Skip to main content

Advertisement

SpringerLink
Log in

Deep learning enables automatic adult age estimation based on CT reconstruction images of the costal cartilage

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

Abstract

Objective

Adult age estimation (AAE) is a challenging task. Deep learning (DL) could be a supportive tool. This study aimed to develop DL models for AAE based on CT images and compare their performance to the manual visual scoring method.

Methods

Chest CT were reconstructed using volume rendering (VR) and maximum intensity projection (MIP) separately. Retrospective data of 2500 patients aged 20.00–69.99 years were obtained. The cohort was split into training (80%) and validation (20%) sets. Additional independent data from 200 patients were used as the test set and external validation set. Different modality DL models were developed accordingly. Comparisons were hierarchically performed by VR versus MIP, single-modality versus multi-modality, and DL versus manual method. Mean absolute error (MAE) was the primary parameter of comparison.

Results

A total of 2700 patients (mean age = 45.24 years ± 14.03 [SD]) were evaluated. Of single-modality models, MAEs yielded by VR were lower than MIP. Multi-modality models generally yielded lower MAEs than the optimal single-modality model. The best-performing multi-modality model obtained the lowest MAEs of 3.78 in males and 3.40 in females. On the test set, DL achieved MAEs of 3.78 in males and 3.92 in females, which were far better than the MAEs of 8.90 and 6.42 respectively, for the manual method. For the external validation, MAEs were 6.05 in males and 6.68 in females for DL, and 6.93 and 8.28 for the manual method.

Conclusions

DL demonstrated better performance than the manual method in AAE based on CT reconstruction of the costal cartilage.

Clinical relevance statement

Aging leads to diseases, functional performance deterioration, and both physical and physiological damage over time. Accurate AAE may aid in diagnosing the personalization of aging processes.

Key Points

• VR-based DL models outperformed MIP-based models with lower MAEs and higher R2 values.

• All multi-modality DL models showed better performance than single-modality models in adult age estimation.

• DL models achieved a better performance than expert assessments.

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

Abbreviations

AAE:

Adult age estimation

CNNs:

Convolutional neural networks

DL:

Deep learning

MAE:

Mean absolute error

MIP:

Maximum intensity projection

ROI:

Region of interest

VR:

Volume rendering

References

  1. Schmeling A, Dettmeyer R, Rudolf E, Vieth V, Geserick G (2016) Forensic age estimation. Dtsch Arztebl Int 113:44–50

    PubMed  PubMed Central  Google Scholar 

  2. 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

    Article  PubMed  Google Scholar 

  3. Štern D, Payer C, Urschler M (2019) Automated age estimation from MRI volumes of the hand. Med Image Anal 58:101538

    Article  PubMed  Google Scholar 

  4. Suciyanie IM, Gultom FP, Hidayat AN, Suhartono AW, Yuniastuti M, Auerkari EI (2022) Accuracy of forensic age estimation using cementum annulation and dentin translucency in adult: a systematic review and meta-analysis. Int J Legal Med 136:1443–1455

    Article  PubMed  Google Scholar 

  5. Cheng J, Liu Z, Guan H et al (2021) Brain age estimation from MRI using cascade networks with ranking loss. IEEE Trans Med Imaging 40:3400–3412

    Article  PubMed  Google Scholar 

  6. Gualdi-Russo E, Saguto I, Frisoni P, Neri M, Mongillo J, Rinaldo N (2022) Age estimation using tooth cementum annulations: bias and sources of inaccuracy. Front Biosci (Landmark Ed) 27:141

    Article  CAS  PubMed  Google Scholar 

  7. San-Millán M, Rissech C, Turbón D (2017) New approach to age estimation of male and female adult skeletons based on the morphological characteristics of the acetabulum. Int J Legal Med 131:501–525

    Article  PubMed  Google Scholar 

  8. Kazmi S, Mânica S, Revie G, Shepherd S, Hector M (2019) Age estimation using canine pulp volumes in adults: a CBCT image analysis. Int J Legal Med 133:1967–1976

    Article  PubMed  PubMed Central  Google Scholar 

  9. Karydi C, García-Donas JG, Tsiminikaki K, Bonicelli A, Moraitis K, Kranioti EF (2022) Estimation of age-at-death using cortical bone histomorphometry of the rib and femur: validation study on a British population. Biology 11(11):1615

