MRF细胞图像自动分割方法设计
|
摘要
针对目前医学细胞图像分割出现的误分割、人为主观因素影响时间效率低等特点,提出了一种结合基于中国餐馆过程的马尔可夫随机场(MRF)细胞图像自动分割方法。首先对图像进行去噪处理,然后采用中国餐厅过程的无监督模型对马尔科夫随机场进行自动确定参数,最后采用条件迭代模式(ICM)方法实现MRF在图像分割并对其口腔粘膜细胞图像进行分割实验,并与传统的马尔可夫随机场图像分割和3种不同的细胞图像分割方法进行比较。结果表明,本文提出的方法无需事先估计参数值,在精确度上能达到96%以上。通过本文算法基本能够准确找到要分割的双核和微核细胞,为后期细胞图像识别打基础,有效解决分割受到人为主观因素影响和精度差等问题。
In view of the current misdivision of medical cell image segmentation and the low time efficiency of human subjective factors,an automatic image segmentation method based on Markov Random Field(MRF)based on Chinese restaurant process was proposed.Firstly,the image was denoised.Then,the Markov random field was automatically determined using the unsupervised mode of the Chinese restaurant process.Finally,the conditional iteration mode(ICM)method was used to implement MRF image segmentation and its oral mucosal cell image,and compared with traditional Markov random field image segmentation and three different cell image segmentation methods.The results show that the method proposed in this paper does not need to estimate the parameter values in advance,and it can reach more than 96%in accuracy.The algorithm can basically find the binucleate and micronucleus cells to be segmented accurately by using this algorithm,which will lay a foundation for the later cell image recognition.The effective solution to segmentation is subject to subjective factors and poor accuracy.
In view of the current misdivision of medical cell image segmentation and the low time efficiency of human subjective factors,an automatic image segmentation method based on Markov Random Field(MRF)based on Chinese restaurant process was proposed.Firstly,the image was denoised.Then,the Markov random field was automatically determined using the unsupervised mode of the Chinese restaurant process.Finally,the conditional iteration mode(ICM)method was used to implement MRF image segmentation and its oral mucosal cell image,and compared with traditional Markov random field image segmentation and three different cell image segmentation methods.The results show that the method proposed in this paper does not need to estimate the parameter values in advance,and it can reach more than 96%in accuracy.The algorithm can basically find the binucleate and micronucleus cells to be segmented accurately by using this algorithm,which will lay a foundation for the later cell image recognition.The effective solution to segmentation is subject to subjective factors and poor accuracy.
引文
[1]LIU F J,XING F Y,ZHANG Z Z,et al.Robust muscle cell quantification using structured edge detection and hierarchical segmentation[C]//Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015.Cham:Springer,2015.
[2]王娅.血液红细胞图像自适应标记分水岭分割算法[J].中国图象图形学报,2017,22(12):1779-1787.WANG Y.Adaptive marked watershed segmentation algorithm for red blood cell images[J].Journal of Image and Graphics,2017,22(12):1779-1787.(in Chinese)
[3]陈恺,陈芳,戴敏,等.基于萤火虫算法的二维熵多阈值快速图像分割[J].光学精密工程,2014,22(2):517-523.CHEN K,CHEN F,DAI M,et al.Fast image segmentation with multilevel threshold of two-dimensional entropy based on firefly algorithm[J].Optics and Precision Engineering,2014,22(2):517-523.(in Chinese)
[4]LI C M,XU C Y,GUI C F,et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
[5]SCAMAN M E,ECONOMIKOS L.Computer vision for automatic inspection of complex metal patterns on multichip modules(MCM-D)[J].IEEE Transactions on Components,Packaging,and Manufacturing Technology:Part B,1995,18(4):675-684.
[6]尹诗白,王一斌,邓箴.基于快速递推模糊2-划分熵图割的红外图像分割[J].光学精密工程,2016,24(3):668-680.YI S B,WANG Y B,DENG Z.Infrared image segmentation based on graph cut of fast recursive fuzzy 2-partition entropy[J].Optics and Precision Engineering,2016,24(3):668-680.(in Chinese)
[7]吴秋红,吴谨,朱磊,等.基于图论和FCM的图像分割算法[J].液晶与显示,2016,31(1):112-116.WU Q H,WU J,ZHU L,et al.Image segmentation algorithm based on graph theory and FCM[J].Chinese Journal of Liquid Crystals and Displays,2016,31(1):112-116.(in Chinese)
[8]LI Y,ZHU R,MI L,et al.Segmentation of white blood cell from acute lymphoblastic leukemia images using dual-threshold method[J].Computational and Mathematical Methods in Medicine,2016,2016:9514707.
