Shape Completion and Real-Time Visualization in Robotic Ultrasound Spine Acquisitions

TL;DR

This paper presents a real-time robotic ultrasound system that uses deep learning-based shape completion to improve spinal visualization during ultrasound-guided procedures, enhancing accuracy and reproducibility.

Contribution

It introduces an integrated robotic ultrasound system with real-time shape completion, enabling autonomous spine imaging and improved visualization without reliance on preoperative CT scans.

Findings

High accuracy in shape completion on phantom data

Effective real-time visualization during spine scans

Potential for improved clinical navigation

Abstract

Ultrasound (US) imaging is increasingly used in spinal procedures due to its real-time, radiation-free capabilities; however, its effectiveness is hindered by shadowing artifacts that obscure deeper tissue structures. Traditional approaches, such as CT-to-US registration, incorporate anatomical information from preoperative CT scans to guide interventions, but they are limited by complex registration requirements, differences in spine curvature, and the need for recent CT imaging. Recent shape completion methods can offer an alternative by reconstructing spinal structures in US data, while being pretrained on large set of publicly available CT scans. However, these approaches are typically offline and have limited reproducibility. In this work, we introduce a novel integrated system that combines robotic ultrasound with real-time shape completion to enhance spinal visualization. Our robotic platform autonomously acquires US sweeps of the lumbar spine, extracts vertebral surfaces from ultrasound, and reconstructs the complete anatomy using a deep learning-based shape completion network. This framework provides interactive, real-time visualization with the capability to autonomously repeat scans and can enable navigation to target locations. This can contribute to better consistency, reproducibility, and understanding of the underlying anatomy. We validate our approach through quantitative experiments assessing shape completion accuracy and evaluations of multiple spine acquisition protocols on a phantom setup. Additionally, we present qualitative results of the visualization on a volunteer scan.