Morphology-, Noise-, and Resolution-Robust Ultrasound Elasticity Imaging with Fourier Neural Operators

TL;DR

This paper demonstrates that Fourier neural operators can robustly and accurately estimate tissue stiffness from ultrasound displacement data across various challenging scenarios, aiding clinical translation.

Contribution

The study introduces the application of Fourier neural operators to ultrasound elasticity imaging, showing superior robustness and generalization over existing deep learning models in simulated scenarios.

Findings

FNO outperforms U-Net and DeepONet in accuracy and generalization.

FNO maintains robustness under noise and resolution variations.

Validated effectiveness through comprehensive in silico simulations.

Abstract

Ultrasound-based elasticity imaging is a non-invasive technique for estimating tissue stiffness fields from displacement fields obtained by comparing ultrasound signals before and after compression. While recent deep learning approaches have enabled faster and more accurate elasticity estimation compared to traditional methods, several challenges remain for clinical translation. In this study, we employ finite element simulations of free-hand palpation to investigate the applicability of the Fourier neural operator (FNO). Four practical scenarios were investigated: (1) prediction across diverse lesion morphologies, (2) generalization to cases with lesion counts differing from those in the training data, (3) robustness to noise in measured displacement fields, and (4) resilience to variations in ultrasound device resolution. Across these tasks, FNO consistently outperformed baseline models such as U-Net and DeepONet in predictive accuracy and generalization, while maintaining robustness under noise and resolution changes. Validated through in silico simulations, these findings demonstrate the potential of FNO as a framework that could facilitate translation of elasticity imaging toward clinical practice.