Skip to main content

Advertisement

SpringerLink
Log in

Classification of rotator cuff tears in ultrasound images using deep learning models

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Rotator cuff tears (RCTs) are one of the most common shoulder injuries, which are typically diagnosed using relatively expensive and time-consuming diagnostic imaging tests such as magnetic resonance imaging or computed tomography. Deep learning algorithms are increasingly used to analyze medical images, but they have not been used to identify RCTs with ultrasound images. The aim of this study is to develop an approach to automatically classify RCTs and provide visualization of tear location using ultrasound images and convolutional neural networks (CNNs). The proposed method was developed using transfer learning and fine-tuning with five pre-trained deep models (VGG19, InceptionV3, Xception, ResNet50, and DenseNet121). The Bayesian optimization method was also used to optimize hyperparameters of the CNN models. A total of 194 ultrasound images from Kosin University Gospel Hospital were used to train and test the CNN models by five-fold cross-validation. Among the five models, DenseNet121 demonstrated the best classification performance with 88.2% accuracy, 93.8% sensitivity, 83.6% specificity, and AUC score of 0.832. A gradient-weighted class activation mapping (Grad-CAM) highlighted the sensitive features in the learning process on ultrasound images. The proposed approach demonstrates the feasibility of using deep learning and ultrasound images to assist RCTs’ diagnosis.

Graphical abstract

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
Fig. 6

Similar content being viewed by others

Abbreviations

AUC:

Area under the curve

CNN:

Convolution neural network

CT:

Computed tomography

DL:

Deep learning

FN:

False negative

FP:

False positive

Grad-CAM:

Gradient-weighted class activation mapping

MRI:

Magnetic resonance imaging

RCTs:

Rotator cuff tears

ROC:

Receiver operating characteristic

TN:

True negative

TP:

True positive

References

  1. Via AG, De Cupis M, Spoliti M, Oliva F (2013) Clinical and biological aspects of rotator cuff tears. Muscles Ligaments Tendons J. 3(2):70–9. https://doi.org/10.11138/mltj/2013.3.2.070.

  2. Craig R, Holt T, Rees JL (2017) Acute rotator cuff tears. BMJ 11(359):j5366. https://doi.org/10.1136/bmj.j5366

    Article  Google Scholar 

  3. Goutallier D, Postel JM, Bernageau J, Lavau L, Voisin MC (1994) Fatty muscle degeneration in cuff ruptures. Pre- and postoperative evaluation by CT scan. Clin Orthop Relat Res 304:78–83. https://doi.org/10.1097/00003086-199407000-00014

  4. Lapner PL, Jiang L, Zhang T, Athwal GS (2015) Rotator cuff fatty infiltration and atrophy are associated with functional outcomes in anatomic shoulder arthroplasty. Clin Orthop Relat Res 473(2):674–682. https://doi.org/10.1007/s11999-014-3963-5

    Article  PubMed  Google Scholar 

  5. Gladstone JN, Bishop JY, Lo IK, Flatow EL (2007) Fatty infiltration and atrophy of the rotator cuff do not improve after rotator cuff repair and correlate with poor functional outcome. Am J Sports Med 35(5):719–728. https://doi.org/10.1177/0363546506297539

    Article  PubMed  Google Scholar 

  6. Donohue KW, Ricchetti ET, Ho JC, Iannotti JP (2018) The association between rotator cuff muscle fatty infiltration and glenoid morphology in glenohumeral osteoarthritis. J Bone Joint Surg Am. 100(5):381–7. https://doi.org/10.2106/JBJS.17.00232

    Article  PubMed  Google Scholar 

  7. Thomazeau H, Rolland Y, Lucas C, Duval JM, Langlais F (1996) Atrophy of the supraspinatus belly. Assessment by MRI in 55 patients with rotator cuff pathology. Acta Orthop Scand 67(3):264–8. https://doi.org/10.3109/17453679608994685

    Article  CAS  PubMed  Google Scholar 

  8. van de Sande MA, Stoel BC, Obermann WR, Tjong a Lieng JG, Rozing PM. (2005) Quantitative assessment of fatty degeneration in rotator cuff muscles determined with computed tomography. Invest Radiol 40(5):313–319. https://doi.org/10.1097/01.rli.0000160014.16577.86

    Article  PubMed  Google Scholar 

  9. Oh JH, Kim SH, Choi JA, Kim Y, Oh CH (2010) Reliability of the grading system for fatty degeneration of rotator cuff muscles. Clin Orthop Relat Res 468(6):1558–1564. https://doi.org/10.1007/s11999-009-0818-6

    Article  PubMed  Google Scholar 

  10. Slabaugh MA, Friel NA, Karas V, Romeo AA, Verma NN, Cole BJ (2012) Interobserver and intraobserver reliability of the Goutallier classification using magnetic resonance imaging: proposal of a simplified classification system to increase reliability. Am J Sports Med 40(8):1728–1734. https://doi.org/10.1177/0363546512452714

