A Comparison of Automatic Bone Age Assessments between the Left and Right Hands: A Tool for Filtering Measurement Errors
Abstract
:1. Introduction
2. Materials and Methods
2.1. Model Development
2.2. Statistical Analyses
3. Results
4. Discussion
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Zerin, J.M.; Hernandez, R.J. Approach to skeletal maturation. Hand Clin. 1991, 7, 53–62. [Google Scholar] [CrossRef] [PubMed]
- Oh, M.S.; Kim, S.; Lee, J.; Lee, M.S.; Kim, Y.J.; Kang, K.S. Factors associated with Advanced Bone Age in Overweight and Obese Children. Pediatr. Gastroenterol. Hepatol. Nutr. 2020, 23, 89–97. [Google Scholar] [CrossRef] [PubMed]
- Kim, D.; Cho, S.Y.; Maeng, S.H.; Yi, E.S.; Jung, Y.J.; Park, S.W.; Sohn, Y.B.; Jin, D.K. Diagnosis and constitutional and laboratory features of Korean girls referred for precocious puberty. Korean J. Pediatr. 2012, 55, 481–486. [Google Scholar] [CrossRef] [PubMed]
- Greulich, W.W.; Pyle, S.I. Radiographic Atlas of Skeletal Development of the Hand and Wrist, 2nd ed.; Stanford University Press: Stanford, CA, USA, 1959. [Google Scholar]
- Malina, R.M.; Beunen, G.P. Assessment of skeletal maturity and prediction of adult height (TW3 method). Third edition. Am. J. Hum. Biol. 2002, 14, 788–789. [Google Scholar] [CrossRef]
- Berst, M.J.; Dolan, L.; Bogdanowicz, M.M.; Stevens, M.A.; Chow, S.; Brandser, E.A. Effect of knowledge of chronologic age on the variability of pediatric bone age determined using the Greulich and Pyle standards. AJR Am. J. Roentgenol. 2001, 176, 507–510. [Google Scholar] [CrossRef] [PubMed]
- Bull, R.K.; Edwards, P.D.; Kemp, P.M.; Fry, S.; Hughes, I.A. Bone age assessment: A large scale comparison of the Greulich and Pyle, and Tanner and Whitehouse (TW2) methods. Arch. Dis. Child. 1999, 81, 172–173. [Google Scholar] [CrossRef] [PubMed]
- Lee, B.D.; Lee, M.S. Automated Bone Age Assessment Using Artificial Intelligence: The Future of Bone Age Assessment. Korean J. Radiol. 2021, 22, 792–800. [Google Scholar] [CrossRef] [PubMed]
- Kim, J.R.; Shim, W.H.; Yoon, H.M.; Hong, S.H.; Lee, J.S.; Cho, Y.A.; Kim, S. Computerized Bone Age Estimation Using Deep Learning Based Program: Evaluation of the Accuracy and Efficiency. AJR Am. J. Roentgenol. 2017, 209, 1374–1380. [Google Scholar] [CrossRef] [PubMed]
- Eng, D.K.; Khandwala, N.B.; Long, J.; Fefferman, N.R.; Lala, S.V.; Strubel, N.A.; Milla, S.S.; Filice, R.W.; Sharp, S.E.; Towbin, A.J.; et al. Artificial Intelligence Algorithm Improves Radiologist Performance in Skeletal Age Assessment: A Prospective Multicenter Randomized Controlled Trial. Radiology 2021, 301, 692–699. [Google Scholar] [CrossRef]
- Lee, K.C.; Lee, K.H.; Kang, C.H.; Ahn, K.S.; Chung, L.Y.; Lee, J.J.; Hong, S.J.; Kim, B.H.; Shim, E. Clinical Validation of a Deep Learning-Based Hybrid (Greulich-Pyle and Modified Tanner-Whitehouse) Method for Bone Age Assessment. Korean J. Radiol. 2021, 22, 2017–2025. [Google Scholar] [CrossRef]
