基于小波变换的新疆地方性肝包虫CT图像分类研究
|
摘要
采用基于sym4和db4小波基两种小波变换方法,探讨对新疆地方性肝包虫CT图像的分类价值。使用sym4和db4小波两种小波基,提取感兴趣病灶区的纹理特征,并通过统计学方法筛选出特征子集,采用C4.5决策树算法构建正常肝脏和多子囊型病变肝脏CT图像的计算机分类模型,并对模型进行准确性、灵敏度和特异性的验证评估。结果显示,对正常肝脏和多子囊型肝包虫进行分类,sym4小波的识别正确率为92.5%,db4小波的识别正确率为97.5%。实验结果表明,小波变换法所提取的纹理特征对识别正常肝脏和多子囊型肝包虫CT影像有较好的意义,也为后续的基于内容的新疆地方性肝包虫病的诊断系统奠定了基础。
To explore classification value for Xinjiang local liver hydatid using two kinds of wavelet transform methods. This two methods consists of sym4 and db4 wavelet. Two wavelet methods were used to extract texture feature of region of interest focal zone,statistical method was used to select the optimal texture feature from the set of extracted features. The C4. 5 Decision Tree was employed as a classifier. The results of C4. 5 Decision Tree for sym4 and db4 wavelet analysis methods were evaluated using accuracy,sensitivity and specificity and the area under the ROC curve( AUC). The results showed that the accuracy rate of sym4 wavelet classifing normal liver and poly-cystic liver hydatid reached to 92. 5%; the accuracy rate of db4 wavelet classification reached to 97. 5%. The experimental results show that db4 wavelet methods is able to achieve higher classification accuracy effectiveness,it can lay a foundation which is subsequent based-content diagnostic system of Xinjiang local liver hydatid.
To explore classification value for Xinjiang local liver hydatid using two kinds of wavelet transform methods. This two methods consists of sym4 and db4 wavelet. Two wavelet methods were used to extract texture feature of region of interest focal zone,statistical method was used to select the optimal texture feature from the set of extracted features. The C4. 5 Decision Tree was employed as a classifier. The results of C4. 5 Decision Tree for sym4 and db4 wavelet analysis methods were evaluated using accuracy,sensitivity and specificity and the area under the ROC curve( AUC). The results showed that the accuracy rate of sym4 wavelet classifing normal liver and poly-cystic liver hydatid reached to 92. 5%; the accuracy rate of db4 wavelet classification reached to 97. 5%. The experimental results show that db4 wavelet methods is able to achieve higher classification accuracy effectiveness,it can lay a foundation which is subsequent based-content diagnostic system of Xinjiang local liver hydatid.
引文
[1]阿勒哈,周翠霞,曹峻,等.52例肝包虫外囊完整剥除术的临床分析[J].新疆医科大学学报,2015,38(1):89-94.
[2]谢天皓,吕海龙,车小双,等.彭心宇肝包虫囊肿退行性变的CT诊断[J].实用放射学杂志,2013,29(7):1098-1101.
[3]陈先志.肝包虫的CT诊断价值[J].医药前沿,2014,(35):43-44.
[4]周晶晶,木拉提·哈米提,严传波,等.新疆地方性肝包虫CT图像纹理特征的分类研究[J].科技通报,2013,29(1):42-46.
[5]木拉提·哈米提,员伟康,严传波,等.基于综合特征的新疆地方性肝包虫病图像特征的提取与分析[J].科技通报,2015,5:58-62.
[6]陈胜,璩心波.基于小波变换的多神经网络胸片骨骼分离[J].电子科技,2015,28(5):124-131.
[7]Penfold TJ,Tavernelli I,Milne CJ,et al.A wavelet analysis for the X-ray absorption spectra of molecules[J].Journal of Chemical Physics,2013,138(1):257-265.
[8]韩晓军,赵宇,杨国环.基于小波变换的肝脏CT图像分类[J].天津工业大学学报,2015,34(1):59-63.
[9]周平,李传富,符志鹏.基于小波分解的脑CT图像纹理特征提取[J].仪器仪表学报2010,31(3):643-648.
[10]周涛,蒋芸,王勇,等.基于小波神经网络的医学图像分类方法[J].计算机应用,2010,30(10):2856-2860.
[11]聂会星,梁坤,徐枞巍.基于小波变换和支持向量机的人脸识别研究[J].合肥工业大学学报(自然科学版),2011,34(2):208-211.
[12]S.G.Mallat.Multi-frequency channel decompositions of images and wavelet models[J].IEEE Traps.Acoust Speech and Signal Process,1989,37(12):2091-2110.
[13]胡昌华,李国华,周涛.基于MATLAB 7.x的系统分析与设计——小波分析.第三版[M].西安电子科技大学出版社,2008.15-22.
[14]高清河,刚晶,王和禹,等.基于小波变换的多模态医学图像的融合及性能评价[J].生物医学工程研究,2014,33(4):259-263.
[15]Patrick J,Sun DW,Paul A.Comparison of various wavelet texture features to predict beef palatability[J].Meat Sci,2009,83:82-87.
[16]Engin A.Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system[J].Appl soft Comput,2008,8:225-231.
