Skip to main content

Advertisement

SpringerLink
Log in

Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics

  • Original Article
  • Published:
International Journal of Legal Medicine Aims and scope Submit manuscript

Abstract

Bone age assessment (BAA) is a crucial task in clinical, forensic, and athletic fields. Since traditional age estimation methods are suffered from potential radiation damage, this study aimed to develop and evaluate a deep learning radiomics method based on multiparametric knee MRI for noninvasive and automatic BAA. This retrospective study enrolled 598 patients (age range,10.00–29.99 years) who underwent MR examinations of the knee joint (T1/T2*/PD-weighted imaging). Three-dimensional convolutional neural networks (3D CNNs) were trained to extract and fuse multimodal and multiscale MRI radiomic features for age estimation and compared to traditional machine learning models based on hand-crafted features. The age estimation error was greater in individuals aged 25–30 years; thus, this method may not be suitable for individuals over 25 years old. In the test set aged 10–25 years (n = 95), the 3D CNN (a fusion of T1WI, T2*WI, and PDWI) demonstrated the lowest mean absolute error of 1.32 ± 1.01 years, which is higher than that of other MRI modalities and the hand-crafted models. In the classification for 12-, 14-, 16-, and 18- year thresholds, accuracies and the areas under the ROC curves were all over 0.91 and 0.96, which is similar to the manual methods. Visualization of important features showed that 3D CNN estimated age by focusing on the epiphyseal plates. The deep learning radiomics method enables non-invasive and automated BAA from multimodal knee MR images. The use of 3D CNN and MRI-based radiomics has the potential to assist radiologists or medicolegists in age estimation.

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

Data availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author upon reasonable request.

References

  1. Diete V, Wabitsch M, Denzer C et al (2021) Applicability of magnetic resonance imaging for bone age estimation in the context of medical issues. Rofo 193:692–700. https://doi.org/10.1055/a-1313-7664

    Article  PubMed  Google Scholar 

  2. Politzer CS, Bomar JD, Pehlivan HC, Gurusamy P, Edmonds EW, Pennock AT (2021) Creation and validation of a shorthand magnetic resonance imaging bone age assessment tool of the knee as an alternative skeletal maturity assessment. Am J Sports Med 49:2955–2959. https://doi.org/10.1177/03635465211032986

    Article  PubMed  Google Scholar 

  3. Ramsthaler F, Proschek P, Betz W, Verhoff MA (2009) How reliable are the risk estimates for X-ray examinations in forensic age estimations? A safety update. Int J Legal Med 123:199–204. https://doi.org/10.1007/s00414-009-0322-2

    Article  CAS  PubMed  Google Scholar 

  4. Hillewig E, Degroote J, Van der Paelt T et al (2013) Magnetic resonance imaging of the sternal extremity of the clavicle in forensic age estimation: towards more sound age estimates. Int J Legal Med 127:677–689. https://doi.org/10.1007/s00414-012-0798-z

    Article  CAS  PubMed  Google Scholar 

  5. Deng XD, Lu T, Liu GF et al (2022) Forensic age prediction and age classification for critical age thresholds via 3.0T magnetic resonance imaging of the knee in the Chinese Han population. Int J Legal Med 136:841–852. https://doi.org/10.1007/s00414-022-02797-y

    Article  PubMed  Google Scholar 

  6. Dedouit F, Auriol J, Rousseau H, Rouge D, Crubezy E, Telmon N (2012) Age assessment by magnetic resonance imaging of the knee: a preliminary study. Forensic Sci Int 217(232):e1-7. https://doi.org/10.1016/j.forsciint.2011.11.013

    Article  Google Scholar 

  7. Ekizoglu O, Hocaoglu E, Inci E, Can IO, Aksoy S, Kazimoglu C (2016) Forensic age estimation via 3-T magnetic resonance imaging of ossification of the proximal tibial and distal femoral epiphyses: Use of a T2-weighted fast spin-echo technique. Forensic Sci Int 260(102):e1–e7. https://doi.org/10.1016/j.forsciint.2015.12.006

