Skip to main content

Advertisement

SpringerLink
Log in

Measuring the critical shoulder angle on radiographs: an accurate and repeatable deep learning model

  • Scientific Article
  • Published:
Skeletal Radiology Aims and scope Submit manuscript

A Correction to this article was published on 05 April 2022

This article has been updated

Abstract

Purpose

Since the critical shoulder angle (CSA) is considered a risk factor for shoulder pathology and the intra- and inter-rater variabilities in its calculation are not negligible, we developed a deep learning model that calculates it automatically and accurately.

Methods

We used a dataset of 8467 anteroposterior x-ray images of the shoulder annotated with 3 landmarks of interest. A Convolutional Neural Network model coupled with a spatial to numerical transform (DSNT) layer was used to predict the landmark coordinates from which the CSA was calculated. The performances were evaluated by calculating the Euclidean distance between the ground truth coordinates and the predicted ones normalized with respect to the distance between the first and the second points, and the error between the CSA angle measured by a human observer and the predicted one.

Results

Regarding the normalized point distances, we obtained a median error of 2.9%, 2.5%, and 2% for the three points among the entire set. Considering CSA calculations, the median errors were 1° (standard deviation 1.2°), 0.88° (standard deviation 0.87°), and 0.99° (standard deviation 1°) for angles below 30°, between 30° and 35°, and above 35°, respectively.

Discussion

These results demonstrate that the model has the potential to be used in clinical settings where the replicability is important. The reported standard error of the CSA measurement is greater than 2° that is above the median error of our model, indicating a potential accuracy sufficient to be used in a clinical setting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Availability of data and materials

The images are confidential. The other data and software are available from the corresponding author upon reasonable request.

Change history

References

  1. Moor BK, Bouaicha S, Rothenfluh DA, Sukthankar A, Gerber C. Is there an association between the individual anatomy of the scapula and the development of rotator cuff tears or osteoarthritis of the glenohumeral joint? A radiological study of the critical shoulder angle. Bone Jt J. 2013;95 B(7):935–41.

    Article  Google Scholar 

  2. Rose-Reneau Z, Moorefield AK, Schirmer D, Ismailov E, Downing R, Wright BW. The critical shoulder angle as a diagnostic measure for osteoarthritis and rotator cuff pathology. Cureus. 2020;12(11):e11447.

    PubMed  PubMed Central  Google Scholar 

  3. Viehöfer AF, Snedeker JG, Baumgartner D, Gerber C. Glenohumeral joint reaction forces increase with critical shoulder angles representative of osteoarthritis - a biomechanical analysis. J Orthop Res. 2016;34(6):1047–52.

    Article  Google Scholar 

  4. Tauber M, Habermeyer P, Zumbansen N, Martetschläger F. Lateral acromioplasty for correction of the critical shoulder angle. Obere Extrem. 2020;15(3):228–32.

    Article  Google Scholar 

  5. Spiegl UJ, Horan MP, Smith SW, Ho CP, Millett PJ. The critical shoulder angle is associated with rotator cuff tears and shoulder osteoarthritis and is better assessed with radiographs over MRI. Knee Surgery, Sport Traumatol Arthrosc. 2016;24(7):2244–51.

    Article  Google Scholar 

  6. Galbusera F, Bassani T, Costa F, Brayda-Bruno M, Zerbi A, Wilke HJ. Artificial neural networks for the recognition of vertebral landmarks in the lumbar spine. Comput Methods Biomech Biomed Eng Imaging Vis. 2018;6(4):447–52.

    Article  Google Scholar 

  7. Chung SW, Han SS, Lee JW, Oh K-S, Kim NR, Yoon JP, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89(4):468–73.

    Article  PubMed Central  Google Scholar 

  8. He Z, Morgan S, Prendergast L. Numerical coordinate regression with convolutional neural networks. 2018. arXiv preprint arXiv:1801.07372.

  9. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. pp. 1–9.

