北京生物医学工程

基于特征融合的肝包虫病CT图像识别

CT image recognition of liver hydatid disease based on feature fusion

作者：排孜丽耶·尤山塔依严传波木拉提·哈米提姚娟阿布都艾尼·库吐鲁克吴淼

单位：新疆医科大学基础医学院（乌鲁木齐 830011）新疆医科大学医学工程技术学院（乌鲁木齐 830011）新疆医科大学第一附属医院影像中心（乌鲁木齐 830011）

关键词：肝包虫病；特征融合；计算机辅助诊断；特征提取；分类识别

分类号：R318.04

出版年·卷·期（页码）：2019·38·4（400-406）

摘要：

目的探讨特征融合方法在肝包虫病CT图像分类识别中的应用，旨在提高肝包虫病的诊断准确率。方法选取正常肝脏和单囊型肝包虫病CT图像各150张，对每幅图像采取空域与频域滤波算法、数学形态学算法和点处理，分别得到10幅特征子图像并对它们进行特征融合，对融合后的图像提取灰度和纹理特征，通过统计学分析筛选关键特征。结果对提取的10维特征进行统计学分析，得到正常肝脏和单囊型肝包虫CT融合图像之间完全没有交集的4个灰度和1个纹理特征取值范围，由此来区分肝包虫病与正常肝脏CT图像。结论从原始图像中提取特征子图像并进行融合，再对融合后图像提取特征的方法能够很好地区分识别正常肝脏和单囊型肝包虫病CT图像，为肝包虫病的早期诊断提供依据。

Objective To discuss the application of feature fusion method in the CT image classification and recognition of hepatic hydatid disease, in order to improve the diagnosis classification of hepatic echinococcosis. Methods CT medical images of normal liver and single cystic hepatic hydatid disease were selected，each 150 spatial and frequency-domain filtering algorithms, mathematical morphology algorithms and point processing were used to each image to obtain 10 feature images respectively and fused them effectively. Grayscale and texture features were extracted from each fused images, and the key features were selected by statistical analysis. Results Statistical analysis was performed on the extracted 10-dimensional features and obtained 4 gray scales and 1 texture features range with no intersection between the normal liver and single-cystic hepatic hydatid fused image, thereby distinguishing the liver hydatid disease and normal liver CT images. Conclusions Extracting feature sub-images from the original image and fusing them, extracting gray and texture features from the fused image can distinguish the CT images of normal liver and single-cystic hepatic hydatid, it also providing evidence for the early diagnosis of hepatic hydatid disease.

参考文献：

[1] 雷军强, 陈勇, 王晓慧, 等. 肝包虫病的CT和MR诊断[J]. 中国医学影像技术, 2010, 26(2): 291-293.

Lei JQ, Chen Y, Wang XH, et al. CT and MR diagnosis of hepatic hydatidosis[J]. Chinese Journal of Medical Imaging Technology,2010,26(2): 291-293.

[2] 袁雁雯, 凯撒尔, 管文举. 囊性肝包虫病的CT诊断[J]. 山东医科大学学报, 2015, 46(9): 896-898.

[3] 张壮志, 张文宝, 石保新, 等. 我国包虫病防控及其面临的困难[J].兽医导刊, 2011, (6): 27-29.

[4] 张壮志, 库尔班·居麦, 陈永强, 等. 包虫病防控的困难与回顾[J].中国动物保健, 2017, 19(7): 33-35.

[5] 温浩. 肝包虫病诊断和手术治疗新进展[J]. 中华消化外科杂志, 2011, 10(4): 290-292.

Wen H. Advancement of diagnosis and surgical treatment for hepatic echinococcosis [J]. Chinese Journal of Digestive Surgery, 2011, 10(4): 290-292.

[6] 陈先志. 肝包虫的CT诊断价值[J]. 医药前沿, 2014, (35): 43-44.

[7] Chang CC, Chen HH, Chang YC, et al. Computer-aided diagnosis of liver tumors on computed tomography images [J]. Computer Methods & Programs in Biomedicine, 2017, 145(4): 45-51.

[8] Yang HC, Lu R, Wu CC, et al. Reliable and stable computer-aided diagnosis systems for images[J]. Computer Methods & Programs in Biomedicine, 2016, 128: A1-A2.

[9] 葛晓倩. 计算机辅助诊断在血糖领域的应用发展分析[J]. 科学与财富, 2016, (12): 403-403.

[10] Fatima T, Naoufel W, Hussain A. Computer aided diagnosis system for early lung cancer detection [J]. Algorithms, 2015, 8(4): 1088-1110.

[11] Park SM, Kim EM, Lee BH. Computer-aided diagnosis system for detection of liver tumor in CT liver image [J]. International Congress，2005，1281(3): 1404-1404.

[12] 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.

Kong XM, Murat H, Yan CB, et al. Xinjiang local liver hydatid ct images classification and research based wavelet transform [J]. Journal of Biomedical Engineering Research, 2016, 35(3): 162-167.

[13] 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.

Zhang SX, Murat H, Yan CB, et al. Classification of hepatic hydatidosis in xinjiang based on data mining [J]. Biomedical Engineering & Clinical Medicine, 2016, 20(5): 521-528.

[14] 桂婷. 肝癌B超图像的计算机辅助诊断研究[D].杭州: 浙江工业大学, 2008.

Gui T. The Study of computer aided diagnosis of b-ultrasonic medical images of liver cancer [D]. Hangzhou：Zhejiang University of Technology, 2008.

[15] 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.

[16] 张汗灵. MATLAB在图像处理中的应用[M]. 北京: 清华大学出版社, 2008: 114，138.

[17] Gonzalez RC, Woods RE, Eddins SL. Digital image processing using MATLAB [M]. Beijing: Publishing House of Electronics Industry, 2009: 423-431.

[18] 张强, 王正林. 精通MATLAB图像处理[M]. 北京: 电子工业出版社, 2009: 197-199.

[19] 杨芳, 木拉提·哈米提, 严传波, 等. 基于SVM的新疆哈萨克族食管癌医学图像特征提取及分类研究[J]. 科技通报, 2016, 32(3): 53-57.

Yang F, Murat H, Yan CB, et al. Feature extraction and classification for Xinjiang Kazak esophageal cancer based on SVM [J]. Bulletin of Science and Technology, 2016, 32(3): 53-57.

[20] Yang F, Murat H, Yan CB, et al. Feature extraction and classification on esophageal x-ray images of Xinjiang Kazak nationality [J]. Journal of Healthcare Engineering, 2017, 2017(5): 1-11.

[21] 孔喜梅, 木拉提·哈米提, 严传波, 等. 新疆高发病食管癌图像的特征提取及分类[J]. 北京生物医学工程, 2017, 36(1): 37-43.

Kong XM, Murat H, Yan CB, et al. Feature extraction and classification of x-ray images for Xinjiang Esophageal cancer with high morbidity[J]. Beijing Biomedical Engineering, 2017, 36(1): 37-43.

[22] 张岁霞, 严传波, 木拉提·哈米提, 等. KNN分类器在新疆哈萨克族食管癌分型中的应用[J]. 科技通报, 2016, 32(8): 46-50.

Zhang SX, Yan CB, Murat H, et al. Classification on Xinjiang Kazak esophageal disease based on KNN classifier [J]. Bulletin of Science and Technology, 2016, 32(8): 46-50.

[23] 张洪举. 网站数据分析: 数据驱动的网站管理、优化和运营[M]. 北京: 机械工业出版社, 2013: 268.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录