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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In this paper, we propose to train deep neural networks with biomechanicalsimulations, to predict the prostate motion encountered duringultrasound-guided interventions. In this application, unstructured points aresampled from segmented pre-operative MR images to represent the anatomicalregions of interest. The point sets are then assigned with point-specificmaterial properties and displacement loads, forming the un-ordered inputfeature vectors. An adapted PointNet can be trained to predict the nodaldisplacements, using finite element (FE) simulations as ground-truth data.Furthermore, a versatile bootstrap aggregating mechanism is validated toaccommodate the variable number of feature vectors due to different patientgeometries, comprised of a training-time bootstrap sampling and a modelaveraging inference. This results in a fast and accurate approximation to theFE solutions without requiring subject-specific solid meshing. Based on 160,000nonlinear FE simulations on clinical imaging data from 320 patients, wedemonstrate that the trained networks generalise to unstructured point setssampled directly from holdout patient segmentation, yielding a near real-timeinference and an expected error of 0.017 mm in predicted nodal displacement.

Prostate motion modelling using biomechanically-trained deep neural networks on unstructured nodes