Conference Papers Year : 2025

Deform Any Liver In Real-time

Abstract

This paper introduces Deform Any Liver (DAL), a realtime surrogate model designed to accurately predict any liver deformation, given a set of applied forces. DAL leverages a hypernetwork to condition a U-Net architecture on the liver shape, with the U-Net receiving the applied external forces as input to predict the resulting displacement field. This design enables the model to generalize across various patient geometries, overcoming the limitations of existing patient-specific approaches. The DAL model is trained, validated, and tested using real human liver geometries, employing finite element method (FEM) simulations to generate realistic deformation data. Our results demonstrate the model's effectiveness and adaptability in accurately predicting the deformation of various liver shapes.
Fichier principal
Vignette du fichier
Deform_Any_liver_in_real_time.pdf (858) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04834198 , version 1 (12-12-2024)

Licence

Identifiers

  • HAL Id : hal-04834198 , version 1

Cite

Sidaty EL HADRAMY, Nicolas Padoy, Stéphane Cotin. Deform Any Liver In Real-time. IEEE International Symposium on Biomedical Imaging (ISBI 2025), Apr 2025, Houston, United States. ⟨hal-04834198⟩
32 View
34 Download

Share

More