基于主成分分析和支持向量机实现膝关节骨龄评估回归算法
|
摘要
目的通过方向梯度直方图(histogram of oriented gradient,HOG)、局部二值模式(local binary patterns,LBP)、支持向量机(support vector machine,SVM)以及主成分分析(principal component analysis,PCA)等机器学习方法构建适用于我国维吾尔族青少年骨龄评估的回归算法模型。方法采集维吾尔族12.0～<19.0岁青少年的膝关节DR摄片图像,其中男性样本275例、女性样本225例,采用PCA法对提取的HOG与LBP特征图像进行降维,再以支持向量回归(support vector regression,SVR)算法构建膝关节骨龄评估算法模型。采用随机分层抽样法分别选取男性样本215例、女性样本180例作为SVR模型训练集,并用K折交叉验证法优化模型参数。剩余样本作为独立测试集,将模型预报年龄与样本真实年龄相比,统计误差范围分别在±0.8岁、±1.0岁的准确率,同时计算平均绝对误差(mean absolute error,MAE)与均方根误差(root mean square error,RMSE)。结果男性年龄误差范围在±0.8岁及±1.0岁的准确率分别为80.67%和89.33%,MAE为0.486岁,RMSE为0.606岁;女性年龄误差范围在±0.8岁及±1.0岁的准确率分别为80.19%和90.45%,MAE为0.485岁,RMSE为0.590岁。结论基于PCA与SVM对膝关节DR摄片图像HOG及LBP特征降维建立骨龄的预报模型,具有较高的准确性。
Objective To establish a regression algorithm model that applies to bone age estimation of Xinjiang Uygur adolescents with machine learning methods such as histogram of oriented gradient(HOG), local binary patterns(LBP), support vector machine(SVM), principal component analysis(PCA). Methods DR images of knee-joints from 275 male and 225 female subjects aged 12.0-<19.0 years old were collected, PCA method was used to reduce the dimensionality of the HOG and LBP features, and support vector regression(SVR) was used to establish a knee-joint bone age estimation algorithm model. Stratified random sampling method was used to select 215 male samples, 180 female samples for the model training set. K-fold cross validation method was used to optimize parameters of the model. The remaining samples as the independent test set was used to compare the sample's true age and model estimated age, and had an accuracy rate in the statistical error range of ±0.8 and± 1.0 years, respectively. Then the mean absolute error(MAE) and root mean square error(RMSE)were calculated. Results The accuracy rate of male in the statistical error range of ±0.8 and ±1.0 year was 80.67%, 89.33%, respectively. The MAE and RMSE were 0.486 and 0.606 years, respectively. The accuracy rate of female in the statistical error range of ±0.8 and ±1.0 years was 80.19%, 90.45%, respectively. The MAE and RMSE were 0.485 and 0.590 years, respectively. Conclusion Establishment of prediction model for bone age estimation by feature dimension reduction of HOG and LBP in DR images of knee-joint based on PCA and SVM has relatively high accuracy.
Objective To establish a regression algorithm model that applies to bone age estimation of Xinjiang Uygur adolescents with machine learning methods such as histogram of oriented gradient(HOG), local binary patterns(LBP), support vector machine(SVM), principal component analysis(PCA). Methods DR images of knee-joints from 275 male and 225 female subjects aged 12.0-<19.0 years old were collected, PCA method was used to reduce the dimensionality of the HOG and LBP features, and support vector regression(SVR) was used to establish a knee-joint bone age estimation algorithm model. Stratified random sampling method was used to select 215 male samples, 180 female samples for the model training set. K-fold cross validation method was used to optimize parameters of the model. The remaining samples as the independent test set was used to compare the sample's true age and model estimated age, and had an accuracy rate in the statistical error range of ±0.8 and± 1.0 years, respectively. Then the mean absolute error(MAE) and root mean square error(RMSE)were calculated. Results The accuracy rate of male in the statistical error range of ±0.8 and ±1.0 year was 80.67%, 89.33%, respectively. The MAE and RMSE were 0.486 and 0.606 years, respectively. The accuracy rate of female in the statistical error range of ±0.8 and ±1.0 years was 80.19%, 90.45%, respectively. The MAE and RMSE were 0.485 and 0.590 years, respectively. Conclusion Establishment of prediction model for bone age estimation by feature dimension reduction of HOG and LBP in DR images of knee-joint based on PCA and SVM has relatively high accuracy.
