Artificial Intelligence (AI)-Based Systems for Automatic Skeletal Maturity Assessment through Bone and Teeth Analysis: A Revolution in the Radiological Workflow?
Source abstract
Abstract
Bone age is an indicator of bone maturity and is useful for the treatment of different pediatric conditions as well as for legal issues. Bone age can be assessed by the analysis of different skeletal segments and teeth and through several methods; however, traditional bone age assessment is a complicated and time-consuming process, prone to inter- and intra-observer variability. There is a high demand for fully automated systems, but creating an accurate and reliable solution has proven difficult. Deep learning technology, machine learning, and Convolutional Neural Networks-based systems, which are rapidly evolving, have shown promising results in automated bone age assessment. We provide the background of bone age estimation, its usefulness and traditional methods of assessment, and review the currently artificial-intelligence-based solutions for bone age assessment and the future perspectives of these applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Forensic Anthropology and Bioarchaeology Studies · Dental Radiography and Imaging · Autopsy Techniques and Outcomes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Postgraduation School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono, 7, 20122 Milan, Italy
Dipartimento di Scienze Biomediche per la Salute, Via Luigi Mangiagalli 31, 20133 Milan, Italy
Radiology Department, San Raffaele Hospital, Via Olgettina 60, 20132 Milan, Italy
Radiology Department, Fatebenefratelli Hospital, ASST Fatebenefratelli Sacco, Piazza Principessa Clotilde 3, 20121 Milan, Italy
References (100+)
Show source-provided references
1. Bone age assessment methods: A critical review
2. Bone age: Assessment methods and clinical applications10.1297/cpe.24.143 ↗
3. Bone Age: A Handy Tool for Pediatric Providers10.1542/peds.2017-1486 ↗
4. The Use of Bone Age in Clinical Practice—Part 110.1159/000329372 ↗
5. Prediction of adult height by Tanner-Whitehouse method in young Caucasian male athletes10.1093/qjmed/hcs230 ↗
6. Incidence and Prevalence of Central Precocious Puberty in Korea: An Epidemiologic Study Based on a National Database10.1016/j.jpeds.2018.12.022 ↗
7. Assessment of Bone Age in Prepubertal Healthy Korean Children: Comparison among the Korean Standard Bone Age Chart, Greulich-Pyle Method, and Tanner-Whitehouse Method10.3348/kjr.2015.16.1.201 ↗
8. Evaluation of the pelvic apophysis with multi-detector computed tomography for legal age estimation in living individuals10.4103/1735-1995.156158 ↗
9. Greulich, W.W., and Pyle, S.I. (1959). Radiographic Atlas of Skeletal Development of the Hand and Wrist Professor of Anatomy, Stanford University School of Medicine.10.1097/00000441-195909000-00030 ↗
10. Gilsanz, V., and Ratib, O. (2005). Hand Bone Age: A Digital Atlas of Skeletal Maturity, Springer.
11. Accuracy of three age determination X-ray methods on the left hand-wrist: A systematic review and meta-analysis10.1016/j.legalmed.2011.01.004 ↗
12. Comparison of the Greulich-Pyle and Tanner Whitehouse (TW3) Methods in Bone age Assessment
13. Effect of Knowledge of Chronologic Age on the Variability of Pediatric Bone Age Determined Using the Greulich and Pyle Standards10.2214/ajr.176.2.1760507 ↗
14. The problem of aging human remains and living individuals: A review10.1016/j.forsciint.2009.09.008 ↗
15. Bone age assessment: A large scale comparison of the Greulich and Pyle, and Tanner and Whitehouse (TW2) methods10.1136/adc.81.2.172 ↗
16. Reynolds, B.C., Beattie, T.J., Ramage, I.J., Lucas, P., Law, C., and Baird, J. (2001). Assessment of Skeletal Maturity and Prediction of Adult Height (TW3 Method), W.B. Saunders. [3rd ed.].
17. Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment10.3348/kjr.2020.0941 ↗
18. A computational TW3 classifier for skeletal maturity assessment. A Computing with Words approach10.1016/j.jbi.2004.01.002 ↗
19. Forensic age estimation in living subjects based on the ossification status of the medial clavicular epiphysis as revealed by thin-slice multidetector computed tomography10.1007/s00414-009-0398-8 ↗
20. Discriminatory ability of the skeletal maturation index and the cervical vertebrae maturation index in detecting peak pubertal growth in Indonesian and white subjects with receiver operating characteristics analysis10.1016/j.ajodo.2006.09.062 ↗
21. Accuracy of the Sauvegrain Method in Determining Skeletal Age During Puberty
22. Skeletal age assessment from elbow radiographs. Review of the literature10.1007/s12306-008-0032-9 ↗
23. HANDX: A model-based system for automatic segmentation of bones from digital hand radiographs10.1109/42.20363 ↗
24. Artificial intelligence: Radiologists’ expectations and opinions gleaned from a nationwide online survey10.1007/s11547-020-01205-y ↗
25. A primer for understanding radiology articles about machine learning and deep learning10.1016/j.diii.2020.10.001 ↗
26. Radiomic analysis of the optic nerve at the first episode of acute optic neuritis: An indicator of optic nerve pathology and a predictor of visual recovery?10.1007/s11547-020-01318-4 ↗
27. A deep look into radiomics10.1007/s11547-021-01389-x ↗
28. Jung, A. (2022). Machine Learning, Springer Nature.10.1007/978-981-16-8193-6 ↗
29. Radiomics and machine learning analysis based on magnetic resonance imaging in the assessment of liver mucinous colorectal metastases10.1007/s11547-022-01501-9 ↗
30. Radiomics: Images Are More than Pictures, They Are Data10.1148/radiol.2015151169 ↗
31. Recent advances and clinical applications of deep learning in medical image analysis10.1016/j.media.2022.102444 ↗
32. Segmentation techniques of brain arteriovenous malformations for 3D visualization: A systematic review10.1007/s11547-022-01567-5 ↗
33. Accuracy of artificial intelligence for the detection of intracranial hemorrhage and chronic cerebral microbleeds: A systematic review and pooled analysis10.1007/s11547-022-01530-4 ↗
34. Chiu, H.-Y., Chao, H.-S., and Chen, Y.-M. (2022). Application of Artificial Intelligence in Lung Cancer. Cancers, 14.10.3390/cancers14061370 ↗
35. Machine learning concepts, concerns and opportunities for a pediatric radiologist10.1007/s00247-018-4277-7 ↗
36. Tan, X.J., Cheor, W.L., Lim, L.L., Ab Rahman, K.S., and Bakrin, I.H. (2022). Artificial Intelligence (AI) in Breast Imaging: A Scientometric Umbrella Review. Diagnostics, 12.10.3390/diagnostics12123111 ↗
37. Ullah, N., Khan, J.A., Almakdi, S., Khan, M.S., Alshehri, M., Alboaneen, D., and Raza, A. (2022). A Novel CovidDetNet Deep Learning Model for Effective COVID-19 Infection Detection Using Chest Radiograph Images. Appl. Sci., 12.10.3390/app12126269 ↗
38. Advanced CT techniques for assessing hepatocellular carcinoma10.1007/s11547-021-01366-4 ↗
39. Han, S., Lee, J., and Lee, S. (2022). Activation Fine-Tuning of Convolutional Neural Networks for Improved Input Attribution Based on Class Activation Maps. Appl. Sci., 12.10.3390/app122412961 ↗
40. Alshehri, A., and AlSaeed, D. (2022). Breast Cancer Detection in Thermography Using Convolutional Neural Networks (CNNs) with Deep Attention Mechanisms. Appl. Sci., 12.10.3390/app122412922 ↗
41. Development and validation of a 3D-convolutional neural network model based on chest CT for differentiating active pulmonary tuberculosis from community-acquired pneumonia
42. Deep learning and radiomics in precision medicine10.1080/23808993.2019.1585805 ↗
43. Effective Doses in Radiology and Diagnostic Nuclear Medicine: A Catalog10.1148/radiol.2481071451 ↗
