Abstract
Purpose
To develop and test the performance of deep convolutional neural networks (DCNNs) for automated classification of age and sex on chest radiographs (CXR).
Methods
We obtained 112,120 frontal CXRs from the NIH ChestX-ray14 database performed in 48,780 females (44%) and 63,340 males (56%) ranging from 1 to 95 years old. The dataset was split into training (70%), validation (10%), and test (20%) datasets, and used to fine-tune ResNet-18 DCNNs pretrained on ImageNet for (1) determination of sex (using entire dataset and only pediatric CXRs); (2) determination of age < 18 years old or ≥ 18 years old (using entire dataset); and (3) determination of age < 11 years old or 11–18 years old (using only pediatric CXRs). External testing was performed on 662 CXRs from China. Area under the receiver operating characteristic curve (AUC) was used to evaluate DCNN test performance.
Results
DCNNs trained to determine sex on the entire dataset and pediatric CXRs only had AUCs of 1.0 and 0.91, respectively (p < 0.0001). DCNNs trained to determine age < or ≥ 18 years old and < 11 vs. 11–18 years old had AUCs of 0.99 and 0.96 (p < 0.0001), respectively. External testing showed AUC of 0.98 for sex (p = 0.01) and 0.91 for determining age < or ≥ 18 years old (p < 0.001).
Conclusion
DCNNs can accurately predict sex from CXRs and distinguish between adult and pediatric patients in both American and Chinese populations. The ability to glean demographic information from CXRs may aid forensic investigations, as well as help identify novel anatomic landmarks for sex and age.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10140-021-01953-y/MediaObjects/10140_2021_1953_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10140-021-01953-y/MediaObjects/10140_2021_1953_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10140-021-01953-y/MediaObjects/10140_2021_1953_Fig3_HTML.png)
Similar content being viewed by others
Data availability
The source data utilized in this study is publicly available.
Code availability
Our code utilizes standard methodologies and software packages that are described in the manuscript to allow independent replication.
References
McCormick WF, Stewart JH, Langford LA (1985) Sex determination from chest plate roentgenograms. Am J Phys Anthropol 68:173–195. https://doi.org/10.1002/ajpa.1330680205
Torwalt CRMM, Hoppa RD (2005) A test of sex determination from measurements of chest radiographs. J Forensic Sci 50:785–790
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:S3–S12. https://doi.org/10.1111/j.1556-4029.2010.01626.x
Yoon SH, Yoo HJ, Yoo R-E et al (2016) Ossification of the medial clavicular epiphysis on chest radiographs: utility and diagnostic accuracy in identifying Korean adolescents and young adults under the age of majority. J Korean Med Sci 31:1538. https://doi.org/10.3346/jkms.2016.31.10.1538
Xue Z, Antani S, Long R, Thoma GR (2018) Using deep learning for detecting gender in adult chest radiographs. In: Zhang J, Chen P-H (eds) Medical Imaging 2018: Imaging Informatics for Healthcare, Research, and Applications. https://doi.org/10.1117/12.2293027
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539
Yune S, Lee H, Kim M et al (2018) Beyond human perception: sexual dimorphism in hand and wrist radiographs is discernible by a deep learning model. J Digit Imaging. https://doi.org/10.1007/s10278-018-0148-x
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. ar**v:1705.02315
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. ar**v:1512.03385
Russakovsky O, Deng J, Su H, et al (2014) ImageNet large scale visual recognition challenge. ar**v:1409.0575
Zhou B, Khosla A, Lapedriza A, et al (2015) Learning deep features for discriminative localization. 2921–2929. https://doi.org/10.1109/CVPR.2016.319
**n J, Zhang Y, Tang Y, Yang Y (2019) Brain differences between men and women: evidence from deep learning. Front Neurosci 13:185. https://doi.org/10.3389/fnins.2019.00185
Sabottke CF, Breaux MA, Spieler BM (2020) Estimation of age in unidentified patients via chest radiography using convolutional neural network regression. Emerg Radiol 27:463–468. https://doi.org/10.1007/s10140-020-01782-5
Zech JR, Badgeley MA, Liu M et al (2018) Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLOS Med 15:e1002683. https://doi.org/10.1371/journal.pmed.1002683
Acknowledgements
We thank Tae Soo Kim, MSE, for technical advising.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
This work utilized publicly available data and was considered not human subjects research by our institutional review board.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yi, P.H., Wei, J., Kim, T.K. et al. Radiology “forensics”: determination of age and sex from chest radiographs using deep learning . Emerg Radiol 28, 949–954 (2021). https://doi.org/10.1007/s10140-021-01953-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10140-021-01953-y