EUVIMEDEUVIMED entdecken
Crossref

DC-YOLOv5-based target detection algorithm for cervical vertebral maturation

Man Jiang, Yun Hu, Jianxia Li, Huanzhuo Zhao, Tianci Zhang, Xiang Li, Leilei Zheng

Physical and Engineering Sciences in Medicine · 2024-09 · 47 (3) · 1277-1290

DOI: 10.1007/s13246-024-01432-x ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical and Engineering Sciences in Medicine, online erschienen am 12.08.2024. Verfasst von Man Jiang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Stomatological Hospital, Chongqing Medical University, No.426 Songshibei Road, Yubei District, Chongqing, 401147, China. Hauptthemen laut MEDLINE: Cervical Vertebrae, Algorithms. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Chongqing Talent Program, Chongqing Medical Scientific Research Project, Chongqing Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The cervical vertebral maturation (CVM) method is essential to determine the timing of orthodontic and orthopedic treatment. In this paper, a target detection model called DC-YOLOv5 is proposed to achieve fully automated detection and staging of CVM. A total of 1800 cephalometric radiographs were labeled and categorized based on the CVM stages. We introduced a model named DC-YOLOv5, optimized for the specific characteristics of CVM based on YOLOv5. This optimization includes replacing the original bounding box regression loss calculation method with Wise-IOU to address the issue of mutual interference between vertical and horizontal losses in Complete-IOU (CIOU), which made model convergence challenging. We incorporated the Res-dcn-head module structure to enhance the focus on small target features, improving the model's sensitivity to subtle sample differences. Additionally, we introduced the Convolutional Block Attention Module (CBAM) dual-channel attention mechanism to enhance focus and understanding of critical features, thereby enhancing the accuracy and efficiency of target detection. Loss functions, precision, recall, mean average precision (mAP), and F1 scores were used as the main algorithm evaluation metrics to assess the performance of these models. Furthermore, we attempted to analyze regions important for model predictions using gradient Class Activation Mapping (CAM) techniques. The final F1 scores of the DC-YOLOv5 model for CVM identification were 0.993, 0.994 for mAp0.5 and 0.943 for mAp0.5:0.95, with faster convergence, more accurate and more robust detection than the other four models. The DC-YOLOv5 algorithm shows high accuracy and robustness in CVM identification, which provides strong support for fast and accurate CVM identification and has a positive effect on the development of medical field and clinical diagnosis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cervical VertebraeAlgorithmsHumansImage Processing, Computer-AssistedCephalometryChild

Stichwörter der Autor:innen

Bone ageCephalometric radiographsCervical vertebral maturation assessmentTarget detectionYOLOv5

Autor:innen und Institutionen

  • Department of Stomatological Hospital, Chongqing Medical University, No.426 Songshibei Road, Yubei District, Chongqing, 401147, China.
  • Chongqing Key Laboratory of Oral Diseases and Biomedical Sciences, Chongqing, China.
  • Chongqing Municipal Key Laboratory of Oral Biomedical Engineering of Higher Education, Chongqing, China.
  • Department of Stomatological Hospital, Chongqing Medical University, No.426 Songshibei Road, Yubei District, Chongqing, 401147, China. zhengleileicqmu@hospital.cqmu.edu.cn.
  • Chongqing Key Laboratory of Oral Diseases and Biomedical Sciences, Chongqing, China. zhengleileicqmu@hospital.cqmu.edu.cn.
  • Chongqing Municipal Key Laboratory of Oral Biomedical Engineering of Higher Education, Chongqing, China. zhengleileicqmu@hospital.cqmu.edu.cn.

Förderung

  • Chongqing Talent Program
  • Chongqing Medical Scientific Research Project
  • Chongqing Medical University

Zitieren

APA

Jiang, M., Hu, Y., Li, J., Zhao, H., Zhang, T., Li, X., & Zheng, L. (2024). DC-YOLOv5-based target detection algorithm for cervical vertebral maturation. Physical and Engineering Sciences in Medicine, 47(3), 1277-1290. https://doi.org/10.1007/s13246-024-01432-x

Vancouver

Jiang M, Hu Y, Li J, Zhao H, Zhang T, Li X, et al. DC-YOLOv5-based target detection algorithm for cervical vertebral maturation. Physical and Engineering Sciences in Medicine. 2024;47(3):1277-1290. doi:10.1007/s13246-024-01432-x

BibTeX
@article{Jiang2024,
  author = {Jiang, Man and Hu, Yun and Li, Jianxia and Zhao, Huanzhuo and Zhang, Tianci and Li, Xiang and Zheng, Leilei},
  title = {DC-YOLOv5-based target detection algorithm for cervical vertebral maturation},
  journal = {Physical and Engineering Sciences in Medicine},
  year = {2024},
  volume = {47},
  number = {3},
  pages = {1277--1290},
  doi = {10.1007/s13246-024-01432-x}
}
Kostenlos starten →