不同预处理方法结合特征的食管癌图像分类
|
摘要
为了探讨不同的预处理方法,结合形状和纹理特征,对新疆哈萨克族食管癌图像的分类效果,通过采用锐化、中值滤波结合锐化和中值滤波结合直方图均衡化三种方法对溃疡型和缩窄型食管癌图像进行预处理;然后提取Hu不变矩形状特征和灰度共生矩阵纹理特征;最后用K最近邻(KNN)分类器分类,以验证预处理方法对图像的功效和特征的分类效率。结果表明:锐化预处理后图像的Hu不变矩、灰度共生矩阵和混合特征分类准确率分别为93. 27%、73. 35%、92. 91%。可见锐化方法能突出图像细节,提高特征的代表性; Hu不变矩形状特征的分类效率优于灰度共生纹理特征的分类效率,锐化滤波结合Hu不变矩形状特征更适合新疆哈萨克族食管癌的分类研究。
In order to discuss the classification effect of different pretreatment methods combined with shape and texture features on Xinjiang Kazakh esophageal cancer images,firstly,the images of ulcerated and constricted esophageal cancer were preprocessed by sharpening,median filtering combined with sharpening and median filtering combined with histogram equalization,and then Hu invariant moments feature and gray level co-occurrence matrix feature were extracted. The features were finally classified by the KNN classifier to verify the efficiency of the preprocessing method on the image and the classification efficiency of the features. The results show that the accuracy of Hu invariant moments,gray level co-occurrence matrix and mixed feature classification after sharpening preprocessing are 93. 27%,73. 35% and 92. 91%,respectively. It is concluded that the sharpening method can highlight the details of the image and improve the representation of the feature; The classification efficiency of Hu invariant moments shape feature is better than that of gray level co-occurrence matrix texture feature classification. Obviously,the sharpening filter combined with hu invariant Moments shape features is more suitable for the classification research of Xinjiang Kazakh esophageal cancer.
In order to discuss the classification effect of different pretreatment methods combined with shape and texture features on Xinjiang Kazakh esophageal cancer images,firstly,the images of ulcerated and constricted esophageal cancer were preprocessed by sharpening,median filtering combined with sharpening and median filtering combined with histogram equalization,and then Hu invariant moments feature and gray level co-occurrence matrix feature were extracted. The features were finally classified by the KNN classifier to verify the efficiency of the preprocessing method on the image and the classification efficiency of the features. The results show that the accuracy of Hu invariant moments,gray level co-occurrence matrix and mixed feature classification after sharpening preprocessing are 93. 27%,73. 35% and 92. 91%,respectively. It is concluded that the sharpening method can highlight the details of the image and improve the representation of the feature; The classification efficiency of Hu invariant moments shape feature is better than that of gray level co-occurrence matrix texture feature classification. Obviously,the sharpening filter combined with hu invariant Moments shape features is more suitable for the classification research of Xinjiang Kazakh esophageal cancer.
引文
1 Chen W,Zheng R,Zeng H,et al. Annual report on status of cancer in China,2011[J]. Chinese Journal of Cancer Research,2015,27(1):2-12
2 孙秀彬.小地域内食管癌空间流行病学特征及其地理危险因素研究[D].济南:山东大学,2017Sun Xiubin. Spatial epidemiology and the geographical risk factors of esophageal cancer on a smaller scale[D]. Jinan:Shandong University,2017
3 陈湘川,庞丽娟,李锋.新疆哈萨克族食管癌研究进展[J].农垦医学,2006,28(5):384-387Chen Xiangchuan,Pang Lijuan,Li Feng. Research progress of Xinjiang Kazakh esophageal cancer[J]. Journal of Nongken Medicine,2006,28(5):384-387
4 赵凤娟,云妙英,张严,等.新疆哈萨克族食管癌研究进展[J].中央民族大学学报(自然科学版),2009,18(3):85-90Zhao Fengjuan,Yun Miaoying,Zhang Yan,et al. The research progress of esophageal cancer in Xinjiang Kazakh[J]. Journal of Minzu University of China(Natural Sciences Edition),2009,18(3):85-90