[9]徐胜军,韩九强,刘光辉.基于马尔可夫随机场的图像分割方法综述[J].计算机应用研究,2013,30(9):2576-2582.XU S J,HAN J Q,LIU G H.Survey of image segmentation methods based on Markov random fields[J].Application Research of Computers,2013,30(9):2576-2582.(in Chinese)
[10]标本.基于马尔科夫随机场、模糊理论、D-S理论的医学图像融合分割方法及研究[D].昆明:昆明理工大学,2017.BIAO B.Segmentation method and research of medical image fusion based on Markov random field,fuzzy theory and D-S theory[D].Kunming:Kunming University of Science and Technology,2017.(in Chinese)
[11]李长春,都伟冰,马潇潇,等.改进马尔可夫模型的SAR图像分割[J].遥感信息,2017,32(6):85-89.LI C C,DU W B,MA X X,et al.SAR image segmentation based on improved MRF model[J].Remote Sensing Information,2017,32(6):85-89.(in Chinese)
[12]王婵.基于Dirichlet过程混合模型的话题识别与追踪[D].北京:北京邮电大学,2013.WANG C.Topic detection and tracking based on Dirichlet process mixture model[D].Beijing:Beijing University of Posts and Telecommunications,2013.(in Chinese)
[13]李天彩,王波,席耀一,等.基于分层狄利克雷过程模型的文本分割[J].数据采集与处理,2017,32(2):408-416.LI T C,WANG B,XI Y Y,et al.Text segmentation based on hierarchical Dirichlet processes[J].Journal of Data Acquisition&Processing,2017,32(2):408-416.(in Chinese)
[14]王开义,张水发,杨锋,等.基于分水岭和改进MRF的马铃薯丁粘连图像在线分割[J].农业机械学报,2013,44(9):187-192.WANG K Y,ZHANG S F,YANG F,et al.Online segmentation of clustering diced-potatoes using watershed and improved MRF algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2013,44(9):187-192.(in Chinese)
[15]冯云丛.基于信息融合的医学图像阈值分割及评价方法研究[D].长春:吉林大学,2017.FENG Y C.Study of medical image thresholding segmentation and evaluation methods based on information fusion[D].Changchun:Jilin University,2017.(in Chinese)
[16]庹谦.最大熵结合遗传算法的图像阈值分割算法研究[D].昆明:昆明理工大学,2016.TUO Q.Research on image threshold segmentation algorithm based on maximum entropy and genetic algorithm[D].Kunming:Kunming University of Science and Technology,2016.(in Chinese)
[17]刘建磊,隋青美,朱文兴.结合概率密度函数和主动轮廓模型的磁共振图像分割[J].光学精密工程,2014,22(12):3435-3443.LIU J L,SUI Q M,ZHU W X.MR image segmentation based on probability density function and active contour model[J].Optics and Precision Engineering,2014,22(12):3435-3443.(in Chinese)
[2]王娅.血液红细胞图像自适应标记分水岭分割算法[J].中国图象图形学报,2017,22(12):1779-1787.WANG Y.Adaptive marked watershed segmentation algorithm for red blood cell images[J].Journal of Image and Graphics,2017,22(12):1779-1787.(in Chinese)
[3]陈恺,陈芳,戴敏,等.基于萤火虫算法的二维熵多阈值快速图像分割[J].光学精密工程,2014,22(2):517-523.CHEN K,CHEN F,DAI M,et al.Fast image segmentation with multilevel threshold of two-dimensional entropy based on firefly algorithm[J].Optics and Precision Engineering,2014,22(2):517-523.(in Chinese)
[4]LI C M,XU C Y,GUI C F,et al.Distance regularized level set evolution and its application to image segmentation[J].IEEE Transactions on Image Processing,2010,19(12):3243-3254.
