EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Spinal x-ray based scoliosis diagnosis using deep learning: a comparison of YOLOv11 and ResNet

Hongbo Zhang, Jialong Qi, Zhidong Zhang

Biomedical Engineering / Biomedizinische Technik · 2026

DOI: 10.1515/bmt-2026-0192 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, 2026. Verfasst von Hongbo Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: First Clinical Medical College, Anhui Medical University, Hefei, China. Hauptthemen laut MEDLINE: Scoliosis, Deep Learning, Spine, Radiography. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To develop and evaluate an automated deep learning framework for scoliosis detection from spinal radiographs and to compare the performance of a single-stage YOLOv11-based approach with a two-stage ROI-guided ResNet model.

Methods

A publicly available spinal X-ray dataset was analyzed for key radiographic features, including spinal alignment, lateral curvature, vertebral asymmetry, and overall spinal contour. Two automated strategies were compared: a YOLOv11-based framework for spinal region detection and direct classification, and a two-stage approach in which the spinal region of interest was first localized using bounding box regression and then classified with ResNet.

Results

The YOLOv11-based framework outperformed the ROI-based ResNet approach in distinguishing scoliosis from non-scoliosis radiographs. It captured scoliosis-related deformity patterns more effectively and demonstrated stronger diagnostic stability across representative cases.

Conclusions

The YOLOv11-based framework demonstrated superior performance over the two-stage ResNet strategy for automated scoliosis recognition and may serve as a useful adjunct for radiographic screening.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ScoliosisDeep LearningSpineRadiographyHumansConvolutional Neural NetworksX-RaysDetection Algorithms

Stichwörter der Autor:innen

automated screeningradiographic featuresscoliosisspinal curvaturespinal radiographyvertebral asymmetry

Autor:innen und Institutionen

  • First Clinical Medical College, Anhui Medical University, Hefei, China.
  • Department of Spine, Third Affiliated Hospital of Anhui Medical University, Hefei, China.

Zitieren

APA

Zhang, H., Qi, J., & Zhang, Z. (2026). Spinal x-ray based scoliosis diagnosis using deep learning: a comparison of YOLOv11 and ResNet. Biomedical Engineering / Biomedizinische Technik. https://doi.org/10.1515/bmt-2026-0192

Vancouver

Zhang H, Qi J, Zhang Z. Spinal x-ray based scoliosis diagnosis using deep learning: a comparison of YOLOv11 and ResNet. Biomedical Engineering / Biomedizinische Technik. 2026. doi:10.1515/bmt-2026-0192

BibTeX
@article{Zhang2026,
  author = {Zhang, Hongbo and Qi, Jialong and Zhang, Zhidong},
  title = {Spinal x-ray based scoliosis diagnosis using deep learning: a comparison of YOLOv11 and ResNet},
  journal = {Biomedical Engineering / Biomedizinische Technik},
  year = {2026},
  doi = {10.1515/bmt-2026-0192}
}
Kostenlos starten →