EUVIMEDEUVIMED entdecken
Crossref

Fully automated pedicle screw manufacturer identification in plain radiograph with deep learning methods

Rattapoom Waranusast, Panomkhawn Riyamongkol, Santi Weerakul, Nattharut Chaibhuddanugul, Artit Laoruengthana, Akaworn Mahatthanatrakul

European Spine Journal · 2025

DOI: 10.1007/s00586-025-09167-3 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Spine Journal, 2025. Verfasst von Rattapoom Waranusast und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Faculty of Engineering, Naresuan University, Phitsanulok, Thailand. Hauptthemen laut MEDLINE: Pedicle Screws, Deep Learning, Radiography, Spinal Fusion. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Faculty of Medicine, Naresuan University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION: Pedicle screw manufacturer identification is crucial for revision surgery planning; however, this information is occasionally unavailable. We developed a deep learning-based algorithm to identify the pedicle screw manufacturer from plain radiographs. METHODS: We collected anteroposterior (AP) and lateral radiographs from 276 patients who had thoracolumbar spine surgery with pedicle screws from three international manufacturers. The samples were randomly assigned to training sets (178), validation sets (40), and test sets (58). The algorithm incorporated a convolutional neural network (CNN) model to classify the radiograph as AP and lateral, followed by YOLO object detection to locate the pedicle screw. Another CNN classifier model then identified the manufacturer of each pedicle screw in AP and lateral views. The voting scheme determined the final classification. For comparison, two spine surgeons independently evaluated the same test set, and the accuracy was compared. RESULTS: The mean age of the patients was 59.5 years, with 1,887 pedicle screws included. The algorithm achieved a perfect accuracy of 100% for the AP radiograph, 98.9% for the lateral radiograph, and 100% when both views were considered. By comparison, the spine surgeons achieved 97.1% accuracy. Statistical analysis revealed near-perfect agreement between the algorithm and the surgeons. CONCLUSION: We have successfully developed an algorithm for pedicle screw manufacturer identification, which demonstrated excellent accuracy and was comparable to experienced spine surgeons.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pedicle ScrewsDeep LearningRadiographySpinal FusionThoracic VertebraeLumbar VertebraeHumansMiddle AgedMaleFemaleAgedAlgorithmsNeural Networks, ComputerAdult

Stichwörter der Autor:innen

Computer-Assisted radiographic image interpretationDeep learningMachine learningPedicle screw

Autor:innen und Institutionen

  • Department of Electrical and Computer Engineering, Faculty of Engineering, Naresuan University, Phitsanulok, Thailand.
  • Department of Orthopaedics,Faculty of Medicine, Naresuan University, Phitsanulok, Thailand.
  • Department of Orthopaedics,Faculty of Medicine, Naresuan University, Phitsanulok, Thailand. akawornm@nu.ac.th.

Förderung

  • Faculty of Medicine, Naresuan University

Zitieren

APA

Waranusast, R., Riyamongkol, P., Weerakul, S., Chaibhuddanugul, N., Laoruengthana, A., & Mahatthanatrakul, A. (2025). Fully automated pedicle screw manufacturer identification in plain radiograph with deep learning methods. European Spine Journal. https://doi.org/10.1007/s00586-025-09167-3

Vancouver

Waranusast R, Riyamongkol P, Weerakul S, Chaibhuddanugul N, Laoruengthana A, Mahatthanatrakul A. Fully automated pedicle screw manufacturer identification in plain radiograph with deep learning methods. European Spine Journal. 2025. doi:10.1007/s00586-025-09167-3

BibTeX
@article{Waranusast2025,
  author = {Waranusast, Rattapoom and Riyamongkol, Panomkhawn and Weerakul, Santi and Chaibhuddanugul, Nattharut and Laoruengthana, Artit and Mahatthanatrakul, Akaworn},
  title = {Fully automated pedicle screw manufacturer identification in plain radiograph with deep learning methods},
  journal = {European Spine Journal},
  year = {2025},
  doi = {10.1007/s00586-025-09167-3}
}
Kostenlos starten →