Artificial Intelligence in Bone Age Assessment of Pediatric Hand-Wrist X-Rays: Systematic Review and Meta-Analysis of Studies from 2019–2024
Main Article Content
Abstract
Objective: Bone age assessment (BAA) is implemented in various medical fields This study aimed to conduct a systematic review and meta-analysis of studies published in 2019–2024 regarding the use of artificial intelligence (AI) and machine learning (ML) in bone age assessment (BAA).
Methodology: This study was conducted in accordance with the PRISMA guidelines. Three databases (PubMed, Scopus, and Cochrane) were screened for studies published from 2019–2024. Two reviewers independently selected the studies. The modified Kitchenham-Charters’ checklist was used to critically appraise the studies. Only studies reporting the mean absolute error (MAE) were included in the analysis. Data regarding the study characteristics, subject characteristics, ML technique, model ground truth, and the performance of the studies were extracted.
Results: The review included 33 studies, mostly from East Asia. Most studies used in-house datasets consisting of hand radiographs of their respective local population. Convolutional neural networks are the most popular AI algorithm used. Most studies used radiologist-annotated BA as ground truth rather than the chronological age. The meta-analysis revealed a weighted MAE of 7.54 months, an improvement compared to the previous study.
Conclusion: AI and ML models continue to demonstrate rapid advancements in their application for BAA. This study described the current trends in ML research and explored ongoing obstacles in BAA, as well as the prospective role of AI. While promising, further research is still required to address current limitations, such as validity issues. Subsequent studies should also be conducted with rigorous methodology and thorough reporting.
Article Details
Work published in JPMI is licensed under a
Creative Commons Attribution-NonCommercial 2.0 Generic License.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
References
Cavallo F, Mohn A, Chiarelli F, Giannini C. Evaluation of Bone Age in Children: A Mini-Review. Front Pediatr. 2021 Mar 12;9.
Franklin D, Flavel A, Noble J, Swift L, Karkhanis S. Forensic age estimation in living individuals: methodological considerations in the context of medico-legal practice. Research and Reports in Forensic Medical Science. 2015 Oct;53.
Prokop-Piotrkowska M, Marszalek-Dziuba K, Moszczynska E, Szalecki M, Jurkiewicz E. Traditional and New Methods of Bone Age Assessment-An Overview. J Clin Res Pediatr Endocrinol. 2021 Aug 23;13(3):251–62.
Halabi SS, Prevedello LM, Kalpathy-Cramer J, Mamonov AB, Bilbily A, Cicero M, et al. The RSNA Pediatric Bone Age Machine Learning Challenge. Radiology. 2019 Feb;290(2):498–503.
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. Stoean R, editor. PLoS One. 2019 Jul 25;14(7):e0220242.
Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: An updated guideline for reporting systematic reviews. The BMJ. 2021;372:n71.
Kitchenham B, Charters SM. Guidelines for performing systematic literature reviews in software engineering (Version 2.3). Software Engineering Technical Report EBSE-2007-0. 2007. Available from: https://legacyfileshare.elsevier.com/promis_misc/525444systematicreviewsguide.pdf.
Dallora AL. machine learning techniques in the automated age assessment of youth Investigating the employment of. Karlskrona: Blekinge Institute of Technology; 2019. p. 6.
Escobar M, Gonzalez C, Torres F, Daza L, Triana G, Arbelaez P. Hand Pose Estimation for Pediatric Bone Age Assessment. In: Shen D, Liu T, Peters TM, Staib LH, Essert C, Zhou S, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Shenzhen: Springer; 2019. p. 531–9.
Liu Y, Zhang C, Cheng J, Chen X, Wang ZJ. A multi-scale data fusion framework for bone age assessment with convolutional neural networks. Comput Biol Med. 2019 May;108:161–73.
Liu B, Zhang Y, Chu M, Bai X, Zhou F. Bone Age Assessment Based on Rank-Monotonicity Enhanced Ranking CNN. IEEE Access. 2019;7:120976–83.
Booz C, Yel I, Wichmann JL, Boettger S, Al Kamali A, Albrecht MH, 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 Dec 28;4(1):6.
Dehghani F, Karimian A, Sirous M. Assessing the Bone Age of Children in an Automatic Manner Newborn to 18 Years Range. J Digit Imaging. 2020 Apr 6;33(2):399–407.
Guo J, Zhu J, Du H, Qiu B. A bone age assessment system for real-world X-ray images based on convolutional neural networks. Computers & Electrical Engineering. 2020 Jan;81:106529.
Koitka S, Kim MS, Qu M, Fischer A, Friedrich CM, Nensa F. Mimicking the radiologists’ workflow: Estimating pediatric hand bone age with stacked deep neural networks. Med Image Anal. 2020 Aug;64:101743.