- Booz, C.; Yel, I.; Wichmann, J.L.; Boettger, S.; Al Kamali, A.; Albrecht, M.H.; Martin, S.S.; Lenga, L.; Huizinga, N.A.; D’Angelo, T.; et al. Artificial intelligence in bone age assessment: Accuracy and efficiency of a novel fully automated algorithm compared to the Greulich-Pyle method. Eur. Radiol. Exp. 2020, 4, 6. [Google Scholar] [CrossRef] [PubMed]
- Lee, H.; Tajmir, S.; Lee, J.; Zissen, M.; Yeshiwas, B.A.; Alkasab, T.K.; Choy, G.; Do, S. Fully Automated Deep Learning System for Bone Age Assessment. J. Digit. Imaging 2017, 30, 427–441. [Google Scholar] [CrossRef] [PubMed]
- Spampinato, C.; Palazzo, S.; Giordano, D.; Aldinucci, M.; Leonardi, R. Deep learning for automated skeletal bone age assessment in X-ray images. Med. Image Anal. 2017, 36, 41–51. [Google Scholar] [CrossRef] [PubMed]
- Ren, X.; Li, T.; Yang, X.; Wang, S.; Ahmad, S.; Xiang, L.; Stone, S.R.; Li, L.; Zhan, Y.; Shen, D.; et al. Regression Convolutional Neural Network for Automated Pediatric Bone Age Assessment from Hand Radiograph. IEEE J. Biomed. Health Inform. 2019, 23, 2030–2038. [Google Scholar] [CrossRef] [PubMed]
- Mutasa, S.; Chang, P.D.; Ruzal-Shapiro, C.; Ayyala, R. MABAL: A Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling. J. Digit. Imaging 2018, 31, 513–519. [Google Scholar] [CrossRef] [PubMed]
- Tajmir, S.H.; Lee, H.; Shailam, R.; Gale, H.I.; Nguyen, J.C.; Westra, S.J.; Lim, R.; Yune, S.; Gee, M.S.; Do, S. Artificial intelligence-assisted interpretation of bone age radiographs improves accuracy and decreases variability. Skelet. Radiol. 2019, 48, 275–283. [Google Scholar] [CrossRef] [PubMed]
- Shin, N.Y.; Lee, B.D.; Kang, J.H.; Kim, H.R.; Oh, D.H.; Lee, B.I.; Kim, S.H.; Lee, M.S.; Heo, M.S. Evaluation of the clinical efficacy of a TW3-based fully automated bone age assessment system using deep neural networks. Imaging Sci. Dent. 2020, 50, 237–243. [Google Scholar] [CrossRef]
- Martin, D.D.; Sato, K.; Sato, M.; Thodberg, H.H.; Tanaka, T. Validation of a new method for automated determination of bone age in Japanese children. Horm. Res. Paediatr. 2010, 73, 398–404. [Google Scholar] [CrossRef] [PubMed]
- Wittschieber, D.; Vieth, V.; Wierer, T.; Pfeiffer, H.; Schmeling, A. 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. Leg. Med. 2013, 127, 825–829. [Google Scholar] [CrossRef]
- Li, Z.; Chen, W.; Ju, Y.; Chen, Y.; Hou, Z.; Li, X.; Jiang, Y. Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction. Front. Artif. Intell. 2023, 6, 1142895. [Google Scholar] [CrossRef]
- Roche, A.F.; Chumlea, W.; Thissen, D. Assessing the Skeletal Maturity of the Hand-Wrist: Fels Method; Thomas: Springfield, IL, USA, 1988. [Google Scholar]
- Baer, M.J.; Djrkatz, J. Bilateral asymmetry in skeletal maturation of the hand and wrist: A roentgenographic analysis. Am. J. Phys. Anthropol. 1957, 15, 181–196. [Google Scholar] [CrossRef] [PubMed]