[17]刘莹.图像纹理的特征提取和分类方法研究[D].华中科技大学,2013.
[18]木拉提·哈米提,孔喜梅,严传波等.新疆维吾尔草药图像特征提取及分类研究[J].新疆医科大学学报,2015,38(7):815-822.
[19]Holzinger,Andreas.Data Mining with Decision Trees:Theory and Applications[J].Online Information Review,2015,39(3):437-438.
[20]张慧,迟庆云,刘彩霞.基于灰度共生矩阵的肝癌B超纹理特征决策树诊断分析[J].中国医药指南,2015,13(25):2-3.
[21]苗红星,余建坤.基于决策树的ID3算法和C4.5算法的比较[J].现代计算机(专业版),2014(10):7-10.
[22]Nanthagopal A P,Rajamony R S.Automatic classification of brain computed tomography images using wavelet-based statistical texture features[J].Journal of Visualization,2012,15(4):363-372.
[23]Yuan XD,Quan CB,AO GK.ROC analysis of CT hemodynamic in the diagnosis of breast cancer[J].The Chinese-German Journal of Clinical Oncology,2010,9(3):165-168.
[24]张岁霞,木拉提·哈米提,姚娟,等.基于集成分类器的新疆哈萨克族食管癌分型的研究[J].生物医学工程研究,2015,34(4):216-223.
[2]谢天皓,吕海龙,车小双,等.彭心宇肝包虫囊肿退行性变的CT诊断[J].实用放射学杂志,2013,29(7):1098-1101.
[3]陈先志.肝包虫的CT诊断价值[J].医药前沿,2014,(35):43-44.
[4]周晶晶,木拉提·哈米提,严传波,等.新疆地方性肝包虫CT图像纹理特征的分类研究[J].科技通报,2013,29(1):42-46.
[5]木拉提·哈米提,员伟康,严传波,等.基于综合特征的新疆地方性肝包虫病图像特征的提取与分析[J].科技通报,2015,5:58-62.
[6]陈胜,璩心波.基于小波变换的多神经网络胸片骨骼分离[J].电子科技,2015,28(5):124-131.
[7]Penfold TJ,Tavernelli I,Milne CJ,et al.A wavelet analysis for the X-ray absorption spectra of molecules[J].Journal of Chemical Physics,2013,138(1):257-265.
[8]韩晓军,赵宇,杨国环.基于小波变换的肝脏CT图像分类[J].天津工业大学学报,2015,34(1):59-63.
[9]周平,李传富,符志鹏.基于小波分解的脑CT图像纹理特征提取[J].仪器仪表学报2010,31(3):643-648.
[10]周涛,蒋芸,王勇,等.基于小波神经网络的医学图像分类方法[J].计算机应用,2010,30(10):2856-2860.
[11]聂会星,梁坤,徐枞巍.基于小波变换和支持向量机的人脸识别研究[J].合肥工业大学学报(自然科学版),2011,34(2):208-211.
[12]S.G.Mallat.Multi-frequency channel decompositions of images and wavelet models[J].IEEE Traps.Acoust Speech and Signal Process,1989,37(12):2091-2110.
[13]胡昌华,李国华,周涛.基于MATLAB 7.x的系统分析与设计——小波分析.第三版[M].西安电子科技大学出版社,2008.15-22.
[14]高清河,刚晶,王和禹,等.基于小波变换的多模态医学图像的融合及性能评价[J].生物医学工程研究,2014,33(4):259-263.
[15]Patrick J,Sun DW,Paul A.Comparison of various wavelet texture features to predict beef palatability[J].Meat Sci,2009,83:82-87.
[16]Engin A.Comparison of wavelet families for texture classification by using wavelet packet entropy adaptive network based fuzzy inference system[J].Appl soft Comput,2008,8:225-231.
[17]刘莹.图像纹理的特征提取和分类方法研究[D].华中科技大学,2013.
[18]木拉提·哈米提,孔喜梅,严传波等.新疆维吾尔草药图像特征提取及分类研究[J].新疆医科大学学报,2015,38(7):815-822.
[19]Holzinger,Andreas.Data Mining with Decision Trees:Theory and Applications[J].Online Information Review,2015,39(3):437-438.
[20]张慧,迟庆云,刘彩霞.基于灰度共生矩阵的肝癌B超纹理特征决策树诊断分析[J].中国医药指南,2015,13(25):2-3.
[21]苗红星,余建坤.基于决策树的ID3算法和C4.5算法的比较[J].现代计算机(专业版),2014(10):7-10.
[22]Nanthagopal A P,Rajamony R S.Automatic classification of brain computed tomography images using wavelet-based statistical texture features[J].Journal of Visualization,2012,15(4):363-372.
[23]Yuan XD,Quan CB,AO GK.ROC analysis of CT hemodynamic in the diagnosis of breast cancer[J].The Chinese-German Journal of Clinical Oncology,2010,9(3):165-168.
[24]张岁霞,木拉提·哈米提,姚娟,等.基于集成分类器的新疆哈萨克族食管癌分型的研究[J].生物医学工程研究,2015,34(4):216-223.