Skip to main content

Advertisement

SpringerLink
Log in

Detecting pediatric wrist fractures using deep-learning-based object detection

  • Original Article
  • Published:
Pediatric Radiology Aims and scope Submit manuscript

Abstract

Background

Missed fractures are the leading cause of diagnostic error in the emergency department, and fractures of pediatric bones, particularly subtle wrist fractures, can be misidentified because of their varying characteristics and responses to injury.

Objective

This study evaluated the utility of an object detection deep learning framework for classifying pediatric wrist fractures as positive or negative for fracture, including subtle buckle fractures of the distal radius, and evaluated the performance of this algorithm as augmentation to trainee radiograph interpretation.

Materials and methods

We obtained 395 posteroanterior wrist radiographs from unique pediatric patients (65% positive for fracture, 30% positive for distal radial buckle fracture) and divided them into train (n = 229), tune (n = 41) and test (n = 125) sets. We trained a Faster R-CNN (region-based convolutional neural network) deep learning object-detection model. Two pediatric and two radiology residents evaluated radiographs initially without the artificial intelligence (AI) assistance, and then subsequently with access to the bounding box generated by the Faster R-CNN model.

Results

The Faster R-CNN model demonstrated an area under the curve (AUC) of 0.92 (95% confidence interval [CI] 0.87–0.97), accuracy of 88% (n = 110/125; 95% CI 81–93%), sensitivity of 88% (n = 70/80; 95% CI 78–94%) and specificity of 89% (n = 40/45, 95% CI 76–96%) in identifying any fracture and identified 90% of buckle fractures (n = 35/39, 95% CI 76–97%). Access to Faster R-CNN model predictions significantly improved average resident accuracy from 80 to 93% in detecting any fracture (P < 0.001) and from 69 to 92% in detecting buckle fracture (P < 0.001). After accessing AI predictions, residents significantly outperformed AI in cases of disagreement (73% resident correct vs. 27% AI, P = 0.002).

Conclusion

An object-detection-based deep learning approach trained with only a few hundred examples identified radiographs containing pediatric wrist fractures with high accuracy. Access to model predictions significantly improved resident accuracy in diagnosing these fractures.

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

References

  1. Hallas P, Ellingsen T (2006) Errors in fracture diagnoses in the emergency department —characteristics of patients and diurnal variation. BMC Emerg Med 6:4

    Article  PubMed  PubMed Central  Google Scholar 

  2. Guly HR (2001) Diagnostic errors in an accident and emergency department. Emerg Med J 18:263–269

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. George MP, Bixby S (2019) Frequently missed fractures in pediatric trauma: a pictorial review of plain film radiography. Radiol Clin North Am 57:843–855

    Article  PubMed  Google Scholar 

  4. Jadhav SP, Swischuk LE (2008) Commonly missed subtle skeletal injuries in children: a pictorial review. Emerg Radiol 15:391–398

    Article  PubMed  Google Scholar 

  5. Halsted MJ, Kumar H, Paquin JJ et al (2004) Diagnostic errors by radiology residents in interpreting pediatric radiographs in an emergency setting. Pediatr Radiol 34:331–336

    Article  PubMed  Google Scholar 

  6. Jones RM, Sharma A, Hotchkiss R et al (2020) Assessment of a deep-learning system for fracture detection in musculoskeletal radiographs. NPJ Digit Med 3:144

    Article  PubMed  PubMed Central  Google Scholar 

  7. Kalmet PHS, Sanduleanu S, Primakov S et al (2020) Deep learning in fracture detection: a narrative review. Acta Orthop 91:215–220

    Article  PubMed  PubMed Central  Google Scholar 

  8. Rayan JC, Reddy N, Kan JH et al (2019) Binomial classification of pediatric elbow fractures using a deep learning multiview approach emulating radiologist decision making. Radiol Artif Intell 1:e180015

    Article  PubMed  PubMed Central  Google Scholar 

  9. Lindsey R, Daluiski A, Chopra S et al (2018) Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A 115:11591–11596

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  10. Ebsim R, Naqvi J, Cootes TF (2019) Automatic detection of wrist fractures from posteroanterior and lateral radiographs: a deep learning-based approach. In: Glocker B, Yao J, Vrtovec T et al (eds) Computational methods and clinical applications in musculoskeletal imaging. Springer International Publishing, Cham, pp 114–125

  11. Thian YL, Li Y, Jagmohan P et al (2019) Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiol Artif Intell 1:e180001

    Article  PubMed  PubMed Central  Google Scholar 

  12. Blüthgen C, Becker AS, Vittoria de Martini I et al (2020) Detection and localization of distal radius fractures: deep learning system versus radiologists. Eur J Radiol 126:108925

    Article  PubMed  Google Scholar 

  13. Ren M, Yi PH (2022) Deep learning detection of subtle fractures using staged algorithms to mimic radiologist search pattern. Skeletal Radiol 51:345–353

    Article  PubMed  Google Scholar 

  14. Lin T-Y, Maire M, Belongie S et al (2014) Microsoft COCO: common objects in context. arXiv [cs.CV]

  15. Guermazi A, Tannoury C, Kompel AJ et al (2021) Improving radiographic fracture recognition performance and efficiency using artificial intelligence. Radiology 302:627–636

    Article  PubMed  Google Scholar 

  16. Langerhuizen DWG, Bulstra AEJ, Janssen SJ et al (2020) Is deep learning on par with human observers for detection of radiographically visible and occult fractures of the scaphoid? Clin Orthop Relat Res 478:2653–2659

