PhysGNN: A Physics--Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image--Guided NeurosurgeryDownload PDF

Published: 31 Oct 2022, Last Modified: 16 Jan 2023NeurIPS 2022 AcceptReaders: Everyone
Keywords: PhysGNN, Physics-Driven, Graph Neural Network, Tissue Deformation, Image-Guided Systems, GraphSAGE, GraphConv, Jumping Knowledge, Physical Simulation, Mechanical Simulation, Finite Element Method, Finite Element Analysis
TL;DR: PhysGNN is a novel physics-driven graph neural network based model capable of accurately and efficiently approximating tissue deformation caused by applied forces by which 94-97% of errors are shown to be less than 1 mm–the precision in neurosurgery.
Abstract: Correctly capturing intraoperative brain shift in image-guided neurosurgical procedures is a critical task for aligning preoperative data with intraoperative geometry for ensuring accurate surgical navigation. While the finite element method (FEM) is a proven technique to effectively approximate soft tissue deformation through biomechanical formulations, their degree of success boils down to a trade-off between accuracy and speed. To circumvent this problem, the most recent works in this domain have proposed leveraging data-driven models obtained by training various machine learning algorithms---e.g., random forests, artificial neural networks (ANNs)---with the results of finite element analysis (FEA) to speed up tissue deformation approximations by prediction. These methods, however, do not account for the structure of the finite element (FE) mesh during training that provides information on node connectivities as well as the distance between them, which can aid with approximating tissue deformation based on the proximity of force load points with the rest of the mesh nodes. Therefore, this work proposes a novel framework, PhysGNN, a data-driven model that approximates the solution of the FEM by leveraging graph neural networks (GNNs), which are capable of accounting for the mesh structural information and inductive learning over unstructured grids and complex topological structures. Empirically, we demonstrate that the proposed architecture, PhysGNN, promises accurate and fast soft tissue deformation approximations, and is competitive with the state-of-the-art (SOTA) algorithms while promising enhanced computational feasibility, therefore suitable for neurosurgical settings.
Supplementary Material: pdf
9 Replies

Loading