- Germanese, D.; Colantonio, S.; Del Coco, M.; Carcagnì, P.; Leo, M. Computer Vision Tasks for Ambient Intelligence in Children’s Health. Information 2023, 14, 548. [Google Scholar] [CrossRef]
- Kim, S.U.; Oh, S.; Lee, K.H.; Kang, C.H.; Ahn, K.S. Improvement of Bone Age Assessment Using a Deep Learning Model in Young Children: Significance of Carpal Bone Analysis. Iran. J. Radiol. 2023, 20, e136311. [Google Scholar] [CrossRef]
- Gerke, O. Reporting Standards for a Bland-Altman Agreement Analysis: A Review of Methodological Reviews. Diagnostics 2020, 10, 334. [Google Scholar] [CrossRef] [PubMed]
- Benchoufi, M.; Matzner-Lober, E.; Molinari, N.; Jannot, A.S.; Soyer, P. Interobserver agreement issues in radiology. Diagn. Interv. Imaging 2020, 101, 639–641. [Google Scholar] [CrossRef]
- Papadatou-Pastou, M.; Ntolka, E.; Schmitz, J.; Martin, M.; Munafò, M.R.; Ocklenburg, S.; Paracchini, S. Human handedness: A meta-analysis. Psychol. Bull. 2020, 146, 481–524. [Google Scholar] [CrossRef] [PubMed]
- Tanner, J.M.; Gibbons, R.D. A computerized image analysis system for estimating Tanner-Whitehouse 2 bone age. Horm. Res. 1994, 42, 282–287. [Google Scholar] [CrossRef] [PubMed]
- Sato, K.; Ashizawa, K.; Anzo, M.; Otsuki, F.; Kaneko, S.; Tanaka, T.; Tsukagoshi, K.; Nimura, A.; Matsuoka, H.; Matsuo, N.; et al. Setting up an automated system for evaluation of bone age. Endocr. J. 1999, 46, S97–S100. [Google Scholar] [CrossRef] [PubMed]
- Thodberg, H.H.; Kreiborg, S.; Juul, A.; Pedersen, K.D. The BoneXpert Method for Automated Determination of Skeletal Maturity. IEEE Trans. Med. Imaging 2009, 28, 52–66. [Google Scholar] [CrossRef]
- Martin, D.D.; Calder, A.D.; Ranke, M.B.; Binder, G.; Thodberg, H.H. Accuracy and self-validation of automated bone age determination. Sci. Rep. 2022, 12, 6388. [Google Scholar] [CrossRef]
- 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. Pediatr. Radiol. 2022, 52, 1338–1346. [Google Scholar] [CrossRef] [PubMed]
- Martin, D.D.; Neuhof, J.; Jenni, O.G.; Ranke, M.B.; Thodberg, H.H. Automatic determination of left- and right-hand bone age in the First Zurich Longitudinal Study. Horm. Res. Paediatr. 2010, 74, 50–55. [Google Scholar] [CrossRef] [PubMed]
- van Rijn, R.R.; Thodberg, H.H. Bone age assessment: Automated techniques coming of age? Acta Radiol. 2013, 54, 1024–1029. [Google Scholar] [CrossRef] [PubMed]
- Ontell, F.K.; Ivanovic, M.; Ablin, D.S.; Barlow, T.W. Bone age in children of diverse ethnicity. AJR Am. J. Roentgenol. 1996, 167, 1395–1398. [Google Scholar] [CrossRef] [PubMed]
- Zhang, A.; Sayre, J.W.; Vachon, L.; Liu, B.J.; Huang, H.K. Racial differences in growth patterns of children assessed on the basis of bone age. Radiology 2009, 250, 228–235. [Google Scholar] [CrossRef]