44. Is the Greulich and Pyle atlas applicable to all ethnicities? A systematic review and meta-analysis10.1007/s00330-018-5792-5 ↗
45. New growth references for assessment of stature and skeletal maturation in Australians
46. Bone age in the 21st century: Is Greulich and Pyle’s atlas accurate for Israeli children?10.1007/s00247-011-2302-1 ↗
47. Is the assessment of bone age by the Greulich–Pyle method reliable at forensic age estimation for Turkish children?10.1016/j.forsciint.2007.02.023 ↗
48. Skeletal and chronological ages in American adolescents: Current findings in skeletal maturation10.1007/s11832-010-0289-z ↗
49. Comparison of bone age readings by pediatric endocrinologists and pediatric radiologists using two bone age atlases10.1007/s00247-010-1915-0 ↗
50. Comparative study of Gilsanz-Ratib digital atlas and Greulich-Pyle atlas for bone age estimation in a Chinese sample10.3109/03014460.2014.977346 ↗
51. The determination of bone age by the Greulich-Pyle and Tanner-Whitehouse methods as a basis for the growth prognosis of tall-stature girls
52. TW2 and TW3 bone ages: Time to change?10.1136/adc.2005.090134 ↗
53. Pediatric skeletal age: Determination with neural networks10.1148/radiology.195.3.7753995 ↗
54. The RSNA Pediatric Bone Age Machine Learning Challenge10.1148/radiol.2018180736 ↗
55. Mehta, C., Ayeesha, B., Sotakanal, A., Nirmala, S.R., Desai, S.D., Suryanarayana, K.V., Ganguly, A.D., and Shetty, V. (2021, January 1–5). Deep Learning Framework for Automatic Bone Age Assessment. Proceedings of the 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Virtual.10.1109/EMBC46164.2021.9629650 ↗
56. Improving Automated Pediatric Bone Age Estimation Using Ensembles of Models from the 2017 RSNA Machine Learning Challenge10.1148/ryai.2019190053 ↗
57. Generalizability and Bias in a Deep Learning Pediatric Bone Age Prediction Model Using Hand Radiographs10.1148/radiol.220505 ↗
58. Computerized Bone Age Estimation Using Deep Learning Based Program: Evaluation of the Accuracy and Efficiency10.2214/AJR.17.18224 ↗
59. Performance of a Deep-Learning Neural Network Model in Assessing Skeletal Maturity on Pediatric Hand Radiographs10.1148/radiol.2017170236 ↗
60. MABAL: A Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling10.1007/s10278-018-0053-3 ↗
61. Deep learning for automated skeletal bone age assessment in X-ray images10.1016/j.media.2016.10.010 ↗
62. Fully Automated Deep Learning System for Bone Age Assessment10.1007/s10278-017-9955-8 ↗
63. A Deep Automated Skeletal Bone Age Assessment Model with Heterogeneous Features Learning10.1007/s10916-018-1091-6 ↗
64. Xu, X., Xu, H., and Li, Z. (2022). Automated Bone Age Assessment: A New Three-Stage Assessment Method from Coarse to Fine. Healthcare, 10.10.3390/healthcare10112170 ↗
65. Bone Age Assessment in Young Children Using Automatic Carpal Bone Feature Extraction and Support Vector Regression10.1007/s10278-011-9372-3 ↗
66. Bone age assessment for young children from newborn to 7-year-old using carpal bones
67. Bai, M., Gao, L., Ji, M., Ge, J., Huang, L., Qiao, H., Xiao, J., Chen, X., Yang, B., and Sun, Y. (2022). The uncovered biases and errors in clinical determination of bone age by using deep learning models. Eur. Radiol., 1–13.10.1007/s00330-022-09330-0 ↗
68. The BoneXpert Method for Automated Determination of Skeletal Maturity10.1109/TMI.2008.926067 ↗
69. Zhao, K., Ma, S., Sun, Z., Liu, X., Zhu, Y., Xu, Y., and Wang, X. (2022). Effect of AI-assisted software on inter- and intra-observer variability for the X-ray bone age assessment of preschool children. BMC Pediatr., 22.10.1186/s12887-022-03727-y ↗
70. Artificial intelligence in bone age assessment: Accuracy and efficiency of a novel fully automated algorithm compared to the Greulich-Pyle method10.1186/s41747-019-0139-9 ↗
