摘要
构建基于深度学习的儿童骨龄人工智能(AI)评估模型,并进行初步的临床验证.方法回顾性连续纳入2018年3月至8月无锡市儿童医院儿童骨龄DR片5000例,按年龄段等比例采样原则训练集纳入2351例,验证集101例.由4名放射学专家采用中华05RUS-CHN法,双盲评估关键骨骺发育等级,取专家骨龄评测的均值为参考金标准.采用深度学习方法训练并建立骨龄评估AI模型,另选2名儿童影像住院医师人工测评验证集骨龄,作为临床验证对照组.计算AI模型和2名住院医师骨龄测评的准确率、平均绝对误差(MAE)、均方根误差(RMSE)及耗时,并采用配对t检验和F检验及χ^2检验比较.结果AI模型与参考金标准之间的MAE为(0.37±0.35)年,RSME为0.50年,完成1份骨龄评价报告用时(4.58±0.91)s.2名住院医师和AI模型评价的MAE、RSME差异均无统计学意义(P>0.05),评价用时明显长于AI,差异有统计学意义(P<0.05).当误差范围在±1.0岁、±0.7岁及±0.5岁以内,AI模型评价验证集准确率分别为94.1%(95/101)、89.1%(90/101)和74.3%(75/101),AI评测骨龄与2名医师之间的准确率差异均无统计学意义(P>0.05).结论构建的基于深度学习的儿童骨龄评估AI模型具有可行性,并具有准确性高以及耗时短的特点.
Objective To build an automatic bone age assessment system based on China 05 Bone Age Standard and the latest deep learning technology,and preliminary clinical verification was carried out.Methods The left-hand radiographs of 5000 children with suspected metabolic disorders were acquired from Wuxi Children′s Hospital.Among these cases,2351 patients were randomly chosen as training set,and 101 patients were randomly used as validation set.Four professional pediatric radiologists annotated the development stage according to the China 05 RUS-CHN standard with double-blind method.The mean value of the bone age assessed by experts was the reference standard which was used to train and validate the deep learning mothods based artificial intelligence(AI)model.Accuracy,mean absolute error(MAE),root mean squared error(RMSE)and time efficiency of bone age assessment were compared by using Chi-square test and t test and F test between resident doctors and AI model in the validation set.Results The MAE and RMSE was(0.37±0.35)years and 0.50 years between AI model and reference standard,respeactively.When the error range was within±1.0,±0.7 and±0.5 years,the accuracy of model on the validation set was 94.1%(95/101),89.1%(90/101),74.3%(75/101)respectively.The accuracy between two resident doctors and AI prediction wasn't statistical significant(P>0.05).Conclusion The AI model of bone age assessment based on deep learning is feasible and has the characteristics of high accuracy and efficiency.
作者
宋娟
宫平
高畅
韩青
李秀丽
朱宗明
陈宏伟
俞益州
方向明
Song Juan;Gong Ping;Gao Chang;Han Qing;Li Xiuli;Zhu Zongming;Chen Hongwei;Yu Yizhou;Fang Xiangming(Department of Imaging,Wuxi People's Hospital Affiliated to Nanjing Medical University,Wuxi Children's Hospital,Wuxi 214023,China;Deep Wise Artificial Intelligence Lab,Beijing 100080,China)
出处
《中华放射学杂志》
CAS
CSCD
北大核心
2019年第11期974-978,共5页
Chinese Journal of Radiology
关键词
骨龄
深度学习
人工智能
中华05
Bone age
Deep learning
Artificial intelligence
China 05 method