Unsupervised Deformable Image Registration for Respiratory Motion Compensation in Ultrasound Images

TL;DR

This paper introduces U-RAFT, an unsupervised deep learning model that accurately tracks pixel movement in ultrasound images to compensate for respiratory motion, achieving significant motion reduction in porcine lung videos.

Contribution

The paper presents a novel unsupervised recurrent all-pairs field transforms (U-RAFT) model for deformable ultrasound image registration, enabling real-time respiratory motion compensation.

Findings

Achieved 76% reduction in pixel movement in porcine lung ultrasound videos.

Demonstrated real-time processing at approximately 30 Hz.

Showed potential for motion compensation in deformable tissues.

Abstract

In this paper, we present a novel deep-learning model for deformable registration of ultrasound images and an unsupervised approach to training this model. Our network employs recurrent all-pairs field transforms (RAFT) and a spatial transformer network (STN) to generate displacement fields at online rates (apprx. 30 Hz) and accurately track pixel movement. We call our approach unsupervised recurrent all-pairs field transforms (U-RAFT). In this work, we use U-RAFT to track pixels in a sequence of ultrasound images to cancel out respiratory motion in lung ultrasound images. We demonstrate our method on in-vivo porcine lung videos. We show a reduction of 76% in average pixel movement in the porcine dataset using respiratory motion compensation strategy. We believe U-RAFT is a promising tool for compensating different kinds of motions like respiration and heartbeat in ultrasound images of deformable tissue.