5 周兰华.产前超声医学图像处理技术研究进展[J].医学信息,2017,30(18):31-32Zhou Lanhua. Research progress on prenatal ultrasound medical image processing technology[J]. Medical Information,2017,30(18):31-32
6 刘千顺.数字图像去噪、锐化与颜色增强研究[D].杭州:浙江大学,2016Liu Qianshun. Research on denoising,sharpening and color enhancement about digital image enhancement[D]. Hangzhou:Zhejiang University of Technology,2016
7 寇毛蕊.医学图像分析系统设计[J].数码世界,2017,(9):78Kou Maorui. Design of medical image analysis system[J]. Digital Space,2017,(9):78
8 郭金鸽.基于纹理特征的医学图像检索技术的研究与应用[D].包头:内蒙古科技大学,2012Guo Jinge. The research and application of medical image retrival technology based on texture feature[D]. Baotou:Inner Mongolia University of Science and Technology,2012
9 陈瑾,王海屹,叶慧义.纹理分析在肿瘤影像学中的研究进展[J].中华放射学杂志,2017,(12):979-982Chen Yu,Wang Haijun,Ye Huiyi. Research progress of texture analysis in tumor imaging[J]. Chinese Journal of Radiology,2017,(12):979-982
10 Haralick R M,Shanmugam K,Dinstein I. Textural features for image classification[J]. Systems Man&Cybernetics IEEE Transactions on,1973,3(6):610-621
11 Haralick R M. Statistical and structural approaches to texture[J].Proceedings of the IEEE,2005,67(5):786-804
12 余丽萍,黎明,杨小芹,等.基于灰度共生矩阵的断口图像识别[J].计算机仿真,2010,27(4):224-227Yu Liping,Li Ming,Yang Xiaoqin,et al. Recognition of fracture image based on gray level co-occurrence matrix[J]. Computer Simulation,2010,27(4):224-227
13 林森森,姜新国,彭小芳,等.基于灰度共生矩阵的乳腺肿瘤纹理特征提取[J].徐州医学院学报,2013,33(3):196-198Lin Sensen,Jiang Xinguo,Peng Xiaofang,et al. Extraction of breast tumor texture features based on graylevel co-occurrence matrix[J].Acta Academiae Medicinae Xuzhou,2013,33(3):196-198
14 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):46-50Zhang Suixia,Yan Chuanbo,Hamit Murat,et al. Classification on Xinjiang Kazak esophageal disease based on KNN classifier[J]. Bulletin of Science and Technology,2016,32(8):46-50
15 李弼程,彭天强,彭波.智能图像处理技术[M].北京:电子工业出版社,2004Li Yicheng,Peng Tianqiang,Peng Bo. Intelligent image processing technology[M]. Beijing:Publishing House of Electronics Industry,2004
16 史延新.基于形状特征的图像检索算法研究[J].电子科技,2008,21(12):69-71Shi Yanxin. Image retrieval algorithm based on the shape characteristic[J]. Electronic Science and Technology,2008,21(12):69-71
17 陈良宵,王斌.基于形状特征的叶片图像识别算法比较研究[J].计算机工程与应用,2017,53(9):17-25Chen Liangxiao,Wang Bin. Comparative study of leaf image recognition algorithm based on shape feature[J]. Computer Engineering and Applications,2017,53(9):17-25
18 Hu M. Visual pattern recognition by moment invariants[J]. Information Theory Ire Transactions on,1962,8(2):179-187
19 Prokop R J,Reeves A P. A survey of moment-based techniques for unoccluded object representation and recognition[J]. Cvgip Graphical Models&Image Processing,1992,54(5):438-460
20 Altman N S. An introduction to kernel and nearest-neighbor nonparametric regression[J]. American Statistician,1992,46(3):175-185
21 毋雪雁,王水花,张煜东. K最近邻算法理论与应用综述[J].计算机工程与应用,2017,53(21):1-7Wu Xueyan,Wang Shuihua,Zhang Yudong. Survey on theory and application of K-Nearest-Neighbors algorithm[J]. Computer Engineering and Applications,2017,53(21):1-7
22 骆名剑.基于ROC的分类算法评价方法[D].武汉:武汉科技大学,2005Luo Mingjian. ROC-based classification algorithm evaluation method[D]. Wuhan:Wuhan University of Science and Technology,2005
2 孙秀彬.小地域内食管癌空间流行病学特征及其地理危险因素研究[D].济南:山东大学,2017Sun Xiubin. Spatial epidemiology and the geographical risk factors of esophageal cancer on a smaller scale[D]. Jinan:Shandong University,2017
3 陈湘川,庞丽娟,李锋.新疆哈萨克族食管癌研究进展[J].农垦医学,2006,28(5):384-387Chen Xiangchuan,Pang Lijuan,Li Feng. Research progress of Xinjiang Kazakh esophageal cancer[J]. Journal of Nongken Medicine,2006,28(5):384-387
