Orientation-guided Graph Convolutional Network for Bone Surface Segmentation

TL;DR

This paper introduces an orientation-guided graph convolutional network that enhances bone surface segmentation in ultrasound images by improving connectivity and topology accuracy, crucial for surgical guidance.

Contribution

The paper proposes a novel orientation-guided graph convolutional network with orientation supervision to improve bone surface segmentation connectivity.

Findings

Achieved 5.01% improvement in connectivity metric over state-of-the-art methods.

Validated on 1042 in vivo ultrasound scans of various bones.

Enhanced segmentation accuracy in challenging ultrasound imaging conditions.

Abstract

Due to imaging artifacts and low signal-to-noise ratio in ultrasound images, automatic bone surface segmentation networks often produce fragmented predictions that can hinder the success of ultrasound-guided computer-assisted surgical procedures. Existing pixel-wise predictions often fail to capture the accurate topology of bone tissues due to a lack of supervision to enforce connectivity. In this work, we propose an orientation-guided graph convolutional network to improve connectivity while segmenting the bone surface. We also propose an additional supervision on the orientation of the bone surface to further impose connectivity. We validated our approach on 1042 vivo US scans of femur, knee, spine, and distal radius. Our approach improves over the state-of-the-art methods by 5.01% in connectivity metric.