Skip to main content
Log in

Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

Automatic bone lesions detection and classifications present a critical challenge and are essential to support radiologists in making an accurate diagnosis of bone lesions. In this paper, we aimed to develop a novel deep learning model called You Only Look Once (YOLO) to handle detecting and classifying bone lesions on full-field radiographs with limited manual intervention.

Methods

In this retrospective study, we used 1085 bone tumor radiographs and 345 normal bone radiographs from two centers between January 2009 and December 2020 to train and test our YOLO deep learning (DL) model. The trained model detected bone lesions and then classified these radiographs into normal, benign, intermediate, or malignant types. The intersection over union (IoU) was used to assess the model’s performance in the detection task. Confusion matrices and Cohen’s kappa scores were used for evaluating classification performance. Two radiologists compared diagnostic performance with the trained model using the external validation set.

Results

In the detection task, the model achieved accuracies of 86.36% and 85.37% in the internal and external validation sets, respectively. In the DL model, radiologist 1 and radiologist 2 achieved Cohen’s kappa scores of 0.8187, 0.7927, and 0.9077 for four-way classification in the external validation set, respectively. The YOLO DL model illustrated a significantly higher accuracy for intermediate bone tumor classification than radiologist 1 (95.73% vs 88.08%, p = 0.004).

Conclusions

The developed YOLO DL model could be used to assist radiologists at all stages of bone lesion detection and classification in full-field bone radiographs.

Key Points

YOLO DL model can automatically detect bone neoplasms from full-field radiographs in one shot and then simultaneously classify radiographs into normal, benign, intermediate, or malignant.

The dataset used in this retrospective study includes normal bone radiographs.

YOLO can detect even some challenging cases with small volumes.

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

Access this article

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

Abbreviations

AI:

Artificial intelligence

AUC:

Area under the receiver operating characteristic curve

CLAHE:

Contrast limited adaptive histogram equalization

COCO:

Common objects in context

CT:

Computed tomography

DICOM:

Digital imaging and communication in medicine

DL:

Deep learning

IoU:

Intersection over union

JPEG:

Joint photographic experts group

MRI:

Magnetic resonance imaging

NPV:

Negative predictive value

PPV:

Positive predictive value

ROI:

Region of interest

YOLO:

You Only Look Once

References

  1. Miller TT (2008) Bone tumors and tumorlike conditions: analysis with conventional radiography. Radiology 246:662–674. https://doi.org/10.1148/radiol.2463061038

    Article  PubMed  Google Scholar 

  2. Vogrin M, Trojner T, Kelc R (2020) Artificial intelligence in musculoskeletal oncological radiology. Radiol Oncol 55:1–6. https://doi.org/10.2478/raon-2020-0068

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  3. Siegel RL, Miller KD, Fuchs HE, Jemal A (2022) Cancer statistics, 2022. CA Cancer J Clin 72:7–33. https://doi.org/10.3322/caac.21708

    Article  PubMed  Google Scholar 

  4. Rosenberg AE (2013) WHO classification of soft tissue and bone, fourth edition: Summary and commentary. Curr Opin Oncol 25:571–573. https://doi.org/10.1097/01.cco.0000432522.16734.2d

    Article  PubMed  Google Scholar 

  5. Gemescu IN, Thierfelder KM, Rehnitz C, Weber MA (2019) Imaging features of bone tumors: conventional radiographs and MR imaging correlation. Magn Reson Imaging Clin N Am 27:753–767. https://doi.org/10.1016/j.mric.2019.07.008

    Article  PubMed  Google Scholar 

  6. Bestic JM, Wessell DE, Beaman FD et al (2020) ACR Appropriateness Criteria® primary bone tumors. J Am Coll Radiol 17:S226–S238. https://doi.org/10.1016/j.jacr.2020.01.038

    Article  PubMed  Google Scholar 

  7. Al-Qassab S, Lalam R, Botchu R, Bazzocchi A (2021) Imaging of pediatric bone tumors and tumor-like lesions. Semin Musculoskelet Radiol 25:57–67. https://doi.org/10.1055/s-0041-1723965

    Article  PubMed  Google Scholar 

  8. Davatzikos C, Sotiras A, Fan Y et al (2019) Precision diagnostics based on machine learning-derived imaging signatures. Magn Reson Imaging 64:49–61. https://doi.org/10.1016/j.mri.2019.04.012

    Article  PubMed  PubMed Central  Google Scholar 

  9. Zhao C, Shao M, Carass A et al (2019) Applications of a deep learning method for anti-aliasing and super-resolution in MRI. Magn Reson Imaging 64:132–141. https://doi.org/10.1016/j.mri.2019.05.038

    Article  PubMed  PubMed Central  Google Scholar 

  10. Olczak J, Fahlberg N, Maki A et al (2017) Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop 88:581–586. https://doi.org/10.1080/17453674.2017.1344459

    Article  PubMed  PubMed Central  Google Scholar 

  11. Krittanawong C (2018) The rise of artificial intelligence and the uncertain future for physicians. Eur J Intern Med 48:e13–e14. https://doi.org/10.1016/j.ejim.2017.06.017

    Article  CAS  PubMed  Google Scholar 

  12. Hinzpeter R, Baumann L, Guggenberger R, Huellner M, Alkadhi H, Baessler B (2022) Radiomics for detecting prostate cancer bone metastases invisible in CT: a proof-of-concept study. Eur Radiol 32:1823–1832. https://doi.org/10.1007/s00330-021-08245-6