引文
[1]GREULICH W W,PYLE S I.Radiographic atlas of skeletal development of the hand and wrist[M].2nd ed.Palo Alto,CA:Stanford University Press,1959.
[2]ACHESON R M.A method of assessing skeletal maturity from radiographs;a report from the Oxford child health survey[J].J Anat,1954,88(4):498-508.
[3]WANG Y H,LIU T A,WEI H,et al.Automated classification of epiphyses in the distal radius and ulna using a support vector machine[J].J Forensic Sci,2016,61(2):409-414.
[4]VAPNIK V N.The nature of statistical learning theory[M].2nd ed.New York:Springer-Verlag,2000.
[5]刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(4):1-9.
[6]顾亚祥,丁世飞.支持向量机研究进展[J].计算机科学,2011,38(2):14-17.
[7]罗娜.数据挖掘中的新方法--支持向量机[J].软件导刊,2008,7(10):30-31.
[8]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05),San Diego,June 20-25,2005.
[9]AHONEN T,HADID A,PIETIK?INEN M.Face recognition with local binary patterns[C]//European Conference on Computer Vision,Prague,May 11-14,2004:469-481.
[10]ZHANG D,ZHOU Z H,CHEN S.Diagonal principal component analysis for face recognition[J].Pattern Recogn,2006,39(1):140-142.
[11]孔繁钰,徐瑞华,姚胜永.交通量的支持向量回归预测及参数选择研究[J].计算机工程,2007,33(5):20-22,28.
[12]张倩,杨耀权.基于支持向量机核函数的研究[J].电力科学与工程,2012,28(5):42-45.
[13]杨俊燕,张优云,朱永生.ε不敏感损失函数支持向量机分类性能研究[J].西安交通大学学报,2007,41(11):1315-1320.
[14]刘旭,陈华才,刘太昂,等.PCA-SVR联用算法在近红外光谱分析烟草成分中的应用[J].光谱学与光谱分析,2007,27(12):2460-2463.
[15]POWELL M J D.Algorithms for nonlinear constraints that use lagrangian functions[J].Math Program,1978,14(1):224-248.
[16]卢涛,陈德钊.径向基网络的研究进展和评述[J].计算机工程与应用,2005,41(4):60-62,81.
[17]CHANG C C,LIN C J.LIBSVM:A library for support vector machines[M].Oxford:Oxford University Press,2011.
[18]最高人民检察院.最高人民检察院关于“骨龄鉴定”能否作为确定刑事责任年龄证据使用的批复[M]//2001中国法律年鉴.北京:中国法律年鉴社,2002.
[19]蔺芳琴,张骥,朱珍,等.自动骨龄评估软件BoneXpert对中国(上海)儿童青少年的适用性研究[J].中华实用儿科临床杂志,2014,29(23):1814-1817.
[20]罗家燕,林珠,卢瑞祥,等.手腕骨骨龄测量的计算机系统[J].中华口腔医学杂志,1998,33(6):378-380.
[21]ZHANG K,DONG X A,FAN F,et al.Age estimation based on pelvic ossification using regression models from conventional radiography[J].Int J Legal Med,2016,130(4):1143-1148.
[22]孙玉,刘贵全.基于HOG与LBP特征的人脸识别方法[J].计算机工程,2015,41(9):205-208,214.
[23]张蕾,何萍,荣静.基于降维和支持向量机的医学诊断[J].计算机时代,2018(11):60-63.
[24]王亚辉,王子慎,魏华,等.基于支持向量机实现骨骺发育分级的自动化评估[J].法医学杂志,2014,30(6):422-426.
[25]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[26]胡婷鸿,火忠,刘太昂,等.基于深度学习实现维吾尔族青少年左手腕关节骨龄自动化评估[J].法医学杂志,2018,34(1):27-32.
