EUVIMEDEUVIMED entdecken
Crossref

Multi-parameter scoliosis evaluation from dual-view x-rays via a local sine-based projection model

Xianbin Wang, Guobao Ma, Zhenrui Wu, Wenzheng Ding iD, Honglian Xiong, Mingyi Wang

Physics in Medicine & Biology · 14.08.2026 · 71 (15) · 155009

DOI: 10.1088/1361-6560/ae8ca3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physics in Medicine & Biology, online erschienen am 03.08.2026. Verfasst von Xianbin Wang und 5 weiteren Autor:innen. Beteiligte Einrichtung: The First Affiliated Hospital of Heilongjiang University of Traditional Chinese Medicine, Harbin, People's Republic of China. Hauptthemen laut MEDLINE: Scoliosis, Image Processing, Computer-Assisted. Die Arbeit nennt 32 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective . To develop a robust and accurate multi-parameter assessment framework for adolescent idiopathic scoliosis based on spinal x-ray images, overcoming the limitations of traditional Cobb angle (CA)-based evaluation. Approach . We proposed a dual-view labeling protocol and employed a Residual U-Net architecture to segment vertebral bodies in 700 paired anteroposterior and lateral x-rays. A novel Local Sine-based Spinal Projection Model was introduced to calculate vertebral inclination angles and derive consecutive CAs. Additional spinal parameters, including coronal balance (T1PL-CSVL), force line (FL), and FL balance, were computed to enable comprehensive spinal evaluation. Main results . The proposed method achieved a vertebral segmentation Dice coefficient of 94.7%. The mean absolute error of the CA was 2.71 ∘ , outperforming the minimum bounding rectangle method ( 3.46 ∘ ) and novice manual measurements ( 5.40 ∘ ), with an intraclass correlation coefficient of 0.958. In diagnostic grading, 120 out of 142 patients were correctly classified (84.5% success rate). Longitudinal follow-up demonstrated accurate tracking of structural improvements and coronal balance recovery following conservative treatment. Significance . This approach enables automatic, precise, and comprehensive scoliosis evaluation by integrating fine-grained segmentation with geometric modeling of spinal curvature. The proposed method improves spinal assessment accuracy and facilitates longitudinal scoliosis monitoring, offering substantial clinical utility and impact in computer-aided orthopedic diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ScoliosisImage Processing, Computer-AssistedHumansRadiographyAdolescent

Stichwörter der Autor:innen

deep learning segmentationdual-view x-raylocal sine modelmulti-parameter assessmentscoliosis

Autor:innen und Institutionen

  • The First Affiliated Hospital of Heilongjiang University of Traditional Chinese Medicine, Harbin, People's Republic of China.
  • School of Physics and Optoelectronic Engineering, Foshan University, Foshan, People's Republic of China.

ORCID-Profile: Wenzheng Ding

Förderung

  • National Natural Science Foundation of China
  • Guangdong Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology

Zitieren

APA

Wang, X., Ma, G., Wu, Z., Ding, W., Xiong, H., & Wang, M. (2026). Multi-parameter scoliosis evaluation from dual-view x-rays via a local sine-based projection model. Physics in Medicine & Biology, 71(15), 155009. https://doi.org/10.1088/1361-6560/ae8ca3

Vancouver

Wang X, Ma G, Wu Z, Ding W, Xiong H, Wang M. Multi-parameter scoliosis evaluation from dual-view x-rays via a local sine-based projection model. Physics in Medicine & Biology. 2026;71(15):155009. doi:10.1088/1361-6560/ae8ca3

BibTeX
@article{Wang2026,
  author = {Wang, Xianbin and Ma, Guobao and Wu, Zhenrui and Ding, Wenzheng and Xiong, Honglian and Wang, Mingyi},
  title = {Multi-parameter scoliosis evaluation from dual-view x-rays via a local sine-based projection model},
  journal = {Physics in Medicine & Biology},
  year = {2026},
  volume = {71},
  number = {15},
  pages = {155009},
  doi = {10.1088/1361-6560/ae8ca3}
}
Kostenlos starten →