Soft Tissue Palpation using Graph Neural Networks
Soft tissue simulation is essential for surgical training, pre-operative planning and visuo-haptic interaction.
Physics-based methods can reproduce tissue deformation with high fidelity, but the numerous pre-processing steps and their computational cost limit interactive use.
We aim to predict soft tissue deformation and forces directly from surface points using Graph Neural Networks and advance towards meshless, simple, fast and generalizable surrogate models.
For more information about this project, please contact Madina Kojanazarova.
Downloads
Madina Kojanazarova
Georg Rauter
Philippe C. Cattin
- Conditional Graph Neural Network for Predicting Soft Tissue Deformation and Forces
- Soft Tissue Simulation and Force Estimation from Heterogeneous Structures using Equivariant Graph Neural Networks
- Generalizing Deformation and Force Prediction Across Material Stiffness and Geometry using Soft Tissue Phantoms - (accepted 2026)
MIRACLE project by Werner Siemens Foundation