EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI

Kyu-Chong Lee iD, Yongwon Cho iD, Kyung-Sik Ahn iD, Hyun-Joon Park iD, Young-Shin Kang, Sungshin Lee, Dongmin Kim iD, Chang Ho Kang iD

Diagnostics · 19.10.2023 · 13 (20) · 3254

DOI: 10.3390/diagnostics13203254 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 19.10.2023. Verfasst von Kyu-Chong Lee und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Information and Communications Promotion Fund through the National IT Industry Promotion Agency (NIPA), funded by the Ministry of Science and ICT (MSIT), Repub…, Information and Communications Promotion Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aimed to develop a screening model for rotator cuff tear detection in all three planes of routine shoulder MRI using a deep neural network. A total of 794 shoulder MRI scans (374 men and 420 women; aged 59 ± 11 years) were utilized. Three musculoskeletal radiologists labeled the rotator cuff tear. The YOLO v8 rotator cuff tear detection model was then trained; training was performed with all imaging planes simultaneously and with axial, coronal, and sagittal images separately. The performances of the models were evaluated and compared using receiver operating curves and the area under the curve (AUC). The AUC was the highest when using all imaging planes (0.94; p < 0.05). Among a single imaging plane, the axial plane showed the best performance (AUC: 0.71), followed by the sagittal (AUC: 0.70) and coronal (AUC: 0.68) imaging planes. The sensitivity and accuracy were also the highest in the model with all-plane training (0.98 and 0.96, respectively). Thus, deep-learning-based automatic rotator cuff tear detection can be useful for detecting torn areas in various regions of the rotator cuff in all three imaging planes.

Schlagwörter

Stichwörter der Autor:innen

deep learningmagnetic resonance imagingrotator cuff tear

Autor:innen und Institutionen

  • Department of Radiology, Korea University Anam Hospital, Korea University College of Medicine, Seoul 02841, Republic of Korea.
  • Advanced Medical Imaging Institute, Korea University College of Medicine, Seoul 02841, Republic of Korea.
  • AI Center, Korea University Anam Hospital, Seoul 02841, Republic of Korea.
  • Institute for Healthcare Service Innovation, College of Medicine, Korea University, Seoul 02841, Republic of Korea.
  • JLK Inc., Seoul 06141, Republic of Korea.

ORCID-Profile: Kyu-Chong Lee, Yongwon Cho, Kyung-Sik Ahn, Hyun-Joon Park, Dongmin Kim, Chang Ho Kang

Förderung

  • Information and Communications Promotion Fund through the National IT Industry Promotion Agency (NIPA), funded by the Ministry of Science and ICT (MSIT), Repub…
  • Information and Communications Promotion Fund

Zitieren

APA

Lee, K. C., Cho, Y., Ahn, K. S., Park, H. J., Kang, Y. S., Lee, S., Kim, D., & Kang, C. H. (2023). Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI. Diagnostics, 13(20), 3254. https://doi.org/10.3390/diagnostics13203254

Vancouver

Lee KC, Cho Y, Ahn KS, Park HJ, Kang YS, Lee S, et al. Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI. Diagnostics. 2023;13(20):3254. doi:10.3390/diagnostics13203254

BibTeX
@article{Lee2023,
  author = {Lee, Kyu-Chong and Cho, Yongwon and Ahn, Kyung-Sik and Park, Hyun-Joon and Kang, Young-Shin and Lee, Sungshin and Kim, Dongmin and Kang, Chang Ho},
  title = {Deep-Learning-Based Automated Rotator Cuff Tear Screening in Three Planes of Shoulder MRI},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {20},
  pages = {3254},
  doi = {10.3390/diagnostics13203254}
}
Kostenlos starten →