Variables | Total (n = 757) | Male (n = 321) | Female (n = 436) |
---|---|---|---|
Age, years a | 8.75 ± 2.66 | 9.49 ± 3.06 | 8.21 ± 2.18 |
Age distribution, years | |||
<5 | 56/757 (7.4%) | 23/321 (7.2%) | 33/436 (7.6%) |
≥5 and <10 | 495/757 (65.8%) | 161/321 (50.2%) | 337/436 (77.3%) |
≥10 and < 15 | 190/757 (25.1%) | 126/321 (39.3%) | 64/436 (14.7%) |
≥15 | 13/757 (1.7%) | 11/321 (3.4%) | 2/436 (0.5%) |
Automatic bone age assessment by the model | 0.775 | ||
Left hand a | 9.15 ± 3.21 | 9.85 ± 3.72 | 8.63 ± 2.67 |
Right hand a | 9.20 ± 3.23 | 9.90 ± 3.72 | 8.69 ± 2.72 |
ADBH model b | 0.23 ± 0.19 (0.22, 0.25) | 0.24 ± 0.19 (0.22, 0.26) | 0.23 ± 0.19 (0.21, 0.25) |
<0.25 | 510/757 (67.4%) | 215/321 (67.0%) | 295/436 (67.7%) |
≥0.25 and <0.5 | 188/757 (24.8%) | 80/321 (24.9%) | 108/436 (24.8%) |
≥0.5 and <0.75 | 48/757 (6.3%) | 20/321 (6.2%) | 28/436 (6.4%) |
≥0.75 and <1 | 11/757 (1.5%) | 6/321 (1.9%) | 5/436 (1.1%) |
Variables | ADBH Model ≤ 0.5 Year (n = 698) | ADBH Model > 0.5 Year (n = 59) | p Value |
---|---|---|---|
Age, years a | 8.77 ± 2.66 | 8.55 ± 2.73 | 0.555 |
Male-to-female ratio | 295:403 | 26:33 | 0.788 |
Left-hand BAA a | 9.18 ± 3.21 | 8.78 ± 2.27 | 0.356 |
Right-hand BAA a | 9.22 ± 3.22 | 9.00 ± 3.39 | 0.620 |
ADBH model b | 0.198 ± 0.145 (0.187, 0.209) | 0.667 ± 0.109 (0.638, 0.695) | <0.001 |
Developmental stage | 0.025 | ||
Pre-puberty | 201/698 (28.2%) | 26/59 (44.1%) | 0.018 |
Early and mid-puberty | 462/698 (66.2%) | 29/59 (49.2%) | 0.010 |
Late puberty | 28/698 (4.0%) | 2/59 (3.4%) | 1.000 |
Post puberty | 7/698 (1.0%) | 2/59 (3.4%) | 0.151 |
Left Hand | Right Hand | p Value | |
---|---|---|---|
Automatic bone age assessment by the model | 8.78 ± 3.27 | 9.00 ± 3.39 | 0.011 |
Reference standard bone age reference by two reviewers | 8.93 ± 3.29 | 8.89 ± 3.33 | 0.157 |
Mean absolute difference a | 0.409 ± 0.335 (0.322, 0.467) | 0.424 ± 0.329 (0.339, 0.510) | 0.809 |
Median | 0.354 | 0.330 | |
Range | 0–1.75 | 0–1.33 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Lee, K.-C.; Kang, C.H.; Ahn, K.-S.; Lee, K.-H.; Lee, J.J.; Cho, K.R.; Oh, S. A Comparison of Automatic Bone Age Assessments between the Left and Right Hands: A Tool for Filtering Measurement Errors. Appl. Sci. 2024, 14, 8135. https://doi.org/10.3390/app14188135
Lee K-C, Kang CH, Ahn K-S, Lee K-H, Lee JJ, Cho KR, Oh S. A Comparison of Automatic Bone Age Assessments between the Left and Right Hands: A Tool for Filtering Measurement Errors. Applied Sciences. 2024; 14(18):8135. https://doi.org/10.3390/app14188135
Chicago/Turabian StyleLee, Kyu-Chong, Chang Ho Kang, Kyung-Sik Ahn, Kee-Hyoung Lee, Jae Joon Lee, Kyu Ran Cho, and Saelin Oh. 2024. "A Comparison of Automatic Bone Age Assessments between the Left and Right Hands: A Tool for Filtering Measurement Errors" Applied Sciences 14, no. 18: 8135. https://doi.org/10.3390/app14188135