures Using Equivariant Graph Neural Networks. Healthcare Technology Letters, 12(1). https://doi.org/10.1049/htl2.70042

Vancouver

Kojanazarova M, Hadramy SE, Wilkie J, Rauter G, Cattin PC. Soft Tissue Simulation and Force Estimation From Heterogeneous Structures Using Equivariant Graph Neural Networks. Healthcare Technology Letters. 2025;12(1). doi:10.1049/htl2.70042

BibTeX
@article{Kojanazarova2025,
  author = {Kojanazarova, Madina and Hadramy, Sidaty El and Wilkie, Jack and Rauter, Georg and Cattin, Philippe C},
  title = {Soft Tissue Simulation and Force Estimation From Heterogeneous Structures Using Equivariant Graph Neural Networks},
  journal = {Healthcare Technology Letters},
  year = {2025},
  volume = {12},
  number = {1},
  doi = {10.1049/htl2.70042}
}
Kostenlos starten →