[5]SCAMAN M E,ECONOMIKOS L.Computer vision for automatic inspection of complex metal patterns on multichip modules(MCM-D)[J].IEEE Transactions on Components,Packaging,and Manufacturing Technology:Part B,1995,18(4):675-684.
[6]尹诗白,王一斌,邓箴.基于快速递推模糊2-划分熵图割的红外图像分割[J].光学精密工程,2016,24(3):668-680.YI S B,WANG Y B,DENG Z.Infrared image segmentation based on graph cut of fast recursive fuzzy 2-partition entropy[J].Optics and Precision Engineering,2016,24(3):668-680.(in Chinese)
[7]吴秋红,吴谨,朱磊,等.基于图论和FCM的图像分割算法[J].液晶与显示,2016,31(1):112-116.WU Q H,WU J,ZHU L,et al.Image segmentation algorithm based on graph theory and FCM[J].Chinese Journal of Liquid Crystals and Displays,2016,31(1):112-116.(in Chinese)
[8]LI Y,ZHU R,MI L,et al.Segmentation of white blood cell from acute lymphoblastic leukemia images using dual-threshold method[J].Computational and Mathematical Methods in Medicine,2016,2016:9514707.
[9]徐胜军,韩九强,刘光辉.基于马尔可夫随机场的图像分割方法综述[J].计算机应用研究,2013,30(9):2576-2582.XU S J,HAN J Q,LIU G H.Survey of image segmentation methods based on Markov random fields[J].Application Research of Computers,2013,30(9):2576-2582.(in Chinese)
[10]标本.基于马尔科夫随机场、模糊理论、D-S理论的医学图像融合分割方法及研究[D].昆明:昆明理工大学,2017.BIAO B.Segmentation method and research of medical image fusion based on Markov random field,fuzzy theory and D-S theory[D].Kunming:Kunming University of Science and Technology,2017.(in Chinese)
[11]李长春,都伟冰,马潇潇,等.改进马尔可夫模型的SAR图像分割[J].遥感信息,2017,32(6):85-89.LI C C,DU W B,MA X X,et al.SAR image segmentation based on improved MRF model[J].Remote Sensing Information,2017,32(6):85-89.(in Chinese)
[12]王婵.基于Dirichlet过程混合模型的话题识别与追踪[D].北京:北京邮电大学,2013.WANG C.Topic detection and tracking based on Dirichlet process mixture model[D].Beijing:Beijing University of Posts and Telecommunications,2013.(in Chinese)
[13]李天彩,王波,席耀一,等.基于分层狄利克雷过程模型的文本分割[J].数据采集与处理,2017,32(2):408-416.LI T C,WANG B,XI Y Y,et al.Text segmentation based on hierarchical Dirichlet processes[J].Journal of Data Acquisition&Processing,2017,32(2):408-416.(in Chinese)
[14]王开义,张水发,杨锋,等.基于分水岭和改进MRF的马铃薯丁粘连图像在线分割[J].农业机械学报,2013,44(9):187-192.WANG K Y,ZHANG S F,YANG F,et al.Online segmentation of clustering diced-potatoes using watershed and improved MRF algorithm[J].Transactions of the Chinese Society for Agricultural Machinery,2013,44(9):187-192.(in Chinese)
[15]冯云丛.基于信息融合的医学图像阈值分割及评价方法研究[D].长春:吉林大学,2017.FENG Y C.Study of medical image thresholding segmentation and evaluation methods based on information fusion[D].Changchun:Jilin University,2017.(in Chinese)
[16]庹谦.最大熵结合遗传算法的图像阈值分割算法研究[D].昆明:昆明理工大学,2016.TUO Q.Research on image threshold segmentation algorithm based on maximum entropy and genetic algorithm[D].Kunming:Kunming University of Science and Technology,2016.(in Chinese)
[17]刘建磊,隋青美,朱文兴.结合概率密度函数和主动轮廓模型的磁共振图像分割[J].光学精密工程,2014,22(12):3435-3443.LIU J L,SUI Q M,ZHU W X.MR image segmentation based on probability density function and active contour model[J].Optics and Precision Engineering,2014,22(12):3435-3443.(in Chinese)