English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Correctly capturing intraoperative brain shift in image-guided neurosurgicalprocedures is a critical task for aligning preoperative data withintraoperative geometry for ensuring accurate surgical navigation. While thefinite element method (FEM) is a proven technique to effectively approximatesoft tissue deformation through biomechanical formulations, their degree ofsuccess boils down to a trade-off between accuracy and speed. To circumventthis problem, the most recent works in this domain have proposed leveragingdata-driven models obtained by training various machine learning algorithms --e.g., random forests, artificial neural networks (ANNs) -- with the results offinite element analysis (FEA) to speed up tissue deformation approximations byprediction. These methods, however, do not account for the structure of thefinite element (FE) mesh during training that provides information on nodeconnectivities as well as the distance between them, which can aid withapproximating tissue deformation based on the proximity of force load pointswith the rest of the mesh nodes. Therefore, this work proposes a novelframework, PhysGNN, a data-driven model that approximates the solution of theFEM by leveraging graph neural networks (GNNs), which are capable of accountingfor the mesh structural information and inductive learning over unstructuredgrids and complex topological structures. Empirically, we demonstrate that theproposed architecture, PhysGNN, promises accurate and fast soft tissuedeformation approximations, and is competitive with the state-of-the-art (SOTA)algorithms while promising enhanced computational feasibility, thereforesuitable for neurosurgical settings.

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