基于改进的FCM模糊聚类的颅内出血CT图像分割研究
|
摘要
本文针对人脑CT图像的出血病灶区域,提出了一种改进的模糊C-均值(Fuzzy C-Means,FCM)算法进行颅脑内出血病灶的分割。首先对颅脑CT图像进行预分割,通过左右扫描算法和中值滤波算法将颅内结构从源CT图像中提取出来;然后对预分割而得到的颅内结构,利用在目标函数和隶属度函数中分别添加空间信息的改进FCM聚类算法进行出血病灶提取。通过对CT颅脑图像和添加椒盐噪声的CT颅脑图像进行病灶分割,结果显示本文算法对噪声不敏感,可以准确分割出出血病灶。
In this paper, an improved fuzzy C-means(FCM) algorithm for the segmentation of intracranial hemorrhage lesions was proposed for the hemorrhagic lesions of human brain CT images. Firstly, the brain CT images were pre-divided, and the intracranial structures were extracted from the source CT images by left and right scanning algorithm and median fi ltering algorithm. Then the pre-segmentation intracranial structures were obtained by adding the objective function and membership function to the spatial information of improved FCM clustering algorithm for extraction of hemorrhagic lesions. Through CT brain images and CT brain images with salt and pepper noise segmentation, the results showed that the algorithm was insensitive to noise and can accurately segregate hemorrhagic lesions.
In this paper, an improved fuzzy C-means(FCM) algorithm for the segmentation of intracranial hemorrhage lesions was proposed for the hemorrhagic lesions of human brain CT images. Firstly, the brain CT images were pre-divided, and the intracranial structures were extracted from the source CT images by left and right scanning algorithm and median fi ltering algorithm. Then the pre-segmentation intracranial structures were obtained by adding the objective function and membership function to the spatial information of improved FCM clustering algorithm for extraction of hemorrhagic lesions. Through CT brain images and CT brain images with salt and pepper noise segmentation, the results showed that the algorithm was insensitive to noise and can accurately segregate hemorrhagic lesions.
引文
[1]张光胜,邹友峰,卢小平,等.基于改进分块阈值的SAR图像分割算法[J].测绘通报,2013,(12):28-30.
[2]肖明尧,李雄飞,张小利,等.基于多尺度的区域生长的图像分割算法[J].吉林大学学报(工学版),2017,(5):1591-1597.
[3]孙中原,张继武,常桂然.一种基于形态学方法优化的种子填充算法及其在脑组织CT影像自动分割中应用[J].中国临床医学杂志,2002,13(6):384-43 2.
[4]蒋小波.GVF Snake模型及其在图像分割中的应用研究[D].无锡:江南大学,2015.
[5]刘杰.基于Snake模型的图像分割算法研究[D].重庆:重庆邮电大学,2016.
[6]Caselles V,Coll T.A geome tric model for active contours in image processing[J].Numer Math,1993,66(1):1-31.
[7]汪亮,金福江,陈峻严.基于区域生长和FCM模糊聚类的颅内出血CT图像分割[J].系统仿真学报,2014,26(2):231-235.
[8]宋国权,李金锋.基于聚类算法的脑部MR图像分割[J].中国医疗设备,2017,32(1):26-29.
[9]Chuang KS,Tzeng HL,Chen S,et al.Fuzzy c-means clustering with spatial information for image segmentation[J].Comput Med Imag Grap,2006,30(1):9-15.
[10]李杰,陈国栋.基于改进区域生长算法的肝脏管道图像分割方法[J].中国医疗设备,2014,29(10):19-23.
[11]陈元堃.改进的FCM算法在脑部图像分割中的应用研究[D].大连:大连海事大学,2017.
[12]Chen S,Zhang D.Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[A].Systems Man&Cybernetics Part B Cybernetics IEEE Transactions on[C].2004,34(4):1907.
[13]王海波.颅脑CT图像分割算法研究[D].哈尔滨:哈尔滨工程大学,2009.
[14]Zhao F,Jiao L,Liu H.Kernel generalized fuzzy C-means clustering with spatial information for image segmentation[J].Digit Signal Process,2013,23(1):184-199.
[15]Chen S,Zhang D.Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[A].Systems Man&Cybernetics Part B Cybernetics IEEE Transactions on[C].2004,34(4):1907.
[16]张文君,顾行发,陈良富,等.基于均值—标准差的K均值初始聚类中心选取算法[J].遥感学报,2006,10(5):715-721.
[2]肖明尧,李雄飞,张小利,等.基于多尺度的区域生长的图像分割算法[J].吉林大学学报(工学版),2017,(5):1591-1597.
[3]孙中原,张继武,常桂然.一种基于形态学方法优化的种子填充算法及其在脑组织CT影像自动分割中应用[J].中国临床医学杂志,2002,13(6):384-43 2.
[4]蒋小波.GVF Snake模型及其在图像分割中的应用研究[D].无锡:江南大学,2015.
[5]刘杰.基于Snake模型的图像分割算法研究[D].重庆:重庆邮电大学,2016.
[6]Caselles V,Coll T.A geome tric model for active contours in image processing[J].Numer Math,1993,66(1):1-31.
[7]汪亮,金福江,陈峻严.基于区域生长和FCM模糊聚类的颅内出血CT图像分割[J].系统仿真学报,2014,26(2):231-235.
[8]宋国权,李金锋.基于聚类算法的脑部MR图像分割[J].中国医疗设备,2017,32(1):26-29.
[9]Chuang KS,Tzeng HL,Chen S,et al.Fuzzy c-means clustering with spatial information for image segmentation[J].Comput Med Imag Grap,2006,30(1):9-15.
[10]李杰,陈国栋.基于改进区域生长算法的肝脏管道图像分割方法[J].中国医疗设备,2014,29(10):19-23.
[11]陈元堃.改进的FCM算法在脑部图像分割中的应用研究[D].大连:大连海事大学,2017.
[12]Chen S,Zhang D.Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[A].Systems Man&Cybernetics Part B Cybernetics IEEE Transactions on[C].2004,34(4):1907.
[13]王海波.颅脑CT图像分割算法研究[D].哈尔滨:哈尔滨工程大学,2009.
[14]Zhao F,Jiao L,Liu H.Kernel generalized fuzzy C-means clustering with spatial information for image segmentation[J].Digit Signal Process,2013,23(1):184-199.
[15]Chen S,Zhang D.Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure[A].Systems Man&Cybernetics Part B Cybernetics IEEE Transactions on[C].2004,34(4):1907.
[16]张文君,顾行发,陈良富,等.基于均值—标准差的K均值初始聚类中心选取算法[J].遥感学报,2006,10(5):715-721.