EUVIMEDEUVIMED entdecken
Crossref

Spine X-ray image segmentation based on deep learning and marker controlled watershed

Yating Xiao, Yan Chen, Yong Zhang, Runjie Zhang, Guangyu Cui, Yufeng Song, Quan Zhang

Journal of X-Ray Science and Technology · 2025-01 · 33 (1) · 109-119

DOI: 10.1177/08953996241299998 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology, online erschienen am 19.12.2024. Verfasst von Yating Xiao und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Communication Engineering, North University of China, Taiyuan, Shanxi Province, China. Hauptthemen laut MEDLINE: Deep Learning, Spine, Image Processing, Computer-Assisted, Radiography. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 23 Literaturangaben. Gefördert von: Natural Science Foundation of Shanxi Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The development of automatic methods for vertebral segmentation provides the objective analysis of each vertebra in the spine image, which is important for the diagnosis of various spinal diseases. However, vertebrae have inter-class similarity and intra-class variability, and some adjacent vertebrae exhibit adhesion.

Objective

To solve the adhesion problem of adjacent vertebrae and ensure that the boundary between adjacent vertebrae can be accurately demarcated, we propose an image segmentation method based on deep learning and marker controlled watershed.

Methods

This method consists of a dual-path model of localization path and segmentation path to achieve automatic vertebral segmentation. For the vertebral localization path, a high-resolution network (HRNet) is used to locate vertebral center. Moreover, based on spine posture, a new bone direction loss (BD-Loss) is designed to constrain HRNet. For the vertebral segmentation path, we proposed a VU-Net network to achieve vertebral preliminary segmentation. Additionally, a position information perception module (PIPM) is introduced to realize the guidance of HRNet to VU-Net. Finally, we novelly use the outputs of HR-Net and VU-Net deep learning networks to initialize the marker controlled watershed algorithm to suppress the adhesion of adjacent vertebrae and achieve vertebral fine segmentation.

Results

The proposed method was evaluated on two spine X-ray datasets using four metrics. The first dataset contains sagittal images of the cervical spine, while the second dataset contains coronal images of the whole spine, both with different health conditions. Our method achieved Recall of 96.82% and 94.38%, Precision of 97.24% and 98.14%, Dice coefficient of 97.03% and 96.22%, Intersection over Union of 94.24% and 92.72% on the cervical spine and whole spine datasets respectively, outperforming current state-of-the-art techniques.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSpineImage Processing, Computer-AssistedRadiographyHumansAlgorithms

Stichwörter der Autor:innen

deep learningmarker controlled watershedspine X-ray imagevertebral localizationvertebral segmentation

Autor:innen und Institutionen

  • School of Information and Communication Engineering, North University of China, Taiyuan, Shanxi Province, China.
  • State Key Laboratory of Dynamic Testing Technology, North University of China, Taiyuan, China.
  • Second Hospital of Shanxi Medical University, Taiyuan, China.

Förderung

  • Natural Science Foundation of Shanxi Province

Zitieren

APA

Xiao, Y., Chen, Y., Zhang, Y., Zhang, R., Cui, G., Song, Y., & Zhang, Q. (2025). Spine X-ray image segmentation based on deep learning and marker controlled watershed. Journal of X-Ray Science and Technology, 33(1), 109-119. https://doi.org/10.1177/08953996241299998

Vancouver

Xiao Y, Chen Y, Zhang Y, Zhang R, Cui G, Song Y, et al. Spine X-ray image segmentation based on deep learning and marker controlled watershed. Journal of X-Ray Science and Technology. 2025;33(1):109-119. doi:10.1177/08953996241299998

BibTeX
@article{Xiao2025,
  author = {Xiao, Yating and Chen, Yan and Zhang, Yong and Zhang, Runjie and Cui, Guangyu and Song, Yufeng and Zhang, Quan},
  title = {Spine X-ray image segmentation based on deep learning and marker controlled watershed},
  journal = {Journal of X-Ray Science and Technology},
  year = {2025},
  volume = {33},
  number = {1},
  pages = {109--119},
  doi = {10.1177/08953996241299998}
}
Kostenlos starten →