Accurate Age Determination for Adolescents Using Magnetic Resonance Imaging of the Hand and Wrist with an Artificial Neural Network-Based Approach
This study proposes an accurate method in assessing chronological age of the adolescents using a machine learning approach using MRI images. We also examined the value of MRI with Tanner-Whitehouse 3 (TW3) method in assessing skeletal maturity. Seventy-nine 12–17-year-old healthy Hong Kong Chinese adolescents were recruited. The left hand and wrist region were scanned by a dedicated skeletal MRI scanner. T1-weighted three-dimensional coronal view images for the left hand and wrist region were acquired. Independent maturity indicators such as subject body height, body weight, bone marrow composition intensity quantified by MRI, and TW3 skeletal age were included for artificial neural network (ANN) analysis. Our results indicated that the skeletal age was generally underestimated using TW3 method, and significant difference (p < 0.05) was noted for skeletal age with chronological age for female category and at later stage of adolescence (15 to 17 years old) in both genders. In our proposed machine learning approach, ages determined by ANN method agreed well with chronological age (p > 0.05).The machine learning approach using ANN method was about 10-fold more accurate than the TW3 method using MRI alone. It offers a more objective and accurate solution for prospective chronological maturity assessment for adolescents.
KeywordsSkeletal maturity Chronological age Machine learning Magnetic resonance imaging Artificial neural networks
Our thanks go to the students Chan Yiu Cheong, Chung Chin Pok, Kwok Man Yin, and Yim Ming Yeung who participated in this project.
This project is partially funded by the departmental one-line budget for Final Year Project of the Hong Kong Polytechnic University.
Compliance with Ethical Standards
Ethics approval was also obtained from the University Research Ethics Committee.
Conflict of Interest
The authors declare that they have no conflict of interest.
- 1.Tscholl PM, Junge A, Dvorak J, Zubler V. MRI of the wrist is not recommended for age determination in female football players of U-16/U-17 competitions. Scand J Med Sci Sports. 2016 Mar;26(3):324–8. https://doi.org/10.1111/sms.12461. Epub 2015 Apr 16.
- 2.Sarkodie BD, Ofori EK, Pambo P. MRI to determine the chronological age of Ghanaian footballers. The South African Journal of Sports Medicine, Vol 25, No 3 (2013)Google Scholar
- 3.Schmeling A, Geserick G, Reisinger W, Olze A: Age estimation. Forensic Sci Int. 165(2–3):178–181, 2007 Jan 17 Epub 2006 Jun 19Google Scholar
- 5.Mughal AM, Hassan N, Ahmed A: Bone age assessment methods: A critical review. Pak J Med Sci 30:211–215, 2013Google Scholar
- 10.Wikipedia: Artificial neural network. Retreived 15 December, 2017 from https://en.wikipedia.org/wiki/Artificial_neural_network.
- 11.Larson DB, Chen MC, Lungren MP, Halabi SS, Stence NV, Langlotz CP. Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Pediatric Hand Radiographs. Radiology Npv 2017.(ahead of print)Google Scholar
- 12.Bocchi L, Ferrara F, Nicoletti I, Valli G. An artificial neural network architecture for skeletal age assessment. In: Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on: IEEE, 2003:I-1077-1080 vol. 1071Google Scholar
- 14.Pynsent P, Fairbank J, Carr A. Assessment Methodology in Orthopaedics: Butterworth-Heinemann Medical, 1997Google Scholar
- 18.Griffith JF, Cheng JCY, Wong E: Are western skeletal age standards applicable to the Hong Kong Chinese population? A comparison of the Greulich and Pyle method and the Tanner and Whitehouse method. Hong Kong Medical Journal 13:28–32, 2007Google Scholar
- 22.Khan K, Elayappen AS. Bone growth estimation using radiology (Greulich–Pyle and Tanner–Whitehouse methods). In: Handbook of Growth and Growth Monitoring in Health and Disease: Springer, 2012:2937–2953Google Scholar