EUVIMEDEUVIMED entdecken
Open Access

Automatic measurement of X-ray radiographic parameters based on cascaded HRNet model from the supraspinatus outlet radiographs

Yuwen Zheng iD, Yuhua Wu iD, Xiaofei Chen iD, Ping Wang iD, Fuwen Dong iD, Linyang He iD, Qing Su iD, Guohua Cheng iD, Chunyu Ma iD, Hongyan Yao iD, Sheng Zhou iD

Quantitative Imaging in Medicine and Surgery · 2025-02 · 15 (2) · 1425-1438

DOI: 10.21037/qims-24-1373 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Quantitative Imaging in Medicine and Surgery, 2025-02. Verfasst von Yuwen Zheng und 10 weiteren Autor:innen. Beteiligte Einrichtung: The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Rotator cuff injury is a common cause of shoulder pain. Precise and efficient measurement of morphological parameters is necessary in the clinical diagnosis and evaluation of shoulder disorders. However, manual measurement is a time-consuming and labor-intensive task, with low inter-observer reliability. The automatic measurement of radiographic parameters in supraspinatus outlet radiographs has not been reported yet. Thus, the objective of this study was to use a cascaded High-Resolution Net (HRNet) model based on deep learning (DL) algorithms to automatically measure morphological parameters from supraspinatus outlet radiographs and assess its performance. It was intended for use in early screening of patients with rotator cuff disease and to guide them to further consultation.

Methods

This cross-sectional study collected 1,668 supraspinatus outlet radiographs from the picture archiving and communication system of Gansu Provincial Hospital of Traditional Chinese Medicine and the Affiliated Hospital of Gansu University of Chinese Medicine. Among them, 521 images were provided for test datasets and 1,147 images were provided for a model training dataset and validation dataset. Landmarks were annotated for acromio-humeral interval (AHI), acromial tilt (AT), and 3 lines in Park's acromial classification (line huo-acrf, line acro-acro1, and line huo-acro1). R4 radiologist reviewed the means of 3 radiologists as a reference standard. Model performance was assessed by calculating the percentage of correct key points (PCK), intra-class correlation coefficients (ICCs), Pearson's correlation coefficients, mean absolute error, and root mean square error. The reliability of R1, R2, R3, AI with R4 and inter-observer reliability of R1, R2, and R3 for acromial morphology classification were assessed by Cohen's kappa coefficient.

Results

Within the 3-mm threshold, the PCK of the model ranged from 74% to 100%. Compared to the reference standard, the model had reliable measurement of AHI, AT, line huo-acrf, line acro-acro1, line huo-acro1 (ICC =0.73-0.94) and moderate reliability of acromial morphology classification (k=0.50-0.56).

Conclusions

The cascaded HRNet developed in this study can automatically measure morphological parameters of the shoulder. It may aid early clinical screening for shoulder disorders and assist physicians in treatment decisions.

Schlagwörter

Stichwörter der Autor:innen

Deep learning (DL)automatic measurementradiographic parametershoulder

Autor:innen und Institutionen

  • The First Clinical Medical College of Gansu University of Chinese Medicine, Lanzhou, China.
  • Xi'an Hospital of Traditional Chinese Medicine, Xi'an, China.
  • Department of Radiology, Gansu Provincial Hospital of Traditional Chinese Medicine, Lanzhou, China.
  • Department of Radiology, Gansu Provincial Hospital, Lanzhou, China.
  • Hangzhou Jianpei Technology Company Ltd., Hangzhou, China.

ORCID-Profile: Yuwen Zheng, Yuhua Wu, Xiaofei Chen, Ping Wang, Fuwen Dong, Linyang He, Qing Su, Guohua Cheng, Chunyu Ma, Hongyan Yao, Sheng Zhou

Zitieren

APA

Zheng, Y., Wu, Y., Chen, X., Wang, P., Dong, F., He, L., Su, Q., Cheng, G., Ma, C., Yao, H., & Zhou, S. (2025). Automatic measurement of X-ray radiographic parameters based on cascaded HRNet model from the supraspinatus outlet radiographs. Quantitative Imaging in Medicine and Surgery, 15(2), 1425-1438. https://doi.org/10.21037/qims-24-1373

Vancouver

Zheng Y, Wu Y, Chen X, Wang P, Dong F, He L, et al. Automatic measurement of X-ray radiographic parameters based on cascaded HRNet model from the supraspinatus outlet radiographs. Quantitative Imaging in Medicine and Surgery. 2025;15(2):1425-1438. doi:10.21037/qims-24-1373

BibTeX
@article{Zheng2025,
  author = {Zheng, Yuwen and Wu, Yuhua and Chen, Xiaofei and Wang, Ping and Dong, Fuwen and He, Linyang and Su, Qing and Cheng, Guohua and Ma, Chunyu and Yao, Hongyan and Zhou, Sheng},
  title = {Automatic measurement of X-ray radiographic parameters based on cascaded HRNet model from the supraspinatus outlet radiographs},
  journal = {Quantitative Imaging in Medicine and Surgery},
  year = {2025},
  volume = {15},
  number = {2},
  pages = {1425--1438},
  doi = {10.21037/qims-24-1373}
}
Kostenlos starten →