71. Automated Determination of Bone Age in a Modern Chinese Population10.5402/2013/874570 ↗
72. Validation and Reference Values of Automated Bone Age Determination for Four Ethnicities10.1016/j.acra.2010.06.007 ↗
73. Applicability of two bone age assessment methods to children from Saudi Arabia10.1016/j.crad.2019.08.029 ↗
74. Skeletal Maturation in the Current Pediatric Mexican Population10.4158/EP-2020-0047 ↗
75. Autonomous artificial intelligence in pediatric radiology: The use and perception of BoneXpert for bone age assessment10.1007/s00247-022-05295-w ↗
76. Schündeln, M.M., Marschke, L., Bauer, J.J., Hauffa, P.K., Schweiger, B., Führer-Sakel, D., Lahner, H., Poeppel, T.D., Kiewert, C., and Hauffa, B.P. (2016). A Piece of the Puzzle: The Bone Health Index of the BoneXpert Software Reflects Cortical Bone Mineral Density in Pediatric and Adolescent Patients. PLoS ONE, 11.10.1371/journal.pone.0151936 ↗
77. A review of the most commonly used dental age estimation techniques
78. Dental age estimation using the pulp-to-tooth ratio in canines by neural networks10.5624/isd.2019.49.1.19 ↗
79. Studies in Tooth Development: The Growth Pattern of Human Teeth10.14219/jada.archive.1940.0340 ↗
80. A new system of dental age assessment
81. The adaptation of Demirjian’s dental age estimation method on North German children10.1016/j.forsciint.2019.109927 ↗
82. Magon, P., and Viswanathan, V.K. (2008). “Bone Age”, Revision Classes in Pediatrics, Jaypee Brothers Medical Publishers (P) Ltd.10.5005/jp/books/10742 ↗
83. Correlation between Radiographic evaluation of dental age and chronological age: A study on 6 to 16 years human population of Ambala using Demirjian method
84. Dental Age Estimation in Belgian Children: Demirjian’s Technique Revisited10.1520/JFS15064J ↗
85. Age estimation of adults from dental radiographs10.1016/0379-0738(95)01760-G ↗
86. A non-destructive dental method for age estimation
87. Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images10.1007/s00414-021-02542-x ↗
88. Deep Neural Networks for Chronological Age Estimation From OPG Images10.1109/TMI.2020.2968765 ↗
89. Zaborowicz, K., Biedziak, B., Olszewska, A., and Zaborowicz, M. (2021). Tooth and Bone Parameters in the Assessment of the Chronological Age of Children and Adolescents Using Neural Modelling Methods. Sensors, 21.10.3390/s21186008 ↗
90. Zaborowicz, M., Zaborowicz, K., Biedziak, B., and Garbowski, T. (2022). Deep Learning Neural Modelling as a Precise Method in the Assessment of the Chronological Age of Children and Adolescents Using Tooth and Bone Parameters. Sensors, 22.10.3390/s22020637 ↗
91. Age-group determination of living individuals using first molar images based on artificial intelligence
92. Implementation of Artificial Intelligence in Chronological Age Estimation from Orthopantomographic X-ray Images of Archaeological Skull Remains
93. Automated estimation of chronological age from panoramic dental X-ray images using deep learning
94. Deep convolutional neural network designed for age as-sessment based on orthopantomography data10.1007/s00521-019-04449-6 ↗
95. Etude de la maturation osseuse du coude
96. Forensic age estimation using computed tomography of the medial clavicular epiphysis: A systematic review10.1007/s00414-018-1847-z ↗
97. Assessment of adulthood in the living Spanish population based on ossification of the medial clavicle epiphysis using ultrasound methods10.1016/j.forsciint.2018.01.007 ↗
98. Forensic age estimation using conventional radiography of the medial clavicular epiphysis: A systematic review10.1177/0025802420988223 ↗
99. Studies on the time frame for ossification of the medial clavicular epiphyseal cartilage in conventional radiography10.1007/s00414-003-0404-5 ↗
100. Bone age determination based on the study of the medial extremity of the clavicle10.1007/s003300050518 ↗