Reddy NE, Rayan JC, Annapragada A V., Mahmood NF, Scheslinger AE, Zhang W, et al. Bone age determination using only the index finger: a novel approach using a convolutional neural network compared with human radiologists. Pediatr Radiol. 2020 Apr 20;50(4):516–23.
Zulkifley MA, Abdani SR, Zulkifley NH. Automated Bone Age Assessment with Image Registration Using Hand X-ray Images. Applied Sciences. 2020 Oct 16;10(20):7233.
Cheng CF, Huang ET-C, Kuo J-T, Liao KY-K, Tsai F. Report of Clinical Bone Age Assessment using Deep Learning for an Asian population in Taiwan. Biomedicine (Taipei). 2021 Aug 25;11(3):50–8.
He J, Jiang D. Fully Automatic Model Based on SE-ResNet for Bone Age Assessment. IEEE Access. 2021;9:62460–6.
Lee K-C, Lee K-H, Kang CH, Ahn K-S, Chung LY, Lee J-J, et al. Clinical Validation of a Deep Learning-Based Hybrid (Greulich-Pyle and Modified Tanner-Whitehouse) Method for Bone Age Assessment. Korean J Radiol. 2021;22(12):2017.
Madan S, Gandhi T, Chaudhury S. Bone Age Assessment for Lower Age Groups Using Triplet Network in Small Dataset of Hand X-Rays. In: Singh M, Kang D-K, Lee J-H, Tiwary US, Singh D, Chung W-Y, editors. Intelligent Human Computer Interaction 2020. Daegu: Springer; 2021. p. 142–53.
Cheng C-F, Liao KY-K, Lee K-J, Tsai F-J. A Study to Evaluate Accuracy and Validity of the EFAI Computer Aided Bone Age Diagnosis System Compared With Qualified Physicians. Front Pediatr. 2022 Apr 8;10.
Hui Q, Wang C, Weng J, Chen M, Kong D. A Global-Local Feature Fusion Convolutional Neural Network for Bone Age Assessment of Hand X-ray Images. Applied Sciences. 2022 Jul 18;12(14):7218.
Hwang J, Yoon HM, Hwang J-Y, Kim PH, Bak B, Bae BU, et al. Re-Assessment of Applicability of Greulich and PyleBased Bone Age to Korean Children Using Manual and Deep Learning-Based Automated Method. Yonsei Med J. 2022;63(7):683.
Lea WW, Hong S-J, Nam H-K, Kang W-Y, Yang Z-P, Noh E-J. External validation of deep learning-based bone-age software: a preliminary study with real world data. Sci Rep. 2022 Jan 24;12(1):1232.
Zhang Y, Zhu W, Li K, Yan D, Liu H, Bai J, et al. SMANet: multi-region ensemble of convolutional neural network model for skeletal maturity assessment. Quant Imaging Med Surg. 2022 Jul;12(7):3556–68.
Zhao X, Zhang M, Cheng M, Yue X, Li W, Li C. Construction of artificial intelligence system of carpal bone age for Chinese children based on China-05 standard. Med Phys. 2022;49(5):3223-3232. doi:10.1002/mp.15554
Deng Y, Chen Y, He Q, Wang X, Liao Y, Liu J, et al. Bone age assessment from articular surface and epiphysis using deep neural networks. Mathematical Biosciences and Engineering. 2023;20(7):13133–48.
Kasani AA, Sajedi H. Hand bone age estimation using divide and conquer strategy and lightweight convolutional neural networks. Eng Appl Artif Intell. 2023 Apr; 120:105935.
Kim PH, Yoon HM, Kim JR, Hwang J-Y, Choi J-H, Hwang J, et al. Bone Age Assessment Using Artificial Intelligence in Korean Pediatric Population: A Comparison of Deep-Learning Models Trained with Healthy Chronological and Greulich-Pyle Ages as Labels. Korean J Radiol. 2023;24(11):1151.
Kim KD, Kyung S, Jang M, Ji S, Lee DH, Yoon HM, et al. Enhancement of Non-Linear Deep Learning Model by Adjusting Confounding Variables for Bone Age Estimation in Pediatric Hand X-rays. J Digit Imaging. 2023 Jun 2;36(5):2003–14.
Kim S-U, Oh S, Lee K-H, Kang CH, Ahn K-S. Improvement of Bone Age Assessment Using a Deep Learning Model in Young Children: Significance of Carpal Bone Analysis. Iranian Journal of Radiology. 2023 Jul 18;20(2).
Li Z, Chen W, Ju Y, Chen Y, Hou Z, Li X, et al. Bone age assessment based on deep neural networks with annotation-free cascaded critical bone region extraction. Front Artif Intell. 2023 Mar 2;6.