[27]HALABI S S,PREVEDELLO L M,KALPATHY-CRAMER J,et al.The RSNA pediatric bone age machine learning challenge[J].Radiology,2019,290(2):498-503.
[2]ACHESON R M.A method of assessing skeletal maturity from radiographs;a report from the Oxford child health survey[J].J Anat,1954,88(4):498-508.
[3]WANG Y H,LIU T A,WEI H,et al.Automated classification of epiphyses in the distal radius and ulna using a support vector machine[J].J Forensic Sci,2016,61(2):409-414.
[4]VAPNIK V N.The nature of statistical learning theory[M].2nd ed.New York:Springer-Verlag,2000.
[5]刘方园,王水花,张煜东.支持向量机模型与应用综述[J].计算机系统应用,2018,27(4):1-9.
[6]顾亚祥,丁世飞.支持向量机研究进展[J].计算机科学,2011,38(2):14-17.
[7]罗娜.数据挖掘中的新方法--支持向量机[J].软件导刊,2008,7(10):30-31.
[8]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition(CVPR’05),San Diego,June 20-25,2005.
[9]AHONEN T,HADID A,PIETIK?INEN M.Face recognition with local binary patterns[C]//European Conference on Computer Vision,Prague,May 11-14,2004:469-481.
[10]ZHANG D,ZHOU Z H,CHEN S.Diagonal principal component analysis for face recognition[J].Pattern Recogn,2006,39(1):140-142.
[11]孔繁钰,徐瑞华,姚胜永.交通量的支持向量回归预测及参数选择研究[J].计算机工程,2007,33(5):20-22,28.
[12]张倩,杨耀权.基于支持向量机核函数的研究[J].电力科学与工程,2012,28(5):42-45.
[13]杨俊燕,张优云,朱永生.ε不敏感损失函数支持向量机分类性能研究[J].西安交通大学学报,2007,41(11):1315-1320.
[14]刘旭,陈华才,刘太昂,等.PCA-SVR联用算法在近红外光谱分析烟草成分中的应用[J].光谱学与光谱分析,2007,27(12):2460-2463.
[15]POWELL M J D.Algorithms for nonlinear constraints that use lagrangian functions[J].Math Program,1978,14(1):224-248.
[16]卢涛,陈德钊.径向基网络的研究进展和评述[J].计算机工程与应用,2005,41(4):60-62,81.
[17]CHANG C C,LIN C J.LIBSVM:A library for support vector machines[M].Oxford:Oxford University Press,2011.
[18]最高人民检察院.最高人民检察院关于“骨龄鉴定”能否作为确定刑事责任年龄证据使用的批复[M]//2001中国法律年鉴.北京:中国法律年鉴社,2002.
[19]蔺芳琴,张骥,朱珍,等.自动骨龄评估软件BoneXpert对中国(上海)儿童青少年的适用性研究[J].中华实用儿科临床杂志,2014,29(23):1814-1817.
[20]罗家燕,林珠,卢瑞祥,等.手腕骨骨龄测量的计算机系统[J].中华口腔医学杂志,1998,33(6):378-380.
[21]ZHANG K,DONG X A,FAN F,et al.Age estimation based on pelvic ossification using regression models from conventional radiography[J].Int J Legal Med,2016,130(4):1143-1148.
[22]孙玉,刘贵全.基于HOG与LBP特征的人脸识别方法[J].计算机工程,2015,41(9):205-208,214.
[23]张蕾,何萍,荣静.基于降维和支持向量机的医学诊断[J].计算机时代,2018(11):60-63.
[24]王亚辉,王子慎,魏华,等.基于支持向量机实现骨骺发育分级的自动化评估[J].法医学杂志,2014,30(6):422-426.
[25]LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[26]胡婷鸿,火忠,刘太昂,等.基于深度学习实现维吾尔族青少年左手腕关节骨龄自动化评估[J].法医学杂志,2018,34(1):27-32.
[27]HALABI S S,PREVEDELLO L M,KALPATHY-CRAMER J,et al.The RSNA pediatric bone age machine learning challenge[J].Radiology,2019,290(2):498-503.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |