基于深度学习的骨龄评估系统对生长发育异常儿童骨龄评测的准确性  

Accuracy of bone age assessment system based on deep learning in children with abnormal growth and development

作　　者：常沙 闫东[2] 杜霞 张玉巧 程晓光[2] 杨洁 宋玲玲 高波 罗贤 Chang Sha;Yan Dong;Du Xia;Zhang Yuqiao;Cheng Xiaoguang;Yang Jie;Song Lingling;Gao Bo;Luo Xian(Department of Imaging,the Affiliated Hospital of Guizhou Medical University,Guiyang 550004,China;Department of Radiology,Beijing Jishuitan Hospital,Beijing 100035,China)

机构地区：[1]贵州医科大学附属医院影像科,贵阳550004 [2]北京积水潭医院放射科,北京100035

出　　处：《中华放射学杂志》2023年第4期364-369,共6页Chinese Journal of Radiology

基　　金：北京积水潭医院高层次人才学科骨干培养计划(XKGG202122);贵州省第七批“千人创新创业人才”(GZQ202007086);贵州省精准影像与诊疗创新群体(黔教合KY[2021]017)。

摘　　要：目的探讨基于深度学习的人工智能(AI)系统评估生长发育异常儿童骨龄的准确性。方法回顾性连续收集2020年1月至2021年12月于贵州医科大学附属医院就诊的生长发育异常儿童的左手腕部X线正位片,共入组717例儿童,男266例、女451例,年龄2~18(11±3)岁。基于Tanner Whitehouse 3(TW3)-RUS(尺骨、桡骨、短骨)和TW3-Carpal(腕骨)法,由3名高年资医师评测骨龄,并取3者的均值作为参考标准。由AI系统(深睿医疗Dr.Wise骨龄预测软件)和2名低年资放射科医师(医师1、医师2)独立评测骨龄,并分别计算骨龄结果与参考标准骨龄之间误差在0.5年内的准确度、1年内的准确度、平均绝对误差(MAE)和均方根误差(RMSE)。以配对样本t检验比较AI系统和低年资医师间的MAE。采用组内相关系数(ICC)评价AI系统、低年资医师评测骨龄与参考标准骨龄之间的一致性。绘制Bland-Altman图,计算AI评测骨龄与参考标准骨龄之间95%一致性界限。结果对TW3-RUS骨龄,与参考标准相比,AI系统、医师1、医师2误差在0.5年内的准确度分别为75.3%(540/717)、62.1%(445/717)、66.2%(475/717),误差在1年内的准确度分别为96.9%(695/717)、86.3%(619/717)、89.1%(639/717),MAE分别为0.360、0.565、0.496年,RMSE分别为0.469、0.634、0.572年。对TW3-Carpal骨龄,与参考标准相比,AI系统、医师1、医师2误差在0.5年内的准确度分别为80.9%(580/717)、65.1%(467/717)、71.7%(514/717),误差在1年内的准确度分别为96.0%(688/717)、87.3%(626/717)、90.4%(648/717),MAE分别为0.330、0.527、0.455年,RMSE分别为0.458、0.612、0.538年。AI系统TW3-RUS和TW3-Carpal骨龄评测的MAE均小于医师1、医师2,差异均有统计学意义(P均<0.001)。AI、医师1、医师2评测骨龄结果与参考标准之间均具有较好的一致性(ICC均>0.950)。Bland-Altman图显示AI系统对TW3-RUS和TW3-Carpal骨龄评测的95%一致性界限分别为-0.75~1.02岁、-0.86~0.91岁。结论AI系统对生长发�Objective To explore the accuracy of artificial intelligence(AI)system based on deep learning in evaluating bone age of children with abnormal growth and development.Methods The positive X-ray films of the left wrist of children with abnormal growth and development who were treated at the Affiliated Hospital of Guizhou Medical University from January 2020 to December 2021 were collected retrospectively.A total of 717 children were collected,including 266 males and 451 females,aged 2-18(11±3)years.Based on Tanner Whitehouse 3(TW 3)-RUS(radius,ulna,short bone)and TW3-Carpal(carpal bone)method,bone age was measured by 3 senior radiologists,and the mean value was taken as reference standard.The bone ages were independently evaluated by the AI system(Dr.Wise bone age prediction software)and two junior radiologists(physicians 1 and 2).The accuracy within 0.5 year,the accuracy within 1 year,the mean absolute error(MAE)and the root mean square error(RMSE)between the evaluation results and the reference standard were analyzed.Paired sample t-test was used to compare MAE between AI system and junior physicians.Intraclass correlation coefficient(ICC)was used to evaluate the consistency between AI system,junior physician and reference standard.The Bland-Altman diagram was drawn and the 95%consistency limit was calculated between AI system and reference standard.Results For TW3-RUS bone age,compared with the reference standard,the accuracy within 0.5 year of AI system,physician 1 and physician 2 was 75.3%(540/717),62.1%(445/717)and 66.2%(475/717),respectively.The accuracy within 1 year was 96.9%(695/717),86.3%(619/717)and 89.1%(639/717),respectively.MAE was 0.360,0.565 and 0.496 years,and RMSE was 0.469,0.634 and 0.572 years,respectively.For TW3-Carpal bone age,compared with the reference standard,the accuracy within 0.5 year of AI system,physician 1 and physician 2 was 80.9%(580/717),65.1%(467/717)and 71.7%(514/717),respectively.The accuracy within 1 year was 96.0%(688/717),87.3%(626/717)and 90.4%(648/717),respectively.MAE

关 键 词：年龄测定 骨骼 人工智能 TW3法 生长发育异常 

分 类 号：R179[医药卫生—妇幼卫生保健]