    Article  Google Scholar 

  8. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577. https://doi.org/10.1148/radiol.2015151169

    Article  PubMed  Google Scholar 

  9. Fritz B, Yi PH, Kijowski R, Fritz J (2023) Radiomics and deep learning for disease detection in musculoskeletal radiology: an overview of novel MRI- and CT-based approaches. Invest Radiol 58:3–13. https://doi.org/10.1097/RLI.0000000000000907

    Article  PubMed  Google Scholar 

  10. Chen H, Li S, Zhang Y et al (2022) Deep learning-based automatic segmentation of meningioma from multiparametric MRI for preoperative meningioma differentiation using radiomic features: a multicentre study. Eur Radiol 32:7248–7259. https://doi.org/10.1007/s00330-022-08749-9

    Article  PubMed  Google Scholar 

  11. Jiang X, Li J, Kan Y et al (2021) MRI based radiomics approach with deep learning for prediction of vessel invasion in early-stage cervical cancer. IEEE/ACM Trans Comput Biol Bioinform 18:995–1002. https://doi.org/10.1109/TCBB.2019.2963867

    Article  CAS  PubMed  Google Scholar 

  12. Iftekharuddin KM, Zheng J, Islam MA, Ogg RJ (2009) Fractal-based brain tumor detection in multimodal MRI. Appl Math Comput 207:23–41. https://doi.org/10.1016/j.amc.2007.10.063

    Article  Google Scholar 

  13. 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 

  14. Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP (2017) Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology 287:313–322. https://doi.org/10.1148/radiol.2017170236

    Article  PubMed  Google Scholar 

  15. Zhu Y, Man C, Gong L et al (2019) A deep learning radiomics model for preoperative grading in meningioma. Eur J Radiol 116:128–134. https://doi.org/10.1016/j.ejrad.2019.04.022

    Article  PubMed  Google Scholar 

  16. Halabi SS, Prevedello LM, Kalpathy-Cramer J et al (2018) The RSNA pediatric bone age machine learning challenge. Radiology 290:498–503. https://doi.org/10.1148/radiol.2018180736

    Article  PubMed  Google Scholar 

  17. Dallora AL, Berglund JS, Brogren M et al (2019) Age assessment of youth and young adults using magnetic resonance imaging of the knee: a deep learning approach. JMIR Med Inform 7:e16291. https://doi.org/10.2196/16291

    Article  PubMed  PubMed Central  Google Scholar 

  18. Stern D, Payer C, Giuliani N, Urschler M (2019) Automatic age estimation and majority age classification from multi-factorial MRI data. IEEE J Biomed Health Inform 23:1392–1403. https://doi.org/10.1109/jbhi.2018.2869606

    Article  PubMed  Google Scholar 

  19. Armanious K, Abdulatif S, Bhaktharaguttu AR et al (2021) Organ-based chronological age estimation based on 3D MRI Scans. 2020 28th European Signal Processing Conference (EUSIPCO), pp 1225–8. https://doi.org/10.23919/Eusipco47968.2020.9287398

  20. Tustison NJ, Avants BB, Cook PA et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29:1310–1320. https://doi.org/10.1109/tmi.2010.2046908

    Article  PubMed  PubMed Central  Google Scholar 

  21. Pan H, Han H, Shan S, Chen X (2018) Mean-variance loss for deep age estimation from a face. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5285–94. https://doi.org/10.1109/CVPR.2018.00554

  22. Mauer MA, Well EJ, Herrmann J et al (2021) Automated age estimation of young individuals based on 3D knee MRI using deep learning. Int J Legal Med 135:649–663. https://doi.org/10.1007/s00414-020-02465-z

    Article  PubMed  Google Scholar 

  23. Fan F, Zhang K, Peng Z, Cui JH, Hu N, Deng ZH (2016) Forensic age estimation of living persons from the knee: comparison of MRI with radiographs. Forensic Sci Int 268:145–150. https://doi.org/10.1016/j.forsciint.2016.10.002