Liu Z-Q, Hu Z-J, Wu T-Q, Ye G-X, Tang Y-L, Zeng Z-H, et al. Bone age recognition based on mask R-CNN using exception regression model. Front Physiol. 2023 Feb 14;14.
Nguyen T, Hermann A-L, Ventre J, Ducarouge A, Pourchot A, Marty V, et al. High performance for bone age estimation with an artificial intelligence solution. Diagn Interv Imaging. 2023 Jul;104(7–8):330 6.
Wang C, Wu Y, Wang C, Zhou X, Niu Y, Zhu Y, et al. Attention-based multiple-instance learning for Pediatric bone age assessment with efficient and interpretable. Biomed Signal Process Control. 2023 Jan; 79:104028.
Yang C, Dai W, Qin B, He X, Zhao W. A real-time automated bone age assessment system based on the RUS-CHN method. Front Endocrinol (Lausanne). 2023 Mar 15;14.
Zhang D, Liu B, Huang Y, Yan Y, Li S, He J, et al. An Automated TW3-RUS Bone Age Assessment Method with Ordinal Regression-Based Determination of Skeletal Maturity. J Digit Imaging. 2023 Feb 22;36(3):1001–15.
Liu Y, Ouyang L, Wu W, Zhou X, Huang K, Wang Z, et al. Validation of an established TW3 artificial intelligence bone age assessment system: a prospective, multicenter, confirmatory study. Quant Imaging Med Surg. 2024 Jan;14(1):144–59.
Nam H-K, Lea WW-I, Yang Z, Noh E, Rhie Y-J, Lee K-H, et al. Clinical validation of a deep-learning based bone age software in healthy Korean children. Ann Pediatr Endocrinol Metab. 2024 Apr 30;29(2):102–8.
Pape J, Hirsch FW, Deffaa OJ, DiFranco MD, Rosolowski M, Grafe D. Applicability and robustness of an artificial intelligence-based assessment for Greulich and Pyle bone age in a German cohort. RoFo Fortschritte auf dem Gebiet der Rontgenstrahlen und der bildgebenden Verfahren. 2024 Jun 8;196(06):600–6.
Mader KS. RSNA Bone Age [Internet]. 2017 [cited 2024 Aug 10]. Available from: https://www.kaggle.com/datasets/kmader/rsna-bone-age
Image Processing and Informatics Lab. Digital Hand Atlas [Internet]. 2013 [cited 2024 Aug 10]. Available from: https://ipilab.usc.edu/research/baaweb.
Rana M, Bhushan M. Machine learning and deep learning approach for medical image analysis: diagnosis to detection. Multimed Tools Appl. 2023 Jul 24;82(17):26731–69.
Erickson BJ, Korfiatis P, Akkus Z, Kline TL. Machine Learning for Medical Imaging. RadioGraphics. 2017 Mar;37(2):505–15.
Sarvamangala DR, Kulkarni R V. Convolutional neural networks in medical image understanding: a survey. Evol Intell. 2022 Mar 3;15(1):1–22.
Alshamrani K, Messina F, Offiah AC. Is the Greulich and Pyle atlas applicable to all ethnicities? A systematic review and meta-analysis. Eur Radiol. 2019 Jun 7;29(6):2910–23.
Tiwari PK, Gupta M, Verma A, Pandey S, Nayak A. Applicability of the Greulich–Pyle Method in Assessing the Skeletal Maturity of Children in the Eastern Utter Pradesh (UP) Region: A Pilot Study. Cureus. 2020 Oct 10;12(10): e10880.
Rubin DA. Assessing Bone Age: A Paradigm for the Next Generation of Artificial Intelligence in Radiology. Radiology. 2021 Dec;301(3):700–1.
Pan I, Baird GL, Mutasa S, Merck D, Ruzal-Shapiro C, Swenson DW, et al. Rethinking Greulich and Pyle: A Deep Learning Approach to Pediatric Bone Age Assessment Using Pediatric Trauma Hand Radiographs. Radiol Artif Intell. 2020 Jul 1;2(4): e190198.
Eng DK, Khandwala NB, Long J, Fefferman NR, Lala S V., Strubel NA, et al. Artificial Intelligence Algorithm Improves Radiologist Performance in Skeletal Age Assessment: A Prospective Multicenter Randomized Controlled Trial. Radiology. 2021 Dec;301(3):692–9.
Goddard K, Roudsari A, Wyatt JC. Automation bias: a systematic review of frequency, effect mediators, and mitigators. Journal of the American Medical Informatics Association. 2012 Jan 1;19(1):121–7.
Yi PH, Arun A, Hafezi-Nejad N, Choy G, Sair HI, Hui FK, et al. Can AI distinguish a bone radiograph from photos of flowers or cars? Evaluation of bone age deep learning model on inappropriate data inputs. Skeletal Radiol. 2022 Feb 5;51(2):401–6