PADReg: Physics-Aware Deformable Registration Guided by Contact Force for Ultrasound Sequences

TL;DR

PADReg introduces a physics-aware ultrasound image registration method guided by contact force, improving alignment accuracy by incorporating biomechanical priors and physical modeling.

Contribution

The paper presents a novel deformable registration framework that uses contact force measurements and tissue stiffness modeling to enhance ultrasound image alignment.

Findings

Achieves 21.34% better HD95 accuracy than previous methods.

Utilizes contact force as a physical prior for more plausible registration.

Demonstrates effectiveness on in-vivo datasets.

Abstract

Ultrasound deformable registration estimates spatial transformations between pairs of deformed ultrasound images, which is crucial for capturing biomechanical properties and enhancing diagnostic accuracy in diseases such as thyroid nodules and breast cancer. However, ultrasound deformable registration remains highly challenging, especially under large deformation. The inherently low contrast, heavy noise and ambiguous tissue boundaries in ultrasound images severely hinder reliable feature extraction and correspondence matching. Existing methods often suffer from poor anatomical alignment and lack physical interpretability. To address the problem, we propose PADReg, a physics-aware deformable registration framework guided by contact force. PADReg leverages synchronized contact force measured by robotic ultrasound systems as a physical prior to constrain the registration. Specifically, instead of directly predicting deformation fields, we first construct a pixel-wise stiffness map utilizing the multi-modal information from contact force and ultrasound images. The stiffness map is then combined with force data to estimate a dense deformation field, through a lightweight physics-aware module inspired by Hooke's law. This design enables PADReg to achieve physically plausible registration with better anatomical alignment than previous methods relying solely on image similarity. Experiments on in-vivo datasets demonstrate that it attains a HD95 of 12.90, which is 21.34\% better than state-of-the-art methods. The source code is available at https://github.com/evelynskip/PADReg.