  10. Zhang K, Fan F, Tu M et al (2018) The role of multislice computed tomography of the costal cartilage in adult age estimation. Int J Legal Med 132:791–798

    Article  PubMed  Google Scholar 

  11. Mavroudas SR, Meckel LA, Gocha TP, Goldstein JZ, Garza SL (2022) The effects of experimental whole-body burning on histological age-at-death estimation from human cortical bone and dental cementum. Biology 11(11):1569

  12. Nam JG, Kang HR, Lee SM et al (2022) Deep learning prediction of survival in patients with chronic obstructive pulmonary disease using chest radiographs. Radiology 305:199–208

    Article  PubMed  Google Scholar 

  13. Yang CY, Pan YJ, Chou Y et al (2021)  Using deep neural networks for predicting age and sex in healthy adult chest radiographs. J Clin Med 10(19):4431

  14. Arunmozhi S, Rajinikanth V, Rajakumar MP (2021) Deep-learning based automated detection of pneumonia in chest radiographs 2021 International Conference on System, Computation, Automation and Networking (ICSCAN), pp 1–4

  15. Zhang K, Liu X, Xu J et al (2021) Deep-learning models for the detection and incidence prediction of chronic kidney disease and type 2 diabetes from retinal fundus images. Nat Biomed Eng 5:533–545

    Article  CAS  PubMed  Google Scholar 

  16. Raghu VK, Weiss J, Hoffmann U, Aerts H, Lu MT (2021) Deep learning to estimate biological age from chest radiographs. JACC Cardiovasc Imaging 14:2226–2236

    Article  PubMed  Google Scholar 

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

  18. Xie S, Girshick R, Dollár P, Tu Z, He K (2017) Aggregated residual transformations for deep neural networksProceedings of the IEEE conference on computer vision and pattern recognition, pp 1492–1500

  19. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700–4708

  20. SzegedyC L (2015) Goingdeeperwithconvolutions//ProceedingsoftheIEEEConferenceonComputerVision andPatternRecognition. Boston, USA 1:9

  21. Luo Y, Zhang Y, Yan J, Liu W (2021) Generalizing face forgery detection with high-frequency features Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 16317–16326

  22. Wang Y, Huang W, Sun F, Xu T, Rong Y, Huang J (2020) Deep multimodal fusion by channel exchanging. Adv Neural Inf Process Syst 33:4835–4845

    Google Scholar 

  23. Hu J, Shen L, Sun G (2018) Squeeze-and-excitation networks Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7132–7141

  24. Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: convolutional block attention module Proceedings of the European conference on computer vision (ECCV), pp 3–19

  25. Park J, Woo S, Lee J-Y, Kweon IS (2018) Bam: bottleneck attention module. https://doi.org/10.48550/arXiv.1807.06514. Accessed 22 May 2023

  26. Nummela MT, Bensch FV, Pyhältö TT, Koskinen SK (2018) Incidence and imaging findings of costal cartilage fractures in patients with blunt chest trauma: a retrospective review of 1461 consecutive whole-body CT examinations for trauma. Radiology 286:696–704

    Article  PubMed  Google Scholar 

  27. Bonicelli A, Zioupos P, Arnold E, Rogers KD, Xhemali B, Kranioti EF (2021) Age related changes of rib cortical bone matrix and the application to forensic age-at-death estimation. Sci Rep 11:2086

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Bonicelli A, Xhemali B, Kranioti EF, Zioupos P (2017) Rib biomechanical properties exhibit diagnostic potential for accurate ageing in forensic investigations. PLoS One 12:e0176785

    Article  PubMed  PubMed Central  Google Scholar 

  29. Milenkovic P, Djuric M, Milovanovic P, Djukic K, Zivkovic V, Nikolic S (2014) The role of CT analyses of the sternal end of the clavicle and the first costal cartilage in age estimation. Int J Legal Med 128:825–839

    Article  PubMed  Google Scholar 

  30. Michelson N (1934) The calcification of the first costal cartilage among whites and negroes. Human Biol 6:543

    Google Scholar 

  31. Garamendi PM, Landa MI, Botella MC, Alemán I (2011) Forensic age estimation on digital X-ray images: medial epiphyses of the clavicle and first rib ossification in relation to chronological age. J Forensic Sci 56(Suppl 1):S3–S12

