Automatic segmentation of vertebral features on ultrasound spine images using Stacked Hourglass Network

TL;DR

This paper presents an automatic method using a Stacked Hourglass Network to accurately segment vertebral features on ultrasound images and measure spinal deformity parameters, showing high accuracy and correlation with radiographs.

Contribution

The study introduces a novel deep learning approach for automatic segmentation of vertebral landmarks on ultrasound images, enabling reliable SPA measurement.

Findings

High segmentation accuracy with 86.8% PCK

SPA measurements from ultrasound correlated well with radiographs (r>0.85)

Mean absolute difference in SPA measurement was 3.3°

Abstract

Objective: The spinous process angle (SPA) is one of the essential parameters to denote three-dimensional (3-D) deformity of spine. We propose an automatic segmentation method based on Stacked Hourglass Network (SHN) to detect the spinous processes (SP) on ultrasound (US) spine images and to measure the SPAs of clinical scoliotic subjects. Methods: The network was trained to detect vertebral SP and laminae as five landmarks on 1200 ultrasound transverse images and validated on 100 images. All the processed transverse images with highlighted SP and laminae were reconstructed into a 3D image volume, and the SPAs were measured on the projected coronal images. The trained network was tested on 400 images by calculating the percentage of correct keypoints (PCK); and the SPA measurements were evaluated on 50 scoliotic subjects by comparing the results from US images and radiographs. Results: The trained network achieved a high average PCK (86.8%) on the test datasets, particularly the PCK of SP detection was 90.3%. The SPAs measured from US and radiographic methods showed good correlation (r>0.85), and the mean absolute differences (MAD) between two modalities were 3.3{\deg}, which was less than the clinical acceptance error (5{\deg}). Conclusion: The vertebral features can be accurately segmented on US spine images using SHN, and the measurement results of SPA from US data was comparable to the gold standard from radiography.