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

Modeling of brain tumor dynamics has the potential to advance therapeuticplanning. Current modeling approaches resort to numerical solvers that simulatethe tumor progression according to a given differential equation. Usinghighly-efficient numerical solvers, a single forward simulation takes up to afew minutes of compute. At the same time, clinical applications of tumormodeling often imply solving an inverse problem, requiring up to tens ofthousands forward model evaluations when used for a Bayesian modelpersonalization via sampling. This results in a total inference timeprohibitively expensive for clinical translation. While recent data-drivenapproaches become capable of emulating physics simulation, they tend to fail ingeneralizing over the variability of the boundary conditions imposed by thepatient-specific anatomy. In this paper, we propose a learnable surrogate forsimulating tumor growth which maps the biophysical model parameters directly tosimulation outputs, i.e. the local tumor cell densities, whilst respectingpatient geometry. We test the neural solver on Bayesian tumor modelpersonalization for a cohort of glioma patients. Bayesian inference using theproposed surrogate yields estimates analogous to those obtained by solving theforward model with a regular numerical solver. The near-real-time computationcost renders the proposed method suitable for clinical settings. The code isavailable at https://github.com/IvanEz/tumor-surrogate.

Geometry-aware neural solver for fast Bayesian calibration of brain tumor models