"Validation of an established TW3 artificial intelligence bone age assessment system: a prospective, multicenter, confirmatory study"

作者全名："Liu, Yanqi; Ouyang, Liujian; Wu, Wei; Zhou, Xuelian; Huang, Ke; Wang, Zhihua; Song, Cui; Chen, Qiuli; Su, Zhe; Zheng, Rongxiu; Wei, Ying; Lu, Wei; Wu, Wei; Liu, Yang; Yan, Ziye; Wu, Zhaoyuan; Fan, Jitao; Zhou, Mingzhi; Fu, Junfen"

作者地址："[Liu, Yanqi; Ouyang, Liujian; Wu, Wei; Zhou, Xuelian; Huang, Ke; Yan, Ziye; Wu, Zhaoyuan; Fu, Junfen] Zhejiang Univ, Childrens Hosp, Sch Med, Natl Clin Res Ctr Child Hlth,Dept Endocrinol, 3333 Binsheng Rd, Hangzhou 310052, Peoples R China; [Wang, Zhihua] Xi An Jiao Tong Univ, Xian Childrens Hosp, Dept Endocrinol & Metab, Xian, Peoples R China; [Song, Cui] Chongqing Med Univ, Childrens Hosp, Natl Clin Res Ctr Child Hlth & Disorders, Dept Endocrinol & Genet Metab Dis, Chongqing, Peoples R China; [Chen, Qiuli] Sun Yat Sen Univ, Affiliated Hosp 1, Dept Pediat, Guangzhou, Peoples R China; [Su, Zhe] Shenzhen Childrens Hosp, Dept Endocrinol, Shenzhen, Peoples R China; [Zheng, Rongxiu; Wei, Ying] Tianjin Med Univ Gen Hosp, Dept Pediat, Tianjin, Peoples R China; [Lu, Wei] Fudan Univ, Childrens Hosp, Natl Childrens Med Ctr, Dept Endocrinol & Inherited Metab Dis, Shanghai, Peoples R China; [Wu, Wei] Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Dept Pediat, Wuhan, Peoples R China; [Liu, Yang] Nanchang Univ, Affiliated Hosp 2, Dept Pediat, Nanchang, Peoples R China; [Fan, Jitao] Beijing Deepwise & League PHD Technol Co Ltd, Dept Res Collaborat, R&D Ctr, Beijing, Peoples R China; [Zhou, Mingzhi] Second Peoples Hosp Yibin City, Clin Res & Translat Ctr, Yibin, Peoples R China"

通信作者："Fu, JF (通讯作者)，Zhejiang Univ, Childrens Hosp, Sch Med, Natl Clin Res Ctr Child Hlth,Dept Endocrinol, 3333 Binsheng Rd, Hangzhou 310052, Peoples R China."

来源：QUANTITATIVE IMAGING IN MEDICINE AND SURGERY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001091931700001

JCR分区：Q2

影响因子：2.9

年份：2023

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：Bone age; multi-center research; artificial intelligence (AI); Tanner-Whitehouse 3 method (TW3 method); convolutional neural network (CNN)

摘要："Background: In 2020, our center established a Tanner-Whitehouse 3 (TW3) artificial intelligence (AI) system using a convolutional neural network (CNN), which was built upon 9059 radiographs. However, the system, upon which our study is based, lacked a gold standard for comparison and had not undergone thorough evaluation in different working environments. Methods: To further verify the applicability of the AI system in clinical bone age assessment (BAA) and to enhance the accuracy and homogeneity of BAA, a prospective multi-center validation was conducted. This study utilized 744 left-hand radiographs of patients, ranging from 1 to 20 years of age, with 378 boys and 366 girls. These radiographs were obtained from nine different children's hospitals between August and December 2020. The BAAs were performed using the TW3 AI system and were also reviewed by experienced reviewers. Bone age accuracy within 1 year, root mean square error (RMSE), and mean absolute error (MAE) were statistically calculated to evaluate the accuracy. Kappa test and Bland-Altman (B-A) plot were conducted to measure the diagnostic consistency. Results: The system exhibited a high level of performance, producing results that closely aligned with those of the reviewers. It achieved a RMSE of 0.52 years and an accuracy of 94.55% for the radius, ulna, and short bones series. When assessing the carpal series of bones, the system achieved a RMSE of 0.85 years and an accuracy of 80.38%. Overall, the system displayed satisfactory accuracy and RMSE, particularly in patients over 7 years old. The system excelled in evaluating the carpal bone age of patients aged 1-6. Both the Kappa test and B-A plot demonstrated substantial consistency between the system and the reviewers, although the model encountered challenges in consistently distinguishing specific bones, such as the capitate. Furthermore, the system's performance proved acceptable across different genders and age groups, as well as radiography instruments. Conclusions: In this multi-center validation, the system showcased its potential to enhance the efficiency and consistency of healthy delivery, ultimately resulting in improved patient outcomes and reduced healthcare costs."

基金机构："National Key Research and Development Program of China [2021YFC2701901, 2016YFC1305301]; National Natural Science Foundation of China [81570759, 81270938]; Zhejiang Provincial Key Disciplines of Medicine (Innovation Discipline) [11-CX24]"

基金资助正文："This work received financial support from the National Key Research and Development Program of China (Nos. 2021YFC2701901 and 2016YFC1305301) , National Natural Science Foundation of China (Nos. 81570759 and 81270938) , and Zhejiang Provincial Key Disciplines of Medicine (Innovation Discipline, 11-CX24) ."