    PubMed  Google Scholar 

  32. Moskovitch G, Dedouit F, Braga J, Rougé D, Rousseau H, Telmon N (2010) Multislice computed tomography of the first rib: a useful technique for bone age assessment. J Forensic Sci 55:865–870

    Article  PubMed  Google Scholar 

  33. Ashiqur Rahman S, Giacobbi P, Pyles L, Mullett C, Doretto G, Adjeroh DA (2021) Deep learning for biological age estimation. Brief Bioinform 22:1767–1781

    Article  PubMed  Google Scholar 

  34. Jiang Y, Yang M, Wang S, Li X, Sun Y (2020) Emerging role of deep learning-based artificial intelligence in tumor pathology. Cancer Commun (Lond) 40:154–166

    Article  PubMed  Google Scholar 

  35. Wainberg M, Merico D, Delong A, Frey BJ (2018) Deep learning in biomedicine. Nat Biotechnol 36:829–838

    Article  CAS  PubMed  Google Scholar 

  36. González G, Ash SY, Vegas-Sánchez-Ferrero G et al (2018) Disease staging and prognosis in smokers using deep learning in chest computed tomography. Am J Respir Crit Care Med 197:193–203

    Article  PubMed  PubMed Central  Google Scholar 

  37. Shi W, Yan G, Li Y et al (2020) Fetal brain age estimation and anomaly detection using attention-based deep ensembles with uncertainty. Neuroimage 223:117316

    Article  PubMed  Google Scholar 

  38. Stahlschmidt SR, Ulfenborg B, Synnergren J (2022) Multimodal deep learning for biomedical data fusion: a review. Brief Bioinform 23(2):bbab569. https://doi.org/10.1093/bib/bbab569

  39. Pan Y, Liu M, Xia Y, Shen D (2022) Disease-image-specific learning for diagnosis-oriented neuroimage synthesis with incomplete multi-modality data. IEEE Trans Pattern Anal Mach Intell 44:6839–6853

    Article  PubMed  Google Scholar 

  40. Kang L, Jiang J, Huang J, Zhang T (2020) Identifying early mild cognitive impairment by multi-modality MRI-based deep learning. Front Aging Neurosci 12:206

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

We would like to thank the excellent professional support of our radiologists and computer experts. Besides, we thank our colleagues for their valuable insights and expertise that contributed to our research and professional assistance in the writing of the manuscript.

Funding

This study was funded by the National Natural Science Foundation of China (No. 81971801) and the Open Fund Project of Shanghai Key Lab of Forensic Medicine and Key Lab of Forensic Science (No. KF202209).

Author information

Author notes

  1. Ting Lu and Ya-ru Diao contributed equally to this work

Authors and Affiliations

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

    Ting Lu, Xian-e Tang, Fei Fan, Meng-jun Zhan, Guang-feng Liu, Yu-shan Lin, Zi-qi Cheng & Zhen-hua Deng

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

    Ya-ru Diao & Hu Chen

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

    Zhao Peng

  4. Department of Radiology, Beidaihe Hospital, Qinhuangdao, Hebei, 066100, People’s Republic of China

    Xu Yi & Yu-jun Wang

Authors
  1. Ting Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ya-ru Diao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xian-e Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fei Fan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhao Peng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Meng-jun Zhan
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Guang-feng Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Yu-shan Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Zi-qi Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Xu Yi
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Yu-jun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Hu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Zhen-hua Deng
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Hu Chen or Zhen-hua Deng.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Zhen-hua Deng, a Professor and the West China School of Basic Medical Sciences and Forensic Medicine, Sichuan University, Chengdu 610041, PR China. Email: dengzhenhua@scu.edu.cn.

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 has significant statistical expertise.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Study subjects or cohorts overlap

None.

Methodology

• Retrospective

• Observational study

• Performed at one institution

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 (PDF 1215 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

Lu, T., Diao, Yr., Tang, Xe. et al. Deep learning enables automatic adult age estimation based on CT reconstruction images of the costal cartilage. Eur Radiol 33, 7519–7529 (2023). https://doi.org/10.1007/s00330-023-09761-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09761-3

Keywords

Search

Navigation