摘要
目的探讨计算机辅助诊断技术在肝包虫病和肝囊肿CT图像分型中的应用。方法对单囊型肝包虫病和单发性肝囊肿CT图像感兴趣区域,分别使用传统的预处理方法和图像融合方法,提取原始ROI、预处理后的和融合后的ROI图像Haar小波、DB2小波、Tamura、Gabor滤波器和灰度-梯度共生矩阵特征,通过支持向量机和BP神经网络分类模型分类,比较三种方法的分类准确率,并对各分类模型进行参数评估。结果从原始ROI图像直接提取的Haar小波、DB2小波、Tamura和GGCM特征的最佳分类准确率均达到了95%以上;融合后的ROI图像五种特征的分类准确率都较高,在90%以上。结论本研究所使用的方法应用于肝包虫病和肝囊肿CT图像的分型中具有一定的分类优势,为影像学诊断提供依据。
Objective To discuss the application of computer aided diagnosis in classification of hepatic hydatid disease and hepatic cyst CT images.Methods For the region of the CT image of single cystic hepatic echinococcosis and single hepatic cyst, the original ROI, pre-processed and fused ROI image Haar wavelet, DB2 were extracted using traditional pre-processing methods and image fusion methods, respectively. Wavelet, Tamura, Gabor filter and gray-gradient co-occurrence matrix characteristics are classified by support vector machine and BP neural network classification model. The classification accuracy of the three methods is compared, and the parameters of each classification model are evaluated. Results The best classification accuracy of Haar wavelet, DB2 wavelet,Tamura and GGCM features extracted from the original ROI image reached more than 95%. The classification accuracy of the five characteristics of the ROI image after fusion is higher,above 90%.Conclusion The method used in this study has a certain classification advantage in the classification of CT images of hepatic hydatidosis and hepatic cysts, and provides a basis for imaging diagnosis.
引文
[1]Memmet Mihmanli,Ufuk Oguz Idiz,Cemal Kaya,et al.Current status of diagnosis and treatment of hepatic echinococcosis[J].World J Hepatol,2016,8(28):1169-1181.
[2]王波涛,刘刚,樊文萍,等.纹理特征分析在肝囊肿及肝血管瘤磁共振成像鉴别诊断中的价值[J].中国医学科学院学报,2017,39(2):169-176.
[3]王晓雷,郝文超,刘志军,等.肝包虫病误诊为肝囊肿原因分析及文献复习[J].临床误诊误治,2017,30(2):4-6.
[4]周靖宇.基于MRI的乳腺癌计算机辅助检测与诊断系统的应用和进展[J].功能与分子医学影像学,2017,6(4):1349-1353.
[5]Taher F,Werghi N,Al-Ahmad H.Computer Aided Diagnosis System for Early Lung Cancer Detection[J].International Conference on Systems,2015,8(4):5-8.
[6]张岁霞,木拉提·哈米提,严传波,等.基于数据挖掘的新疆高发肝包虫病的分型研究[J].生物医学工程与临床,2016,20(5):521-528.
[7]孔喜梅,木拉提·哈米提,严传波,等.基于小波变换的新疆地方性肝包虫CT图像分类研究[J].生物医学工程研究,2016,35(3):162-167.
[8]Zhang XL,Li XF,Feng YC.Image fusion based on simultaneous empirical wavelet transform[J].Multimedia Tools&Applications,2017,76(6):1-19.
[9]张静,倪红霞,苑春苗,等.精通MATLAB数字图像处理与识别[M].北京:人民邮电出版社,2013:95-98,131-137,222-232.
[10]姚飞,闫晓丽,苏景霞,等.基于中值和同态滤波器相结合增强图像的研究[J].科技视界,2014(6):14,25.
[11]Aman Ghasemzadeh,Hasan Demirel.3D discrete wavelet transform-based feature extraction for hyperspectral face recognition[J].IET Biometrics,2018,7(1):49-55.
[12]甘露,田丽华,李晨.基于融合特征和BP网络的交通标志识别方法[J].计算机工程与设计,2017,38(10):2783-2787.
[13]高源,宋辉,张志佳.基于Tamura特征的虹膜结构密度计算方法[J].计算机技术与发展,2016,26(3):36-39.
[14]Hu S,Xu C,Guan WQ,et al.Texture feature extraction based on wavelet transform and gray-level co-occurrence matrices applied to osteosarcoma diagnosis[J].Bio-Medical Materials and Engineering,2014,24(1):129-143.
[15]de Carvalho Filho AO,Silva AC,de Paiva AC,et al.Computer-aided diagnosis system for lung nodules based on computed tomography using shape analysis,a genetic algorithm,and SVM[J].Med Biol Eng Comput,2017,55(8):1129-1146.
[16]Wang XJ,Bai YP.BP Network Based on Handwritten Digital Image Feature Extraction[J].Advances in Applied Mathematics,2014,3(11):104-111.