    Article  PubMed  Google Scholar 

  11. McElvany MD, McGoldrick E, Gee AO, Neradilek MB, Matsen FA 3rd (2015) Rotator cuff repair: published evidence on factors associated with repair integrity and clinical outcome. Am J Sports Med 43(2):491–500. https://doi.org/10.1177/0363546514529644

    Article  PubMed  Google Scholar 

  12. Terrier A, Ston J, Dewarrat A, Becce F, Farron A (2017) A semi-automated quantitative CT method for measuring rotator cuff muscle degeneration in shoulders with primary osteoarthritis. Orthop Traumatol Surg Res 103(2):151–157. https://doi.org/10.1016/j.otsr.2016.12.006

    Article  CAS  PubMed  Google Scholar 

  13. Park J, Kim S, Lim JK, Jin KN, Yang MS, Chae KJ et al (1985) (2021) Quantitative CT image-based structural and functional changes during asthma acute exacerbations. J Appl Physiol 131(3):1056–1066. https://doi.org/10.1152/japplphysiol.00743.2020

    Article  Google Scholar 

  14. Yoon S, Tam TM, Rajaraman PK, Lin CL, Tawhai M, Hoffman EA et al (1985) (2020) An integrated 1D breathing lung simulation with relative hysteresis of airway structure and regional pressure for healthy and asthmatic human lungs. J Appl Physiol 129(4):732–747. https://doi.org/10.1152/japplphysiol.00176.2020

    Article  Google Scholar 

  15. Klibanov AL, Hossack JA (2015) Ultrasound in radiology: from anatomic, functional, molecular imaging to drug delivery and image-guided therapy. Invest Radiol 50(9):657–670. https://doi.org/10.1097/RLI.0000000000000188

    Article  PubMed  PubMed Central  Google Scholar 

  16. Grassi W, Filippucci E, Busilacchi P (2004) Musculoskeletal ultrasound. Best Pract Res Clin Rheumatol 18(6):813–826. https://doi.org/10.1016/j.berh.2004.05.001

    Article  PubMed  Google Scholar 

  17. Tan A (2003) Imaging of the musculoskeletal system: magnetic resonance imaging, ultrasonography and computed tomography. Best Pract Res Clin Rheumatol 17(3):513–528. https://doi.org/10.1016/s1521-6942(03)00021-4

    Article  PubMed  Google Scholar 

  18. Saraya S, El Bakry R (2016) Ultrasound: can it replace MRI in the evaluation of the rotator cuff tears? Egypt J Radiol Nucl Med 47(1):193–201. https://doi.org/10.1016/j.ejrnm.2015.11.010

    Article  Google Scholar 

  19. de Jesus JO, Parker L, Frangos AJ, Nazarian LN (2009) Accuracy of MRI, MR arthrography, and ultrasound in the diagnosis of rotator cuff tears: a meta-analysis. AJR Am J Roentgenol 192(6):1701–1707. https://doi.org/10.2214/AJR.08.1241

    Article  PubMed  Google Scholar 

  20. Hashimoto F, Kakimoto A, Ota N, Ito S, Nishizawa S (2019) Automated segmentation of 2D low-dose CT images of the psoas-major muscle using deep convolutional neural networks. Radiol Phys Technol 12(2):210–215. https://doi.org/10.1007/s12194-019-00512-y

    Article  PubMed  Google Scholar 

  21. Weber KA, Smith AC, Wasielewski M, Eghtesad K, Upadhyayula PA, Wintermark M et al (2019) Deep learning convolutional neural networks for the automatic quantification of muscle fat infiltration following whiplash injury. Sci Rep 9(1):7973. https://doi.org/10.1038/s41598-019-44416-8

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  22. Burns JE, Yao J, Chalhoub D, Chen JJ, Summers RM (2020) A machine learning algorithm to estimate sarcopenia on abdominal CT. Acad Radiol 27(3):311–320. https://doi.org/10.1016/j.acra.2019.03.011

    Article  PubMed  Google Scholar 

  23. Graffy PM, Liu J, Pickhardt PJ, Burns JE, Yao J, Summers RM (2019) Deep learning-based muscle segmentation and quantification at abdominal CT: application to a longitudinal adult screening cohort for sarcopenia assessment. Br J Radiol 92(1100):20190327. https://doi.org/10.1259/bjr.20190327

    Article  PubMed  PubMed Central  Google Scholar 

  24. Shim E, Kim JY, Yoon JP, Ki SY, Lho T, Kim Y et al (2020) Automated rotator cuff tear classification using 3D convolutional neural network. Sci Rep 10(1):15632. https://doi.org/10.1038/s41598-020-72357-0

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  25. Kim M, Park Hm, Kim JY, Kim SH, Hoeke S, Neve WD (2020) MRI-based diagnosis of rotator cuff tears using deep learning and weighted linear combinations. In: Proceedings of the 5th Machine Learning for Healthcare Conference. 292–308