  10. Galbusera F, Niemeyer F, Joachim H, Tito W, Gloria B, Carla C, et al. Fully automated radiological analysis of spinal disorders and deformities : a deep learning approach. Eur Spine J. 2019;28(5):951–60.

    Article  Google Scholar 

  11. Cina A, Bassani T, Panico M, Luca A, Masharawi Y, Bruno MB, et al. 2 - step deep learning model for landmarks localization in spine radiographs. Sci Rep. 2021;0123456789:1–12.

    Google Scholar 

  12. Paszke A, Gross S, Massa F, Lerer A, Bradbury J, Chanan G, et al. PyTorch: an imperative style, high-performance deep learning library. NeurIPS. 2019. p. 32.

  13. Urban G, Porhemmat S, Stark M, Feeley B, Okada K, Baldi P. Classifying shoulder implants in X-ray images using deep learning. Comput Struct Biotechnol J. 2020;18:967–72.

    Article  PubMed Central  Google Scholar 

  14. Shim E, Kim JY, Yoon JP, Ki S-Y, Lho T, Kim Y, et al. Automated rotator cuff tear classification using 3D convolutional neural network. Sci Rep. 2020;10(1):15632.

    Article  CAS  PubMed Central  Google Scholar 

  15. Taghizadeh E, Truffer O, Becce F, Eminian S, Gidoin S, Terrier A, et al. Deep learning for the rapid automatic quantification and characterization of rotator cuff muscle degeneration from shoulder CT datasets. Eur Radiol. 2021;31(1):181–90.

    Article  Google Scholar 

  16. Medina G, Buckless CG, Thomasson E, Oh LS, Torriani M. Deep learning method for segmentation of rotator cuff muscles on MR images. Skeletal Radiol. 2021;50(4):683–92.

    Article  Google Scholar 

  17. Cantarelli Rodrigues T, Deniz CM, Alaia EF, Gorelik N, Babb JS, Dublin J, et al. Three-dimensional MRI bone models of the glenohumeral joint using deep learning: evaluation of normal anatomy and glenoid bone loss. Radiol Artif Intell. 2020;2(5):e190116.

    Article  PubMed Central  Google Scholar 

Download references

Funding

The study was funded by the Italian Ministry of Health (“Ricerca Corrente”).

Author information

Authors and Affiliations

  1. Department of Biomedical Sciences, Humanitas University, Via Rita Levi Montalcini 4, Pieve Emanuele, 20090, Milan, Italy

    Marco Minelli & Alessandro Castagna

  2. IRCCS Istituto Ortopedico Galeazzi, Via Riccardo Galeazzi 4, 20161, Milan, Italy

    Andrea Cina, Fabio Galbusera & Luca Maria Sconfienza

  3. Shoulder and Elbow Unit, Department of Orthopedic and Trauma Surgery, Humanitas Clinical and Research Center, IRCCS, via Manzoni 56, Rozzano, 20089, Milan, Italy

    Alessandro Castagna

  4. Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Via Manzoni 56, 20089, Milan, Italy

    Victor Savevski

  5. Dipartimento Di Scienze Biomediche Per La Salute, Università Degli Studi Di Milano, Via Pascal, 36, 20133, Milan, Italy

    Luca Maria Sconfienza

Authors
  1. Marco Minelli
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andrea Cina
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fabio Galbusera
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alessandro Castagna
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Victor Savevski
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Luca Maria Sconfienza
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Marco Minelli.

Ethics declarations

Ethics approval

This retrospective study was approved by our Institutional Review Board.

Consent to participate

All images were fully anonymized and all subjects gave informed consent for participation.

Consent for publication

All subjects gave informed consent for scientific use of the data including publication of results.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

The original version of this article was revised. Luca Maria Sconfienza’s affiliations should be 2 and 5.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Minelli, M., Cina, A., Galbusera, F. et al. Measuring the critical shoulder angle on radiographs: an accurate and repeatable deep learning model. Skeletal Radiol 51, 1873–1878 (2022). https://doi.org/10.1007/s00256-022-04041-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00256-022-04041-5

Keywords

Search

Navigation