Automatic Contouring of Spinal Vertebrae on X-Ray using a Novel Sandwich U-Net Architecture

TL;DR

This paper introduces a novel 'sandwich' U-Net architecture with dual activation functions for improved automatic segmentation of thoracic vertebrae on X-ray images, significantly enhancing accuracy over traditional models.

Contribution

The study presents a new U-Net variation with a unique sandwich structure and dual activation functions, achieving better segmentation accuracy for vertebral contouring.

Findings

4.1% Dice score improvement over baseline U-Net

Enhanced segmentation accuracy for thoracic vertebrae

Reliable automatic vertebral contour extraction

Abstract

In spinal vertebral mobility disease, accurately extracting and contouring vertebrae is essential for assessing mobility impairments and monitoring variations during flexion-extension movements. Precise vertebral contouring plays a crucial role in surgical planning; however, this process is traditionally performed manually by radiologists or surgeons, making it labour-intensive, time-consuming, and prone to human error. In particular, mobility disease analysis requires the individual contouring of each vertebra, which is both tedious and susceptible to inconsistencies. Automated methods provide a more efficient alternative, enabling vertebra identification, segmentation, and contouring with greater accuracy and reduced time consumption. In this study, we propose a novel U-Net variation designed to accurately segment thoracic vertebrae from anteroposterior view on X-Ray images. Our proposed approach, incorporating a ``sandwich" U-Net structure with dual activation functions, achieves a 4.1\% improvement in Dice score compared to the baseline U-Net model, enhancing segmentation accuracy while ensuring reliable vertebral contour extraction.