Abstract
Purpose
To develop a deep learning bone age assessment model based on pelvic radiographs for forensic age estimation and compare its performance to that of the existing cubic regression model.
Materials and method
A retrospective collection data of 1875 clinical pelvic radiographs between 10 and 25 years of age was obtained to develop the model. Model performance was assessed by comparing the testing results to estimated ages calculated directly using the existing cubic regression model based on ossification staging methods. The mean absolute error (MAE) and root-mean-squared error (RMSE) between the estimated ages and chronological age were calculated for both models.
Results
For all test samples (between 10 and 25 years old), the mean MAE and RMSE between the automatic estimates using the proposed deep learning model and the reference standard were 0.94 and 1.30 years, respectively. For the test samples comparable to those of the existing cubic regression model (between 14 and 22 years old), the mean MAE and RMSE for the deep learning model were 0.89 and 1.21 years, respectively. For the existing cubic regression model, the mean MAE and RMSE were 1.05 and 1.61 years, respectively.
Conclusion
The deep learning convolutional neural network model achieves performance on par with the existing cubic regression model, demonstrating predictive ability capable of automated skeletal bone assessment based on pelvic radiographic images.
Key Points
• The pelvis has considerable value in determining the bone age.
• Deep learning can be used to create an automated bone age assessment model based on pelvic radiographs.
• The deep learning convolutional neural network model achieves performance on par with the existing cubic regression model.
Similar content being viewed by others
Abbreviations
- CA:
-
Chronological age
- CNN:
-
Convolutional neural network
- EBA-CNN:
-
Bone age estimated by the CNN
- EBA-CR:
-
Bone age calculated by the cubic regression model
- ICA:
-
Ossification centre of the iliac crest
- IW:
-
Iliac wing
- KK-SM:
-
Kreitner and Kellinghaus ossification staging methods
- MAE:
-
Mean absolute difference
- RMSE:
-
Root-mean-squared error
- ROC:
-
Receiver operating characteristic
References
Schmeling A, Grundmann C, Fuhrmann A et al (2008) Criteria for age estimation in living individuals. Int J Legal Med 122:457
Bartolini V, Pinchi V, Gualco B et al (2018) The iliac crest in forensic age estimation: evaluation of three methods in pelvis X-rays. Int J Legal Med 132:1–10
Wittschieber D, Schmeling A, Schmidt S, Heindel W, Pfeiffer H, Vieth V (2013) The Risser sign for forensic age estimation in living individuals: a study of 643 pelvic radiographs. Forensic Sci Med Pathol 9:36–43
Zhang K, Dong XA, Chen XG, Li Y, Deng ZH (2015) Forensic age estimation through evaluation of the apophyseal ossification of the iliac crest in Western Chinese. Forensic Sci Int 252:192.e191–192.e195
Zhang K, Dong XA, Fan F, Deng ZH (2016) Age estimation based on pelvic ossification using regression models from conventional radiography. Int J Legal Med 130:1143–1148
Lottering N, Reynolds MS, Macgregor DM et al (2016) Apophyseal ossification of the iliac crest in forensic age estimation: computed tomography standards for modern Australian subadults. J Forensic Sci 62:292–307
Schmidt S, Schiborr M, Pfeiffer H, Schmeling A, Schulz R (2013) Sonographic examination of the apophysis of the iliac crest for forensic age estimation in living persons. Sci Justice 53:395–401
Schmidt S, Schmeling A, Zwiesigk P, Pfeiffer H, Schulz R (2011) Sonographic evaluation of apophyseal ossification of the iliac crest in forensic age diagnostics in living individuals. Int J Legal Med 125:271
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436
Esteva A, Kuprel B, Novoa RA et al (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118
Kermany DS, Goldbaum M, Cai W et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172:1122–1131.e1129
Gulshan V, Peng L, Coram M et al (2016) Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316:2402
Setio AA, Ciompi F, Litjens G et al (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35:1160–1169
Mansourvar M, Ismail MA, Herawan T, Raj RG, Kareem SA, Nasaruddin FH (2013) Automated bone age assessment: motivation, taxonomies, and challenges. Comput Math Methods Med 2013:391626–391626
Wang YH, Liu TA, Wei H, Wan L, Ying CL, Zhu GY (2016) Automated classification of epiphyses in the distal radius and ulna using a support vector machine. J Forensic Sci 61:409–414