  26. Lu HY, Huang CY, Su CT, Lin CC (2014) Predicting rotator cuff tears using data mining and Bayesian likelihood ratios. PLoS ONE 9(4):e94917. https://doi.org/10.1371/journal.pone.0094917

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  27. Brock KK, Mutic S, McNutt TR, Li H, Kessler ML (2017) Use of image registration and fusion algorithms and techniques in radiotherapy: report of the AAPM radiation therapy committee task group no. 132. Med Phys 44(7):e43–e76. https://doi.org/10.1002/mp.12256

    Article  CAS  PubMed  Google Scholar 

  28. Kim Y, Choi D, Lee KJ, Kang Y, Ahn JM, Lee E et al (2020) Ruling out rotator cuff tear in shoulder radiograph series using deep learning: redefining the role of conventional radiograph. Eur Radiol 30(5):2843–2852. https://doi.org/10.1007/s00330-019-06639-1

    Article  PubMed  Google Scholar 

  29. Lee K, Kim JY, Lee MH, Choi CH, Hwang JY (2021) Imbalanced loss-integrated deep-learning-based ultrasound image analysis for diagnosis of rotator-cuff tear. Sensors 21(6):2214. https://doi.org/10.3390/s21062214

  30. P.I. F. (2018) A tutorial on Bayesian optimization. ArXiv preprint. arXiv:1807.02811

  31. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision. 618–626

  32. Simonyan K, Andrew Z (2014) Very deep convolutional networks for large-scale image recognition. ArXiv preprint. arXiv:1409.1556

  33. He K, Zhang Z, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778

  34. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV2016.

  35. G. Huang ZL, L. Van Der Maaten and K. Q. Weinberger. Densely connected convolutional networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)2017.

  36. Chollet F (2017) Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 1251–1258

  37. Rawat W, Wang Z (2017) Deep convolutional neural networks for image classification: a comprehensive review. Neural Comput 29(9):2352–2449. https://doi.org/10.1162/NECO_a_00990

    Article  PubMed  Google Scholar 

  38. Ko H, Chung H, Kang WS, Kim KW, Shin Y, Kang SJ et al (2020) COVID-19 pneumonia diagnosis using a simple 2D deep learning framework with a single chest CT image: model development and validation. J Med Internet Res 22(6):e19569. https://doi.org/10.2196/19569

    Article  PubMed  PubMed Central  Google Scholar 

  39. Wu J, Chen XY, Zhang H, Xiong LD, Lei H, Deng SH (2019) Hyperparameter optimization for machine learning models based on Bayesian optimization. J Electron Sci Technol 17(1):26–40. https://doi.org/10.11989/JEST.1674-862X.80904120

    Article  Google Scholar 

  40. Sokolova M, Lapalme G (2009) A systematic analysis of performance measures for classification tasks. Inf Process Manage 45(4):427–437. https://doi.org/10.1016/j.ipm.2009.03.002

    Article  Google Scholar 

  41. Medina G, Buckless CG, Thomasson E, Oh LS, Torriani M (2021) Deep learning method for segmentation of rotator cuff muscles on MR images. Skeletal Radiol 50(4):683–692. https://doi.org/10.1007/s00256-020-03599-2

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

This work was supported by the Korea Ministry of Environment (MOE) as “The Environmental Health Action Program” [2018001360004], and the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) [NRF-2018R1D1A1B07040886, and NRF-2021R1F1A1060436].

Author information

Author notes

  1. Thao Thi Ho and Geun-Tae Kim contributed equally.

Authors and Affiliations

  1. School of Mechanical Engineering, College of Engineering, Kyungpook National University, 80 Daehak-ro, Buk-gu, Daegu, 41566, Republic of Korea

    Thao Thi Ho, Taewoo Kim & Sanghun Choi

  2. Department of Internal Medicine, College of Medicine, Kosin University, 262 Gamcheon-ro, Seo-gu, Busan, 49267, Republic of Korea

    Geun-Tae Kim

  3. Department of Medical Humanities and Social Medicine, College of Medicine, Kosin University, 262 Gamcheon-ro, Seo-gu, Busan, 49267, Republic of Korea

    Eun-Kee Park

Authors
  1. Thao Thi Ho
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Geun-Tae Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Taewoo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sanghun Choi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Eun-Kee Park
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

TTH, TK, SC, G-TK, and E-KP designed the experiments and interpreted the results. G-TK, E-KP, and SC collected experimental data. TTH, SC, and TK performed the experiments. TTH, E-KP, and SC performed the analyses and wrote the manuscript. E-KP, and SC served as co-corresponding authors. All the authors provided feedback on the manuscript.

Corresponding author

Correspondence to Sanghun Choi.

Ethics declarations

Conflict of interest

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.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ho, T.T., Kim, GT., Kim, T. et al. Classification of rotator cuff tears in ultrasound images using deep learning models. Med Biol Eng Comput 60, 1269–1278 (2022). https://doi.org/10.1007/s11517-022-02502-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-022-02502-6

Keywords

Search

Navigation