4 赵凤娟,云妙英,张严,等.新疆哈萨克族食管癌研究进展[J].中央民族大学学报(自然科学版),2009,18(3):85-90Zhao Fengjuan,Yun Miaoying,Zhang Yan,et al. The research progress of esophageal cancer in Xinjiang Kazakh[J]. Journal of Minzu University of China(Natural Sciences Edition),2009,18(3):85-90
5 周兰华.产前超声医学图像处理技术研究进展[J].医学信息,2017,30(18):31-32Zhou Lanhua. Research progress on prenatal ultrasound medical image processing technology[J]. Medical Information,2017,30(18):31-32
6 刘千顺.数字图像去噪、锐化与颜色增强研究[D].杭州:浙江大学,2016Liu Qianshun. Research on denoising,sharpening and color enhancement about digital image enhancement[D]. Hangzhou:Zhejiang University of Technology,2016
7 寇毛蕊.医学图像分析系统设计[J].数码世界,2017,(9):78Kou Maorui. Design of medical image analysis system[J]. Digital Space,2017,(9):78
8 郭金鸽.基于纹理特征的医学图像检索技术的研究与应用[D].包头:内蒙古科技大学,2012Guo Jinge. The research and application of medical image retrival technology based on texture feature[D]. Baotou:Inner Mongolia University of Science and Technology,2012
9 陈瑾,王海屹,叶慧义.纹理分析在肿瘤影像学中的研究进展[J].中华放射学杂志,2017,(12):979-982Chen Yu,Wang Haijun,Ye Huiyi. Research progress of texture analysis in tumor imaging[J]. Chinese Journal of Radiology,2017,(12):979-982
10 Haralick R M,Shanmugam K,Dinstein I. Textural features for image classification[J]. Systems Man&Cybernetics IEEE Transactions on,1973,3(6):610-621
11 Haralick R M. Statistical and structural approaches to texture[J].Proceedings of the IEEE,2005,67(5):786-804
12 余丽萍,黎明,杨小芹,等.基于灰度共生矩阵的断口图像识别[J].计算机仿真,2010,27(4):224-227Yu Liping,Li Ming,Yang Xiaoqin,et al. Recognition of fracture image based on gray level co-occurrence matrix[J]. Computer Simulation,2010,27(4):224-227
13 林森森,姜新国,彭小芳,等.基于灰度共生矩阵的乳腺肿瘤纹理特征提取[J].徐州医学院学报,2013,33(3):196-198Lin Sensen,Jiang Xinguo,Peng Xiaofang,et al. Extraction of breast tumor texture features based on graylevel co-occurrence matrix[J].Acta Academiae Medicinae Xuzhou,2013,33(3):196-198
14 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):46-50Zhang Suixia,Yan Chuanbo,Hamit Murat,et al. Classification on Xinjiang Kazak esophageal disease based on KNN classifier[J]. Bulletin of Science and Technology,2016,32(8):46-50
15 李弼程,彭天强,彭波.智能图像处理技术[M].北京:电子工业出版社,2004Li Yicheng,Peng Tianqiang,Peng Bo. Intelligent image processing technology[M]. Beijing:Publishing House of Electronics Industry,2004
16 史延新.基于形状特征的图像检索算法研究[J].电子科技,2008,21(12):69-71Shi Yanxin. Image retrieval algorithm based on the shape characteristic[J]. Electronic Science and Technology,2008,21(12):69-71
17 陈良宵,王斌.基于形状特征的叶片图像识别算法比较研究[J].计算机工程与应用,2017,53(9):17-25Chen Liangxiao,Wang Bin. Comparative study of leaf image recognition algorithm based on shape feature[J]. Computer Engineering and Applications,2017,53(9):17-25
18 Hu M. Visual pattern recognition by moment invariants[J]. Information Theory Ire Transactions on,1962,8(2):179-187
19 Prokop R J,Reeves A P. A survey of moment-based techniques for unoccluded object representation and recognition[J]. Cvgip Graphical Models&Image Processing,1992,54(5):438-460
20 Altman N S. An introduction to kernel and nearest-neighbor nonparametric regression[J]. American Statistician,1992,46(3):175-185
21 毋雪雁,王水花,张煜东. K最近邻算法理论与应用综述[J].计算机工程与应用,2017,53(21):1-7Wu Xueyan,Wang Shuihua,Zhang Yudong. Survey on theory and application of K-Nearest-Neighbors algorithm[J]. Computer Engineering and Applications,2017,53(21):1-7
22 骆名剑.基于ROC的分类算法评价方法[D].武汉:武汉科技大学,2005Luo Mingjian. ROC-based classification algorithm evaluation method[D]. Wuhan:Wuhan University of Science and Technology,2005
© 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 |