Van Rijn RR, Thodberg HH (2013) Bone age assessment: automated techniques coming of age? Acta Radiol 54:1024
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 287:170236
Kim JR, Shim WH, Yoon HM et al (2017) Computerized bone age estimation using deep learning based program: evaluation of the accuracy and efficiency. AJR Am J Roentgenol 209:1
Lee H, Tajmir S, Lee J et al (2017) Fully automated deep learning system for bone age assessment. J Digit Imaging 30:427–441
Spampinato C, Palazzo S, Giordano D, Aldinucci M, Leonardi R (2016) Deep learning for automated skeletal bone age assessment in X-ray images. Med Image Anal 36:41–51
Mutasa S, Chang PD, Ruzal-Shapiro C, Ayyala R (2018) MABAL: a novel deep-learning architecture for machine-assisted bone age labeling. J Digit Imaging 9:1–7
Wittschieber D, Vieth V, Wierer T, Pfeiffer H, Schmeling A (2013) Cameriere’s approach modified for pelvic radiographs: a novel method to assess apophyseal iliac crest ossification for the purpose of forensic age diagnostics. Int J Legal Med 127(4):825–829
Wittschieber D, Vieth V, Domnick C, Pfeiffer H, Schmeling A (2013) The iliac crest in forensic age diagnostics: evaluation of the apophyseal ossification in conventional radiography. Int J Legal Med 127:473–479
Diedrichs V, Wagner UA, Seiler W, Schmitt O (1998) Reference values for development of the iliac crest apophysis (Risser sign). Z Orthop Ihre Grenzgeb 136:226
Coqueugniot H, Weaver TD (2007) Brief communication: Infracranial maturation in the skeletal collection from Coimbra, Portugal: new aging standards for epiphyseal union. Am J Phys Anthropol 134:424–437
Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. International Conference on Neural Information Processing Systems, pp 1097–1105
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE T Knowl Data En 22:1345–1359
Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks?. International Conference on Neural Information Processing Systems, pp 3320–3328
Cameriere R, Ferrante L, Belcastro MG, Bonfiglioli B, Rastelli E, Cingolani M (2007) Age estimation by pulp/tooth ratio in canines by mesial and vestibular peri-apical X-rays. J Forensic Sci 52:1151–1155
Corradi F, Pinchi V, Barsanti I, Garatti S (2013) Probabilistic classification of age by third molar development: the use of soft evidence. J Forensic Sci 58:51–59
Pinchi V, Norelli GA, Pradella F, Vitale G, Rugo D, Nieri M (2012) Comparison of the applicability of four odontological methods for age estimation of the 14 years legal threshold in a sample of Italian adolescents. J Forensic Odontostomatol 2:17–25
Pinchi V, Luca FD, Focardi M et al (2016) Combining dental and skeletal evidence in age classification: pilot study in a sample of Italian sub-adults. Leg Med (Tokyo) 20:75–79
Pinchi V, Luca FD, Ricciardi F et al (2014) Skeletal age estimation for forensic purposes: a comparison of GP, TW2 and TW3 methods on an Italian sample. Forensic Sci Int 238:83–90
Hoochang S, Roth HR, Gao M et al (2016) Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans Med Imaging 35:1285
Tajbakhsh N, Shin JY, Gurudu SR et al (2016) Convolutional neural networks for medical image analysis: fine tuning or full training? IEEE Trans Med Imaging 35:1299–1312
Zhang A, Sayre J, Vachon L, Liu B, Huang H (2009) Racial differences in growth patterns of children assessed on the basis of bone age. Radiology 250:228
Funding
The authors state that this work has not received any funding.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The scientific guarantor of this publication is Zhen-hua Deng.
Conflict of interest
The authors declare that they have no conflict of interest.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Informed consent
Informed consent was waived.
Ethical approval
This study was performed with the approval of the ethics committee of the West China Hospital of Sichuan University.
Study subjects or cohorts overlap
Some study subjects or cohorts have been previously reported in Zhang K, Dong XA, Fan F, Deng ZH (2016) Age estimation based on pelvic ossification using regression models from conventional radiography. International Journal of Legal Medicine 130:1143–1148.
Methodology
• Diagnostic or prognostic study
• Performed at one institution
Rights and permissions
About this article
Cite this article
Li, Y., Huang, Z., Dong, X. et al. Forensic age estimation for pelvic X-ray images using deep learning. Eur Radiol 29, 2322–2329 (2019). https://doi.org/10.1007/s00330-018-5791-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-018-5791-6