    Article  PubMed  PubMed Central  Google Scholar 

  17. Hardalaç F, Uysal F, Peker O et al (2022) Fracture detection in wrist X-ray images using deep learning-based object detection models. Sensors 22:1285

    Article  PubMed  PubMed Central  Google Scholar 

  18. Hernandez JA, Swischuk LE, Yngve DA, Carmichael KD (2003) The angled buckle fracture in pediatrics: a frequently missed fracture. Emerg Radiol 10:71–75

    Article  PubMed  Google Scholar 

  19. Wang X, Peng Y, Lu L et al (2017) ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. arXiv [cs.CV]

  20. Kluyver T, Ragan-Kelley B, Pérez F et al (2016) Jupyter Notebooks — a publishing format for reproducible computational workflows. In: Loizides F, Schmidt B (eds) Positioning and power in academic publishing: players, agents and agendas. IOS Press, pp 87–90

    Google Scholar 

  21. Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137–1149

    Article  PubMed  Google Scholar 

  22. Wu Y, Kirillov A, Massa F et al (2019) Detectron2. https://github.com/facebookresearch/detectron2. Accessed 22 Dec 2022

  23. Paszke A, Gross S, Chintala S et al (2017) Automatic differentiation in PyTorch

  24. Zhao Z-Q, Zheng P, Xu S-T, Wu X (2019) Object Detection With Deep Learning: A Review. IEEE Trans Neural Netw Learn Syst 30:3212–3232

    Article  PubMed  Google Scholar 

  25. Merkel D (n.d.) Docker: lightweight linux containers for consistent development and deployment. https://www.seltzer.com/margo/teaching/CS508.19/papers/merkel14.pdf. Accessed 26 Nov 2022

  26. Mongan J, Moy L, Kahn CE (2020) Checklist for artificial intelligence in medical imaging (CLAIM): a guide for authors and reviewers. Radiol Artif Intell 2:e200029

    Article  PubMed  PubMed Central  Google Scholar 

  27. Merewitz L, Sunshine JH (2006) A portrait of pediatric radiologists in the United States. AJR Am J Roentgenol 186:12–22

    Article  PubMed  Google Scholar 

  28. Rosenkrantz AB, Wang W, Hughes DR, Duszak JRR (2018) Generalist versus subspecialist characteristics of the U.S. radiologist workforce. Radiology 286:929–937

    Article  PubMed  Google Scholar 

  29. Eng DK, Khandwala NB, Long J et al (2021) Artificial intelligence algorithm improves radiologist performance in skeletal age assessment: a prospective multicenter randomized controlled trial. Radiology 301:692–699

    Article  PubMed  Google Scholar 

  30. Wu N, Phang J, Park J et al (2020) Deep neural networks improve radiologists’ performance in breast cancer screening. IEEE Trans Med Imaging 39:1184–1194

    Article  PubMed  Google Scholar 

  31. Fenton JJ, Xing G, Elmore JG et al (2013) Short-term outcomes of screening mammography using computer-aided detection: a population-based study of Medicare enrollees. Ann Intern Med 158:580–587

    Article  PubMed  PubMed Central  Google Scholar 

  32. Liu B, Luo J, Huang H (2020) Toward automatic quantification of knee osteoarthritis severity using improved Faster R-CNN. Int J Comput Assist Radiol Surg 15:457–466

    Article  PubMed  Google Scholar 

  33. Su Y, Li D, Chen X (2021) Lung nodule detection based on Faster R-CNN framework. Comput Methods Programs Biomed 200:105866

    Article  PubMed  Google Scholar 

  34. Lu Y, Yu Q, Gao Y et al (2018) Identification of metastatic lymph nodes in MR imaging with faster region-based convolutional neural networks. Cancer Res 78:5135–5143

    Article  CAS  PubMed  Google Scholar 

  35. Tan M, Pang R, Le QV (2019) EfficientDet: scalable and efficient object detection. arXiv [cs.CV]

  36. Wang C-Y, Bochkovskiy A, Liao H-YM (2022) YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv [cs.CV]

  37. Raisuddin AM, Vaattovaara E, Nevalainen M et al (2021) Critical evaluation of deep neural networks for wrist fracture detection. Sci Rep 11:6006

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Mårtensson G, Ferreira D, Granberg T et al (2020) The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study. Med Image Anal 66:101714

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Radiology, Columbia University Irving Medical Center/New York Presbyterian Hospital, 622 W 168th St., New York, NY, 10032, USA

    John R. Zech, Zenas Igbinoba, Clement Vinh Tran & Tony T. Wong

  2. Department of Radiology, University of California San Diego, San Diego, CA, USA

    Giuseppe Carotenuto

  3. Department of Pediatrics, Columbia University Irving Medical Center/Morgan Stanley Children’s Hospital of New York, New York, NY, USA

    Elena Insley

  4. Division of Gastroenterology, Children’s Hospital of Philadelphia, Philadelphia, PA, USA

    Alyssa Baccarella

Authors
  1. John R. Zech
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Giuseppe Carotenuto
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zenas Igbinoba
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Clement Vinh Tran
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Elena Insley
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alyssa Baccarella
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tony T. Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to John R. Zech.

Ethics declarations

Conflicts of interest

None

Additional information

Publisher's Note

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

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 29 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zech, J.R., Carotenuto, G., Igbinoba, Z. et al. Detecting pediatric wrist fractures using deep-learning-based object detection. Pediatr Radiol 53, 1125–1134 (2023). https://doi.org/10.1007/s00247-023-05588-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00247-023-05588-8

Keywords

Search

Navigation