    Article  PubMed  Google Scholar 

  24. Schmeling A, Schulz R, Reisinger W, Muhler M, Wernecke KD, Geserick G (2004) Studies on the time frame for ossification of the medial clavicular epiphyseal cartilage in conventional radiography. Int J Legal Med 118:5–8. https://doi.org/10.1007/s00414-003-0404-5

    Article  PubMed  Google Scholar 

  25. Kellinghaus M, Schulz R, Vieth V, Schmidt S, Pfeiffer H, Schmeling A (2010) Enhanced possibilities to make statements on the ossification status of the medial clavicular epiphysis using an amplified staging scheme in evaluating thin-slice CT scans. Int J Legal Med 124:321–325. https://doi.org/10.1007/s00414-010-0448-2

    Article  PubMed  Google Scholar 

  26. Fan F, Dong X, Wu X et al (2020) An evaluation of statistical models for age estimation and the assessment of the 18-year threshold using conventional pelvic radiographs. Forensic Sci Int 314:110350. https://doi.org/10.1016/j.forsciint.2020.110350

    Article  PubMed  Google Scholar 

  27. Wittschieber D, Chitavishvili N, Papageorgiou I, Malich A, Mall G, Mentzel HJ (2022) Magnetic resonance imaging of the proximal tibial epiphysis is suitable for statements as to the question of majority: a validation study in forensic age diagnostics. Int J Legal Med 136:777–784. https://doi.org/10.1007/s00414-021-02766-x

    Article  PubMed  Google Scholar 

  28. Guo S, Wang L, Chen Q, Wang L, Zhang J, Zhu Y (2022) Multimodal MRI image decision fusion-based network for glioma classification. Front Oncol 12:819673. https://doi.org/10.3389/fonc.2022.819673

    Article  PubMed  PubMed Central  Google Scholar 

  29. Pröve PL, Jopp-van Well E, Stanczus B et al (2019) Automated segmentation of the knee for age assessment in 3D MR images using convolutional neural networks. Int J Legal Med 133:1191–1205. https://doi.org/10.1007/s00414-018-1953-y

    Article  PubMed  Google Scholar 

  30. Weikert T, Cyriac J, Yang S, Nesic I, Parmar V, Stieltjes B (2020) A practical guide to artificial intelligence-based image analysis in radiology. Invest Radiol 55:1–7. https://doi.org/10.1097/rli.0000000000000600

    Article  PubMed  Google Scholar 

  31. Fan F, Tu M, Li R et al (2020) Age estimation by multidetector computed tomography of cranial sutures in Chinese male adults. Am J Phys Anthropol 171:550–558. https://doi.org/10.1002/ajpa.23998

    Article  PubMed  Google Scholar 

  32. Grabherr S, Cooper C, Ulrich-Bochsler S et al (2009) Estimation of sex and age of “virtual skeletons”–a feasibility study. Eur Radiol 19:419–429. https://doi.org/10.1007/s00330-008-1155-y

    Article  PubMed  Google Scholar 

  33. Liversidge HM, Smith BH, Maber M (2010) Bias and accuracy of age estimation using developing teeth in 946 children. Am J Phys Anthropol 143:545–554. https://doi.org/10.1002/ajpa.21349

    Article  PubMed  Google Scholar 

  34. Meinl A, Huber CD, Tangl S, Gruber GM, Teschler-Nicola M, Watzek G (2008) Comparison of the validity of three dental methods for the estimation of age at death. Forensic Sci Int 178:96–105. https://doi.org/10.1016/j.forsciint.2008.02.008

    Article  CAS  PubMed  Google Scholar 

  35. Aykroyd RG, Lucy D, Pollard AM, Solheim T (1997) Technical note: regression analysis in adult age estimation. Am J Phys Anthropol 104:259–265. https://doi.org/10.1002/(sici)1096-8644(199710)104:2%3c259::aid-ajpa11%3e3.0.co;2-z

    Article  CAS  PubMed  Google Scholar 

  36. Vossoughi M, Movahhedian N, Ghafoori A (2022) The impact of age mimicry bias on the accuracy of methods for age estimation based on Kvaal’s pulp/tooth ratios: a bootstrap study. Int J Legal Med 136:269–278. https://doi.org/10.1007/s00414-021-02651-7

