Abstract
Introduction: Bone age is an important parameter for the determination of human skeletal development, which is determined manually by the Greulich and Pyle method. This makes obtaining bone age impractical. Artificial intelligence programs and applications have been developed with the aim of optimizing bone age reading, one of them being the automated BoneXpert (BE) software. Scientific studies have determined the efficacy of this method when compared with the conventional Greulich and Pyle method, which favors its use in daily clinical practice.
Objective: Correlate results of bone age obtained by the Greulich and Pyle method versus BoneXpert automated software.
Methods: Descriptive, retrospective study, performed with hand radiographs available in the database of the Herrera Llerandi Hospital. Radiographs with bone age reports available from 2021 to 2022 were used.
Results: 20 cases were included, 9 female (45%) and 11 male (55%), the mean chronological age was 8.98 years. The correlation between bone age by conventional method (GP) and bone age by automated software (BE) was 0.978 suggesting a high correlation. It is concluded that the BoneXpert automated software has a high diagnostic accuracy when compared with the conventional method of Greulich and Pyle, giving it the virtue of being used as a diagnostic tool.
Keywords: Bone age, Greulich and Pyle, BoneXpert, Bone age correlation, Artificial Intelligence.
References
- Cavallo, F., Mohn, A., Chiarelli, F., & Giannini, C. Evaluation of Bone Age in Children: A Mini-Review. Frontiers in Pediatrics, 2021, March; 9. https://doi.org/10.3389/fped.2021.580314 DOI: https://doi.org/10.3389/fped.2021.580314
- De Sanctis, V., Di Maio, S., Soliman, A.T., Raiola, G., Elalaily, R., Millimaggi, G. Hand X-ray in pediatric endocrinology: Skeletal age assessment and beyond. Indian Journal of Endocrinol Metab. 2014, Nov.; 18(Suppl 1): S63-71. DOI: 10.4103/2230-8210.145076 . DOI: https://doi.org/10.4103/2230-8210.145076
- Thodberg, H. H., Kreiborg, S., Juul, A., & Pedersen, K. D. The BoneXpert method for automated determination of skeletal maturity. IEEE Transactions on Medical Imaging, 2009, Jan. 28(1): 52-66. https://doi.org/10.1109/TMI.2008.926067 DOI: https://doi.org/10.1109/TMI.2008.926067
- Satoh, M. Bone age: Assessment methods and clinical applications. Clinical Pediatric Endocrinology, 2015, Oct.; 24(4): 143-152. https://doi.org/10.1297/cpe.24.143 DOI: https://doi.org/10.1297/cpe.24.143
- Thodberg, H. H., Thodberg, B., Ahlkvist, J., & Offiah, A. C. Autonomous artificial intelligence in pediatric radiology: the use and perception of BoneXpert for bone age assessment. Pediatric Radiology, 2022, Feb., 52(7): 1338-1346. https://doi.org/10.1007/s00247-022-05295-w DOI: https://doi.org/10.1007/s00247-022-05295-w
- Gerges, M., Eng, H., Chhina, H., & Cooper, A. Modernization of bone age assessment: comparing the accuracy and reliability of an artificial intelligence algorithm and shorthand bone age to Greulich and Pyle. Skeletal Radiology, 2020, April; 49(9): 1449-1457. https://doi.org/10.1007/s00256-020-03429-5 DOI: https://doi.org/10.1007/s00256-020-03429-5
- Pose Lepe, G., Villacrés, F., Silva Fuente-Alba, C., & Guiloff, S. Correlación en la determinación de la edad ósea radiológica mediante el método de Greulich y Pyle versus la evaluación automatizada utilizando el software BoneXpert. Revista Chilena de Pediatría, 2018, Oct.; 89(5): 606-611. https://doi.org/10.4067/s0370-41062018005000705 DOI: https://doi.org/10.4067/S0370-41062018005000705
- Artioli, T.O., Alvares, M.A., Carvalho Macedo, et al. Bone age determination in eutrophic, overweight and obese Brazilian children and adolescents: a comparison between computerized BoneXpert and Greulich-Pyle methods. Pediatr Radiol. 2019, Aug.; 49(9): 1185-1191. DOI: 10.1007/s00247-019-04435-z DOI: https://doi.org/10.1007/s00247-019-04435-z
- Bowden, J.J., Bowden, S.A., Ruess, L., et al. Validation of automated bone age analysis from hand radiographs in a North American pediatric population. Pediatr Radiol. 2022, Jun.; 52(7): 1347-1355. DOI: 10.1007/s00247-022-05310-0 . DOI: https://doi.org/10.1007/s00247-022-05310-0