Use of artificial intelligence in bone age assessment

doi:10.16352/j.issn.1001-6325.2022.11.1776

Abstract

Abstract: Artificial intelligence (AI) system which can achieve stable, efficient and automatic bone age (BA) evaluation has been gradually embedded into clinical workflow. Herein, the routine BA methods were briefly reviewed and then followed by explanation of some terms commonly used in the area of AI. Then authors reviewed the research progresses of AI bone age software both in China and abroad in recent years, including the sources of training and validation dataset, the construction of algorithms and modules, and its performance in testing dataset. Finally, the challenges of applying AI in BA assessment were presented and some suggestions were given.

Key words: bone age, growth and development, artificial intelligence, deep learning

CLC Number:

O633.0

WANG Feng-dan, Cidanwangjiu, JIAO Yang, PAN Hui, YIN Wu, JIN Zheng-yu. Use of artificial intelligence in bone age assessment[J]. Basic & Clinical Medicine, 2022, 42(11): 1776-1780.

References 29

[1]	Cameron N. Can maturity indicators be used to estimate chronological age in children?[J]. Ann Hum Biol, 2015, 42:302-307.
[2]	Huda W, Gkanatsios NA. Radiation dosimetry for extre-mity radiographs[J]. Health Phys, 1998, 75:492-499.
[3]	GBD 2016 Healthcare Access and Quality Collaborators. Measuring performance on the Healthcare Access and Quality Index for 195 countries and territories and selected subnational locations: a systematic analysis from the Global Burden of Disease Study 2016[J]. Lancet, 2018, 391:2236-2271.
[4]	Martin DD, Wit JM, Hochberg Z, et al. The use of bone age in clinical practice-part 1[J]. Horm Res Paediatr, 2011, 76:1-9.
[5]	Berst MJ, Dolan L, Bogdanowicz MM, et al. Effect of knowledge of chronologic age on the variability of pediatric bone age determined using the Greulich and Pyle standards[J]. Am J Roentgenol, 2001, 176:507-510.
[6]	Spampinato C, Palazzo S, Giordano D, et al. Deep learning for automated skeletal bone age assessment in X-ray images[J]. Med Image Anal, 2017, 36:41-51.
[7]	Lee H, Tajmir S, Lee J, et al. Fully automated deep learning system for bone age assessment[J]. J Digit Imaging, 2017, 30:427-441.
[8]	Larson DB, Chen MC, Lungren MP, et al. Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs[J]. Radiology, 2018, 287:313-322.
[9]	Kim JR, Shim WH, Yoon HM, et al. Computerized bone age estimation using deep learning based program: evaluation of the accuracy and efficiency[J]. Am J Roentgenol, 2017, 209:1374-1380.
[10]	Lee BD, Lee MS. Automated bone age assessment using artificial intelligence: the future of bone age assessment[J]. Korean J Radiol, 2021, 22:792-800.
[11]	Halabi SS, Prevedello LM, Kalpathy-Cramer J, et al. The RSNA pediatric bone age machine learning challenge[J]. Radiology, 2019, 290:498-503.
[12]	Tong C, Liang B, Li J, et al. A deep automated skeletal bone age assessment model with heterogeneous features learning[J]. J Med Syst, 2018, 42:249.
[13]	Liu Y, Zhang C, Cheng J, et al. A multi-scale data fusion framework for bone age assessment with convolu-tional neural networks[J]. Comput Biol Med, 2019, 108:161-173.
[14]	Ren X, Li T, Yang X, et al. Regression convolutional neural network for automated pediatric bone age assess-ment from hand radiograph[J]. IEEE J Biomed Health Inform, 2019, 23:2030-2038.
[15]	王嘉庆, 梅礼晔, 张俊华. 基于深度学习的手骨X射线图像骨龄评估[J]. 计算机工程, 2021, 47:291-297.
[16]	管骏. 基于卷积神经网络的骨龄辅助评测技术[J]. 科学技术创新, 2021, 4:53-55.
[17]	文颖, 任旭华, 杨秀军, 等. 基于手腕部影像传统关注特征区域深度学习的人工智能骨龄评估[J]. 中华放射学杂志, 2019, 53:895-899.
[18]	Zhou XL, Wang EG, Lin Q, et al. Diagnostic perfor-mance of convolutional neural network-based Tanner-Whitehouse 3 bone age assessment system[J]. Quant Imaging Med Surg, 2020, 10:657-667.
[19]	Wang F, Gu X, Chen S, et al. Artificial intelligence system can achieve comparable results to experts for bone age assessment of Chinese children with abnormal growth and development[J]. PeerJ, 2020, 8:e8854. doi: 10.7717/peerj.8854.
[20]	Wang F, Cidan W, Gu X, et al. Performance of an artificial intelligence system for bone age assessment in Tibet[J]. Br J Radiol, 2021, 94:20201119. doi: 10.1259/bjr.20201119.
[21]	赵凯, 马帅, 孙佳丽, 等. 人工智能软件对住院医师X线骨龄诊断辅助效果初探[J]. 实用放射学杂志, 2021, 37:317-320.
[22]	宋娟, 宫平, 高畅, 等. 基于深度学习的儿童骨龄智能评估模型构建及初步临床验证[J]. 中华放射学杂志, 2019, 53:974-978.
[23]	李睿, 张世杰, 黄奥云, 等. 基于深度学习的青少年手腕骨骨龄评价[J]. 计算机技术与发展, 2020, 30:124-134.
[24]	王岩, 霍爱华, 王大为, 等. 基于深度学习人工智能骨龄评测系统临床应用[J]. 中国医学影像技术, 2021, 37:104-107.
[25]	Cavallo F, Mohn A, Chiarelli F, et al. Evaluation of bone age in children: a mini-review[J]. Front Pediatr, 2021, 9:580314. doi: 10.3389/fped.2021.580314.
[26]	van Leeuwen KG, Schalekamp S, Rutten M, et al. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence[J]. Eur Radiol, 2021, 31:3797-3804.
[27]	刘士远. 中国医学影像人工智能发展报告 [M]. 北京: 科学出版社, 2020:118-128.
[28]	宋绮蕊, 蔡军. 人工智能及机器学习在心血管疾病中的应用[J]. 基础医学与临床, 2020, 40: 707-710.
[29]	Omoumi P, Ducarouge A, Tournier A, et al. To buy or not to buy-evaluating commercial AI solutions in radiology (the ECLAIR guidelines)[J]. Eur Radiol, 2021, 31:3786-3796.