EUVIMEDEUVIMED entdecken
Crossref

Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT

Jianan Chen, Song Liu, Yong Li, Zaoqiang Zhang, Nianchun Liao, Huihong Shi, Wenjun Hu, Youxi Lin, Yanbo Chen, Bo Gao, Dongsheng Huang, Anjing Liang und 1 weitere

European Spine Journal · 2025

DOI: 10.1007/s00586-024-08623-w ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Spine Journal, 2025. Verfasst von Jianan Chen und 12 weiteren Autor:innen. Beteiligte Einrichtung: Sun Yat-Sen Memorial Hospital Department of Orthopedics, Guangzhou, China. Hauptthemen laut MEDLINE: Deep Learning, Spinal Fractures, Lumbar Vertebrae, Thoracic Vertebrae. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Guangdong Medical Research Foundation, Science and Technology Program of Guangzhou, Sun Yat-sen Scientific Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To develop a deep learning system for automatic segmentation of compression fracture vertebral bodies on thoracolumbar CT and differentiate between fresh and old fractures. METHODS: We included patients with thoracolumbar fractures treated at our Hospital South Campus from January 2020 to December 2023, with prospective validation from January to June 2024, and used data from the North Campus from January to December 2023 for external validation. Fresh fractures were defined as back pain lasting less than 4 weeks, with MRI showing bone marrow edema (BME). We utilized a 3D V-Net for image segmentation and several ResNet and DenseNet models for classification, evaluating performance with ROC curves, accuracy, sensitivity, specificity, precision, F1 score, and AUC. The optimal model was selected to construct deep learning system and its diagnostic efficacy was compared with that of two clinicians. RESULTS: The training dataset included 238 vertebras (man/women: 55/183; age: 72.11 ± 11.55), with 59 in internal validation (man/women: 13/46; age: 74.76 ± 8.96), 34 in external validation, and 48 in prospective validation. The 3D V-Net model achieved a DSC of 0.90 on the validation dataset. ResNet18 performed best among classification models, with an AUC of 0.96 in validation, 0.89 in external dataset, and 0.87 in prospective validation, surpassing the two clinicians in both external and prospective validations. CONCLUSION: The deep learning model can automatically and accurately segment the vertebral bodies with compression fractures and classify them as fresh or old fractures, thereby assisting clinicians in making clinical decisions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningSpinal FracturesLumbar VertebraeThoracic VertebraeTomography, X-Ray ComputedFractures, CompressionHumansFemaleAgedMaleAged, 80 and overMiddle AgedProspective Studies

Stichwörter der Autor:innen

Deep learningFracture classificationSegmentationVertebral compression fractures

Autor:innen und Institutionen

  • Sun Yat-Sen Memorial Hospital Department of Orthopedics, Guangzhou, China.
  • Sun Yat-Sen Memorial Hospital Department of Radiology, Guangzhou, China.
  • Sun Yat-Sen Memorial Hospital Department of Orthopedics, Guangzhou, China. hdongsh@mail.sysu.edu.cn.
  • Sun Yat-Sen Memorial Hospital Department of Orthopedics, Guangzhou, China. lianganj@mail.sysu.edu.cn.
  • Sun Yat-Sen Memorial Hospital Department of Orthopedics, Guangzhou, China. gaowj7@mail.sysu.edu.cn.

Förderung

  • Guangdong Medical Research Foundation
  • Science and Technology Program of Guangzhou
  • Sun Yat-sen Scientific Research Project
  • National Natural Science Foundation of China

Zitieren

APA

Chen, J., Liu, S., Li, Y., Zhang, Z., Liao, N., Shi, H., Hu, W., Lin, Y., Chen, Y., Gao, B., Huang, D., Liang, A., & Gao, W. (2025). Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT. European Spine Journal. https://doi.org/10.1007/s00586-024-08623-w

Vancouver

Chen J, Liu S, Li Y, Zhang Z, Liao N, Shi H, et al. Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT. European Spine Journal. 2025. doi:10.1007/s00586-024-08623-w

BibTeX
@article{Chen2025,
  author = {Chen, Jianan and Liu, Song and Li, Yong and Zhang, Zaoqiang and Liao, Nianchun and Shi, Huihong and Hu, Wenjun and Lin, Youxi and Chen, Yanbo and Gao, Bo and Huang, Dongsheng and Liang, Anjing and Gao, Wenjie},
  title = {Deep learning model for automated detection of fresh and old vertebral fractures on thoracolumbar CT},
  journal = {European Spine Journal},
  year = {2025},
  doi = {10.1007/s00586-024-08623-w}
}
Kostenlos starten →