Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Graph Neural Networks for modelling breast biomechanical compression

Hadeel Awwad, Eloy García, Robert Martí

TL;DR

This work proposes to explore Physics-based Graph Neural Networks (PhysGNN) for breast compression simulation and presents the first investigation of their potential in predicting breast deformation during mammographic compression, showing promise for accurate, rapid breast deformation approximations.

Abstract

Breast compression simulation is essential for accurate image registration from 3D modalities to X-ray procedures like mammography. It accounts for tissue shape and position changes due to compression, ensuring precise alignment and improved analysis. Although Finite Element Analysis (FEA) is reliable for approximating soft tissue deformation, it struggles with balancing accuracy and computational efficiency. Recent studies have used data-driven models trained on FEA results to speed up tissue deformation predictions. We propose to explore Physics-based Graph Neural Networks (PhysGNN) for breast compression simulation. PhysGNN has been used for data-driven modelling in other domains, and this work presents the first investigation of their potential in predicting breast deformation during mammographic compression. Unlike conventional data-driven models, PhysGNN, which incorporates mesh structural information and enables inductive learning on unstructured grids, is well-suited for capturing complex breast tissue geometries. Trained on deformations from incremental FEA simulations, PhysGNN's performance is evaluated by comparing predicted nodal displacements with those from finite element (FE) simulations. This deep learning (DL) framework shows promise for accurate, rapid breast deformation approximations, offering enhanced computational efficiency for real-world scenarios.

Graph Neural Networks for modelling breast biomechanical compression

TL;DR

This work proposes to explore Physics-based Graph Neural Networks (PhysGNN) for breast compression simulation and presents the first investigation of their potential in predicting breast deformation during mammographic compression, showing promise for accurate, rapid breast deformation approximations.

Abstract

Breast compression simulation is essential for accurate image registration from 3D modalities to X-ray procedures like mammography. It accounts for tissue shape and position changes due to compression, ensuring precise alignment and improved analysis. Although Finite Element Analysis (FEA) is reliable for approximating soft tissue deformation, it struggles with balancing accuracy and computational efficiency. Recent studies have used data-driven models trained on FEA results to speed up tissue deformation predictions. We propose to explore Physics-based Graph Neural Networks (PhysGNN) for breast compression simulation. PhysGNN has been used for data-driven modelling in other domains, and this work presents the first investigation of their potential in predicting breast deformation during mammographic compression. Unlike conventional data-driven models, PhysGNN, which incorporates mesh structural information and enables inductive learning on unstructured grids, is well-suited for capturing complex breast tissue geometries. Trained on deformations from incremental FEA simulations, PhysGNN's performance is evaluated by comparing predicted nodal displacements with those from finite element (FE) simulations. This deep learning (DL) framework shows promise for accurate, rapid breast deformation approximations, offering enhanced computational efficiency for real-world scenarios.

Paper Structure

This paper contains 12 sections, 1 equation, 5 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Materials
  3. Methods
  4. Biomechanical Breast Model
  5. PhysGNN
  6. Voxelised Compressed Phantom Reconstruction
  7. PhysGNN Training Experiments
  8. Evaluation Metrics
  9. Results and Discussion
  10. Performance of PhysGNN Model
  11. Quantitative and Qualitative Analysis of Leave-one-deformation-out experiment
  12. Conclusion

Figures (5)

  • Figure 1: (a) Reconstructed dataset from breast CT gazi2015evolution. (b) Flow chart of the proposed method to simulate the breast compression using PhysGNN.
  • Figure 2: Overview of steps to set up and solve compressed breast geometry using FEA, then apply deformation to reposition and compress the breast phantom.
  • Figure 3: Architectural diagram of PhysGNN physgnn2022
  • Figure 4: Cross-sectional views of compressed digital phantoms from NiftySim and PhysGNN: (a) and (b) sagittal sections, (c) and (d) axial sections, (e) and (f) coronal sections
  • Figure 5: Output displacements (mm) of NiftySim and PhysGNN on the FE model