    Article  PubMed  Google Scholar 

  37. Jonsson BA, Bjornsdottir G, Thorgeirsson TE et al (2019) Brain age prediction using deep learning uncovers associated sequence variants. Nat Commun 10:5409. https://doi.org/10.1038/s41467-019-13163-9

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Funding

This work was supported by the Key Research and Development Program of Sichuan Province of China (grant number 2022YFS0530); the Opening Project of Key Laboratory of Evidence Science (China University of Political Science and Law), Ministry of Education (grant number 2021KFKT03); the Postdoctoral Research Project of Sichuan Province (grant number 2021–12); the Natural Science Foundation of Sichuan Province (grant number 2022NSFSC1286); the Sichuan Province Science and Technology Support Program (grant number 2020YJ0267).

Author information

Authors and Affiliations

  1. West China School of Basic Medical Sciences & Forensic Medicine, Sichuan University, Chengdu, 610041, People’s Republic of China

    Fei Fan, Guangfeng Liu, Junhong Liu, Xiaodong Deng, Kui Zhang, Mengjun Zhan & Zhenhua Deng

  2. College of Computer Science, Sichuan University, Chengdu, 610064, People’s Republic of China

    Han Liu & Hu Chen

  3. Department of Laboratory Medicine, West China Hospital, Sichuan University, Chengdu, 610041, People’s Republic of China

    Xinhua Dai

  4. Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, People’s Republic of China

    Zhao Peng

  5. Department of Radiology, Anhui Provincial Children’s Hospital, Hefei, 230054, People’s Republic of China

    Chang Wang & Chuangao Yin

Authors
  1. Fei Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Han Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xinhua Dai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guangfeng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Junhong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiaodong Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Zhao Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Chang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Kui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Hu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Chuangao Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Mengjun Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Zhenhua Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: Fei Fan, Hu Chen, Chuangao Yin, Mengjun Zhan, Zhenhua Deng.

Data curation: Fei Fan, Han Liu, Mengjun Zhan, Zhenhua Deng.

Formal analysis: Fei Fan, Han Liu, Xinhua Dai, Guangfeng Liu, Junhong Liu, Kui Zhang.

Funding acquisition: Fei Fan, Xiaodong Deng, Kui Zhang.

Investigation: Fei Fan, Xinhua Dai, Guangfeng Liu, Junhong Liu, Xiaodong Deng, Zhao Peng.

Methodology: Fei Fan, Han Liu, Chuangao Yin, Chang Wang, Hu Chen, Mengjun Zhan, Zhenhua Deng.

Project administration: Zhenhua Deng.

Resources: Fei Fan, Xiaodong Deng, Zhenhua Deng.

Software: Fei Fan, Han Liu, Xinhua Dai,Hu Chen, Zhenhua Deng.

Supervision: Zhenhua Deng.

Validation: Zhao Peng, Xinhua Dai, Chuangao Yin, Chang Wang.

Visualization: Fei Fan, Han Liu, Zhenhua Deng.

Writing—original draft: Fei Fan.

Writing—review & editing: all authors.

Corresponding authors

Correspondence to Chuangao Yin, Mengjun Zhan or Zhenhua Deng.

Ethics declarations

Ethics approval

Approval was obtained from the ethics committee of Sichuan University. And informed consent was waived because of the retrospective nature. The procedures used in this study adhere to the tenets of the Declaration of Helsinki.

Research involving human participants and/or animals

Human participants.

Disclosure of potential conflicts of interest

The authors have no relevant financial or non-financial interests to disclose.

Additional information

Publisher's Note

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

Zhenhua Deng, Mengjun Zhan, and Chuangao Yin are co-senior authors.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (MP4 2044 KB) Video 1 The whole heatmap images of the example in Figure 5

Supplementary file2 (DOCX 1179 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

Fan, F., Liu, H., Dai, X. et al. Automated bone age assessment from knee joint by integrating deep learning and MRI-based radiomics. Int J Legal Med 138, 927–938 (2024). https://doi.org/10.1007/s00414-023-03148-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00414-023-03148-1

Keywords

Search

Navigation