    Article  CAS  PubMed  Google Scholar 

  13. Gitto S, Cuocolo R, Albano D et al (2020) MRI radiomics-based machine-learning classification of bone chondrosarcoma. Eur J Radiol 128:109043. https://doi.org/10.1016/j.ejrad.2020.109043

    Article  PubMed  Google Scholar 

  14. Hong JH, Jung JY, Jo A et al (2021) Development and validation of a radiomics model for differentiating bone islands and osteoblastic bone metastases at abdominal CT. Radiology 299:626–632. https://doi.org/10.1148/radiol.2021203783

    Article  PubMed  Google Scholar 

  15. Hirschmann A, Cyriac J, Stieltjes B, Kober T, Richiardi J, Omoumi P (2019) Artificial intelligence in musculoskeletal imaging: review of current literature, challenges, and trends. Semin Musculoskelet Radiol 23:304–311. https://doi.org/10.1055/s-0039-1684024

    Article  PubMed  Google Scholar 

  16. Gyftopoulos S, Subhas N (2020) Musculoskeletal imaging applications of artificial intelligence. Semin Musculoskelet Radiol 24:1–2. https://doi.org/10.1055/s-0039-3400511

    Article  PubMed  Google Scholar 

  17. He Y, Pan I, Bao B et al (2020) Deep learning-based classification of primary bone tumors on radiographs: a preliminary study. EBioMedicine 62:103121. https://doi.org/10.1016/j.ebiom.2020.103121

    Article  PubMed  PubMed Central  Google Scholar 

  18. Liu R, Pan D, Xu Y et al (2022) A deep learning–machine learning fusion approach for the classification of benign, malignant, and intermediate bone tumors. Eur Radiol 32:1371–1383. https://doi.org/10.1007/s00330-021-08195-z

    Article  PubMed  Google Scholar 

  19. von Schacky CE, Wilhelm NJ, Schäfer VS et al (2021) Multitask deep learning for segmentation and classification of primary bone tumors on radiographs. Radiology 301:398–406. https://doi.org/10.1148/radiol.2021204531

    Article  Google Scholar 

  20. WHO Classification of Tumours Editorial Board (2020) Soft tissue and bone tumours, 5th edn. IARCPress, Lyon, pp 338.

  21. Kim DH, MacKinnon T (2018) Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clin Radiol 73:439–445. https://doi.org/10.1016/j.crad.2017.11.015

    Article  CAS  PubMed  Google Scholar 

  22. Bien N, Rajpurkar P, Ball RL et al (2018) Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of MRNet. PLoS Med 15:e1002699. https://doi.org/10.1371/journal.pmed.1002699

    Article  PubMed  PubMed Central  Google Scholar 

  23. Salzler M, Nwachukwu BU, Rosas S et al (2015) State-of-the-art anterior cruciate ligament tears: a primer for primary care physicians. Phys Sportsmed 43:169–177. https://doi.org/10.1080/00913847.2015.1016865

    Article  PubMed  Google Scholar 

  24. Liu F, Guan B, Zhou Z et al (2019) Fully automated diagnosis of anterior cruciate ligament tears on knee MR images by using deep learning. Radiol Artif Intell 1:180091. https://doi.org/10.1148/ryai.2019180091

    Article  PubMed  PubMed Central  Google Scholar 

  25. Fritz B, Fritz J (2022) Artificial intelligence for MRI diagnosis of joints: a scoping review of the current state-of-the-art of deep learning-based approaches. Skeletal Radiol 51:315–329. https://doi.org/10.1007/s00256-021-03830-8

    Article  PubMed  Google Scholar 

  26. Gorelik N, Gyftopoulos S (2021) Applications of artificial intelligence in musculoskeletal imaging: from the request to the report. Can Assoc Radiol J 72:45–59. https://doi.org/10.1177/0846537120947148

    Article  PubMed  Google Scholar 

  27. Al-masni MA, Al-antari MA, Park JM et al (2018) Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system. Comput Methods Programs Biomed 157:85–94. https://doi.org/10.1016/j.cmpb.2018.01.017

    Article  PubMed  Google Scholar 

  28. Aly GH, Marey M, El-Sayed SA, Tolba MF (2021) YOLO based breast masses detection and classification in full-field digital mammograms. Comput Methods Programs Biomed 200:105823. https://doi.org/10.1016/j.cmpb.2020.105823

    Article  PubMed  Google Scholar 

  29. Kim W, Cho H, Kim J, Kim B, Lee S (2020) Yolo-based simultaneous target detection and classification in automotive FMCW radar systems. Sensors 20:2897. https://doi.org/10.3390/s20102897

    Article  PubMed  PubMed Central  Google Scholar 

  30. Ünver HM, Ayan E (2019) Skin lesion segmentation in dermoscopic images with combination of yolo and grabcut algorithm. Diagnostics 9:72. https://doi.org/10.3390/diagnostics9030072

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

There is no financial support.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jiufa Cui.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jiufa Cui.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

One of the authors (Sheng Miao) has significant statistical expertise.

Informed consent

The requirement for written informed consent for this retrospective study was waived.

Ethical approval

The Ethical Committee of Affiliated Hospital of Qingdao University approved this retrospective study.

Methodology

• retrospective

• diagnostic or prognostic study

• multicentre study

Additional information

Publisher’s note

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

Supplementary Information

ESM 1

(DOCX 1560 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

Li, J., Li, S., Li, X. et al. Primary bone tumor detection and classification in full-field bone radiographs via YOLO deep learning model. Eur Radiol 33, 4237–4248 (2023). https://doi.org/10.1007/s00330-022-09289-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-09289-y

Keywords

Navigation