EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images

Mengqi Li iD, Jingchao Fang, Haonan Hou, Li Yuan iD, Jin Guo, Zhenlong Liu

Bioengineering · 21.02.2025 · 12 (3) · 218

DOI: 10.3390/bioengineering12030218 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 21.02.2025. Verfasst von Mengqi Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Sports Medicine, Peking University Third Hospital, Institute of Sports Medicine of Peking University, Beijing 100191, China. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Haidian Innovation Transformation Special Science and Technology R&D, Beijing Natural Science Foundation, Science and Technology Innovation Project of the State General Administration of Sports.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper proposes an AI-based diagnostic method using MRI images for rotator cuff injuries to assist in treatment by segmenting tear areas and assessing tear severity. A multi-model deep learning network based on Unet + FPN architecture was developed to automatically segment rotator cuff injury images and determine tear grades. A dataset of 376 patients with 5640 images was used for training, with an additional 94 patients and 1410 images reserved for testing. To optimize segmentation, a tailored matching strategy was applied, achieving an Intersection over Union (IoU) of 0.79 ± 0.01 and a Dice coefficient of 0.75 ± 0.01, indicating high accuracy in segmenting tear areas. For tear severity indicators, the accuracy of estimating retraction (ER) reached 0.92 ± 0.02, and the accuracy of estimating stop tear width (ESTW) reached 0.79 ± 0.01. As the first AI algorithm specifically developed for diagnosing rotator cuff injuries, this platform demonstrates promising accuracy in both tear segmentation and severity assessment, aiming to support doctors in providing efficient, accurate diagnoses of rotator cuff tears.

Schlagwörter

Stichwörter der Autor:innen

AI segmentationMRIdeep learningmulti-model mechanismrotator cuff injury

Autor:innen und Institutionen

  • Department of Sports Medicine, Peking University Third Hospital, Institute of Sports Medicine of Peking University, Beijing 100191, China.
  • School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China.
  • Department of Radiology, Peking University Third Hospital, Beijing 100191, China.
  • Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, Beijing 100083, China.
  • Beijing Key Laboratory of Sports Injuries, Beijing 100191, China.
  • Engineering Research Center of Sports Trauma Treatment Technology and Devices, Ministry of Education, Beijing 100191, China.

ORCID-Profile: Mengqi Li, Li Yuan

Förderung

  • Haidian Innovation Transformation Special Science and Technology R&D
  • Beijing Natural Science Foundation
  • Science and Technology Innovation Project of the State General Administration of Sports
  • Haidian Innovation Transformation Special Science and Technology R&D

Zitieren

APA

Li, M., Fang, J., Hou, H., Yuan, L., Guo, J., & Liu, Z. (2025). Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images. Bioengineering, 12(3), 218. https://doi.org/10.3390/bioengineering12030218

Vancouver

Li M, Fang J, Hou H, Yuan L, Guo J, Liu Z. Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images. Bioengineering. 2025;12(3):218. doi:10.3390/bioengineering12030218

BibTeX
@article{Li2025,
  author = {Li, Mengqi and Fang, Jingchao and Hou, Haonan and Yuan, Li and Guo, Jin and Liu, Zhenlong},
  title = {Multi-Model Segmentation Algorithm for Rotator Cuff Injury Based on MRI Images},
  journal = {Bioengineering},
  year = {2025},
  volume = {12},
  number = {3},
  pages = {218},
  doi = {10.3390/bioengineering12030218}
}
Kostenlos starten →