EUVIMEDEUVIMED entdecken
Crossref

Fully Automated Approach for Diagnosis of Supraspinatus Tendon Tear on Shoulder MRI by Using Deep Learning

Jiufa Cui, Xiaona Xia, Jia Wang, Xirui Li, Mingqian Huang, Sheng Miao, Dapeng Hao, Jie Li

Academic Radiology · 2024-03 · 31 (3) · 994-1002

DOI: 10.1016/j.acra.2023.09.012 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Radiology, 2024-03. Verfasst von Jiufa Cui und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China (J.C., X.L., D.H., J.L.). Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 27 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RATIONALE AND OBJECTIVES: To explore the feasibility of applying deep learning (DL) approach to detect supraspinatus tendon (ST) tear on shoulder MRI by using arthroscopy as the reference standard. MATERIALS AND METHODS: In this retrospective study, a total of 431 participants from two different manufacturers and two centers was used to build and validate a DL-based ST tear detection system. The proposed system was developed by using U-Net networks to segment and isolate ST followed by a swin transformer architecture to determine the presence or absence of a ST tear. The Densnet101 and Resnet50 as classifiers were also evaluated. Three radiologists performed subjective diagnoses to obtain the diagnosis results. Receptor operating characteristics (ROC) curves, area under the curve (AUC), sensitivity, specificity, and accuracy were used to evaluate the diagnosis performance of the proposed system and radiologists. We also compared the model's performance to that of radiologists. RESULTS: The proposed ST tear detection system with the classification network adapted from swin transformer achieved an AUC of 0.986, an accuracy of 0.929, a sensitivity of 0.918, and a specificity of 0.940 for detecting a ST tear, indicating high overall diagnostic accuracy. No statistically significant disparities in diagnostic efficacy were observed between the proposed ST tear detection system and musculoskeletal radiologist. CONCLUSION: The proposed ST tear detection system exhibits a diagnostic performance on par with that of seasoned clinical radiologist.

Schlagwörter

Stichwörter der Autor:innen

Deep learningMRISupraspinatus tendon

Autor:innen und Institutionen

  • Department of Radiology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China (J.C., X.L., D.H., J.L.).
  • Department of Radiology, Shandong University, Cheeloo College of Medicine, Qilu Hospital, Qingdao, Shandong, China (X.X.).
  • Department of Abdominal Ultrasound, Qingdao Women and Children's Hospital, Qingdao, Shandong, China (J.W.).
  • Department of Radiology, the Mount Sinai hospital, New York, New York, USA (M.H.).
  • School of Information and Control Engineering, Qingdao University of Technology, Qingdao, Shandong, China (S.M.).
  • Department of Radiology, the Affiliated Hospital of Qingdao University, Qingdao, Shandong, China (J.C., X.L., D.H., J.L.). Electronic address: lijie7737@qdu.edu.cn.

Zitieren

APA

Cui, J., Xia, X., Wang, J., Li, X., Huang, M., Miao, S., Hao, D., & Li, J. (2024). Fully Automated Approach for Diagnosis of Supraspinatus Tendon Tear on Shoulder MRI by Using Deep Learning. Academic Radiology, 31(3), 994-1002. https://doi.org/10.1016/j.acra.2023.09.012

Vancouver

Cui J, Xia X, Wang J, Li X, Huang M, Miao S, et al. Fully Automated Approach for Diagnosis of Supraspinatus Tendon Tear on Shoulder MRI by Using Deep Learning. Academic Radiology. 2024;31(3):994-1002. doi:10.1016/j.acra.2023.09.012

BibTeX
@article{Cui2024,
  author = {Cui, Jiufa and Xia, Xiaona and Wang, Jia and Li, Xirui and Huang, Mingqian and Miao, Sheng and Hao, Dapeng and Li, Jie},
  title = {Fully Automated Approach for Diagnosis of Supraspinatus Tendon Tear on Shoulder MRI by Using Deep Learning},
  journal = {Academic Radiology},
  year = {2024},
  volume = {31},
  number = {3},
  pages = {994--1002},
  doi = {10.1016/j.acra.2023.09.012}
}
Kostenlos starten →