Feature-aggregated spatiotemporal spine surface estimation for wearable patch ultrasound volumetric imaging

TL;DR

This paper introduces a novel spatiotemporal U-Net based method that uses feature aggregation from a wearable patch ultrasound device to accurately estimate vertebra surfaces, aiding ultrasound-guided interventions.

Contribution

It presents a new approach combining handcrafted features and deep learning for 3D spine surface estimation using wearable ultrasound, improving accuracy over baseline methods.

Findings

Significant accuracy improvement over baseline methods

Effective surface estimation on spine phantom data

Potential for augmented reality guided interventions

Abstract

Clear identification of bone structures is crucial for ultrasound-guided lumbar interventions, but it can be challenging due to the complex shapes of the self-shadowing vertebra anatomy and the extensive background speckle noise from the surrounding soft tissue structures. Therefore, we propose to use a patch-like wearable ultrasound solution to capture the reflective bone surfaces from multiple imaging angles and create 3D bone representations for interventional guidance. In this work, we will present our method for estimating the vertebra bone surfaces by using a spatiotemporal U-Net architecture learning from the B-Mode image and aggregated feature maps of hand-crafted filters. The methods are evaluated on spine phantom image data collected by our proposed miniaturized wearable "patch" ultrasound device, and the results show that a significant improvement on baseline method can be achieved with promising accuracy. Equipped with this surface estimation framework, our wearable ultrasound system can potentially provide intuitive and accurate interventional guidance for clinicians in augmented reality setting.