Bone age prediction from carpal radiographic images using deep learning
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1361Keywords:
Radiodiagnosis, Deep Learning, Bone AgeAbstract
Biological age, a crucial indicator of human development, reflects the physical and mental changes associated with aging. Estimating bone age, a common method in clinical practice that seeks information about biological age, can be subjective and imprecise. Objective: This study proposes methods based on deep learning techniques to estimate skeletal age from hand X-ray images. Methods: We used datasets divided by gender and age to train and test the models. Results: The results show promising estimates, with mean errors of 10.808 months in a public dataset and 15.548 months in a private dataset. The developed tool, with its intuitive graphical interface, offers practical use for medical professionals and researchers. Conclusion: This study applies deep learning to predict bone age, which can aid in assessing skeletal development in fields like pediatrics and orthopedics.
References
Prokop-Piotrkowska M, Marszałek-Dziuba K, Moszczyńska E, Szalecki M, Jurkiewicz E. Traditional and new methods of bone age assessment-an overview. J Clin Res Pediatric Endocrinology. 2021;13:251. DOI: https://doi.org/10.4274/jcrpe.galenos.2020.2020.0091
Dallora AL, Anderberg P, Kvist O, Mendes E, Diaz Ruiz S, Sanmartin Berglund J. Bone age assessment with various machine learning techniques: A systematic literature review and meta-analysis. PLoS One. 2019;14 DOI: https://doi.org/10.1371/journal.pone.0220242
Delorme AL. Automatic methodology for bone age estimation using shape analysis in carpal radiographs [dissertação de mestrado]. São Carlos: School of Engineering of São Carlos, University of São Paulo; 2010. [citado em 13 fev 2023].
Vrbaški S, Ito M, Moyano LG, de Santana VF. Characterization of breast tissues in density and effective atomic number basis via spectral X-ray computed tomography. Physics in Medicine & Biology. 2023;68(14):145019. DOI: https://doi.org/10.1088/1361-6560/acdbb6
Todd TW. Atlas of Skeletal Maturation. The C.V. Mosby Company; 1937. p. 37.
Olivete Júnior C, Rodrigues ELL. Bone maturity: estimation by simplifications of the Eklof and Ringertz method. Radiol Bras. 2010;43. DOI: https://doi.org/10.1590/S0100-39842010000100006
Halabi SS, et al. The RSNA pediatric bone age machine learning challenge. Radiology. 2019;290:498-503. DOI: https://doi.org/10.1148/radiol.2018180736
Zulkifley MA, Mohamed NA, Abdani SR, Kamari NAM, Moubark AM, Ibrahim AA. Intelligent bone age assessment: an automated system to detect a bone growth problem using convolutional neural networks with attention mechanism. Diagnostics. 2021;11(5):765. DOI: https://doi.org/10.3390/diagnostics11050765
An DY. Bone age estimation using mosaics of ossification centers from carpal radiographs as input images for Deep Learning [dissertação de mestrado]. Espírito Santo: Federal Institute of Espírito Santo; 2017.
Lee H, et al. Fully Automated Deep Learning System for Bone Age Assessment. Boston: Springer; 2017. p. 30, 427-441. DOI: https://doi.org/10.1007/s10278-017-9955-8
Tuma CESN, et al. Assessment of bone age in children aged 9 to 12 years in the city of Manaus-AM. Dental Press J Orthod. 2011;16(3):63-69. DOI: https://doi.org/10.1590/S2176-94512011000300008
Pinto VCM, et al. Relationship of bone age and hormonal markers with the physical capacity of adolescents. J Hum Growth Dev. 2017;27(1):77-83. DOI: https://doi.org/10.7322/jhgd.127658
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
