法医学杂志
法醫學雜誌
법의학잡지
JOURNAL OF FORENSIC MEDICINE
2014年
6期
422-426
,共5页
王亚辉%王子慎%魏华%万雷%应充亮%朱广友
王亞輝%王子慎%魏華%萬雷%應充亮%硃廣友
왕아휘%왕자신%위화%만뢰%응충량%주엄우
法医人类学%骨骺%尺骨%桡骨%支持向量机
法醫人類學%骨骺%呎骨%橈骨%支持嚮量機
법의인류학%골후%척골%뇨골%지지향량궤
forensic anthropology%epiphyses%ulna%radius%support vector m achine
目的:运用支持向量机(support vector machine,SVM)实现尺、桡骨远端骨骺发育分级的自动化评估。方法收集我国140例11~19周岁青少年左侧腕关节X线正位片作为训练样本。将尺、桡骨远端骨骺分为五个发育分级,每个分级均包含28例样本。另选35例作为独立校验样本。建立尺、桡骨远端骨骺五个发育分级的SVM分类模型,用留一交叉验证法(leave one out cross validation,LOOCV)进行模型内部交叉验证以及梯度方向直方图(histogram of oriented gradient,HOG)进行模型外部验证,分别计算其准确率(PA)。结果桡骨远端骨骺分级SVM建模、LOOCV和HOG的PA分别为100.0%、78.6%和82.8%。尺骨远端骨骺分级SVM建模、LOOCV和HOG的PA分别为100.0%、80.0%和88.6%。结论运用SVM建立的尺、桡骨远端骨骺发育分级的自动化模型具有一定的可行性,为法医学骨龄评估软件的开发奠定基础。
目的:運用支持嚮量機(support vector machine,SVM)實現呎、橈骨遠耑骨骺髮育分級的自動化評估。方法收集我國140例11~19週歲青少年左側腕關節X線正位片作為訓練樣本。將呎、橈骨遠耑骨骺分為五箇髮育分級,每箇分級均包含28例樣本。另選35例作為獨立校驗樣本。建立呎、橈骨遠耑骨骺五箇髮育分級的SVM分類模型,用留一交扠驗證法(leave one out cross validation,LOOCV)進行模型內部交扠驗證以及梯度方嚮直方圖(histogram of oriented gradient,HOG)進行模型外部驗證,分彆計算其準確率(PA)。結果橈骨遠耑骨骺分級SVM建模、LOOCV和HOG的PA分彆為100.0%、78.6%和82.8%。呎骨遠耑骨骺分級SVM建模、LOOCV和HOG的PA分彆為100.0%、80.0%和88.6%。結論運用SVM建立的呎、橈骨遠耑骨骺髮育分級的自動化模型具有一定的可行性,為法醫學骨齡評估軟件的開髮奠定基礎。
목적:운용지지향량궤(support vector machine,SVM)실현척、뇨골원단골후발육분급적자동화평고。방법수집아국140례11~19주세청소년좌측완관절X선정위편작위훈련양본。장척、뇨골원단골후분위오개발육분급,매개분급균포함28례양본。령선35례작위독립교험양본。건립척、뇨골원단골후오개발육분급적SVM분류모형,용류일교차험증법(leave one out cross validation,LOOCV)진행모형내부교차험증이급제도방향직방도(histogram of oriented gradient,HOG)진행모형외부험증,분별계산기준학솔(PA)。결과뇨골원단골후분급SVM건모、LOOCV화HOG적PA분별위100.0%、78.6%화82.8%。척골원단골후분급SVM건모、LOOCV화HOG적PA분별위100.0%、80.0%화88.6%。결론운용SVM건립적척、뇨골원단골후발육분급적자동화모형구유일정적가행성,위법의학골령평고연건적개발전정기출。
Objective To realize the autom ated assessm ent of the levels of epiphysis of distal radius and ulna by support vector m achine (SVM). Methods The X-ray film s of the leftwrist jointswere taken from 140 teenagers aged from 11 to 19 years old as training sam ples. The levels of epiphysis of distal radius and ulnawere divided into five developm ental levels. Each level contained 28 sam ples. A nother 35 cas-eswere selected as independent verifying sam ples. SVM classification m odels of the five developm ental levels of epiphysis of distal radius and ulnawere established. The internal cross validationwas m ade by leave one out cross validation (LOOCV ),while the external validationwas m ade by histogram of orient-ed gradient (HOG), and then the accuracy (PA ) of testing resultswas calculated, respectively. Results The PA of SVM, LOOCV and HOG of distal radius epiphyseal levelwere 100%, 78.6%, and 82.8%, respec-tively;whereas the PA of SVM, LOOCV and HOGof distal ulna epiphyseal levelwere 100.0%, 80.0%and 88.6%, respectively. Conclusion The SVM -based autom atic m odels of the growth stage of distal ra-dius and ulna appear to have certain feasibility, and m ay provide a foundation for software developm ent of bone age assessm ent by forensic medicine.