斑马鱼视网膜细胞图像分析研究
|
摘要
斑马鱼视网膜细胞的计数与分类是检查细胞变异的重要依据,具有重要的生物学意义。先前的视网膜细胞的计数和分类以人工操作为主,由于工作量太大,因此,必须研究自动的方法来帮助研究人员完成这两项工作。本文在细胞图像分割、细胞计数、特征提取与选择、细胞分类这四个方面进行了研究。
在细胞图像的分割方面,本文采用了基于梯度流跟踪的分割方法。它包括以下三个步骤:梯度向量扩散、梯度流跟踪和自适应阈值分割。通过梯度向量扩散与梯度流跟踪,细胞图像被分割成很多个仅包含一个细胞和周围背景的小区域;然后使用自适应阈值法成功地从每一个小区域的背景中提取独立的细胞。该方法很好地解决了其他算法在粘连细胞图像分割过程中经常发生的较严重的过分割或欠分割问题。
在细胞图像分割的基础上,本文参照八邻域边界跟踪技术和图像标号算法,采用了基于边界跟踪的计数算法实现了细胞计数。
最后,本文研究了斑马鱼视网膜七类细胞的特征及分类规则,提取了细胞的彩色光密度特征和形态特征,并对特征的选择和分类器的设计进行了讨论和研究。选用最小距离分类器对斑马鱼视网膜细胞进行分类。
Counting and classification of zebrafish retinal cells are important gist in the inspection of cell mutation, have important biological significance. Previous counting and classification of zebrafish retinal cells are mainly based on manual operation. Because of heavy workload, automatic methods should be developed to finish above task. In this thesis, in the view of image analysis of zebrafish retinal cell, following issues are researched: image segmentation, cell counting,feature extraction and selection,and cell classification.
For image segmentation,gradient- flow-tracking based method is adopted, which is composed of three key steps: gradient vector diffusion,gradient flow tracking and adaptive thresholding. After gradient vector diffusion and gradient flow tracking, the cell image is separated into some small regions, each region containing one cell and its background. Local adaptive thresholding is performed for each small region, the single cell can be extracted from the background. Above method favorably overcomes the shortcoming of over-segmentation and under-segmentation by other algorithms for the segmentation of touching cells On the basis of above cell image segmentation, boundary tracking based algorithm is used for cell counting, which refers to image labeling algorithm and 8-connected boundary tracking.
Finally, cell features and classification rules are studied, color density features and morphological features of zebrafish retinal cells are extracted. Then the problems of feature selection and the design of classifier are studied. The least distance classifier is used to classify the zebrafish retinal cells.
在细胞图像的分割方面,本文采用了基于梯度流跟踪的分割方法。它包括以下三个步骤:梯度向量扩散、梯度流跟踪和自适应阈值分割。通过梯度向量扩散与梯度流跟踪,细胞图像被分割成很多个仅包含一个细胞和周围背景的小区域;然后使用自适应阈值法成功地从每一个小区域的背景中提取独立的细胞。该方法很好地解决了其他算法在粘连细胞图像分割过程中经常发生的较严重的过分割或欠分割问题。
在细胞图像分割的基础上,本文参照八邻域边界跟踪技术和图像标号算法,采用了基于边界跟踪的计数算法实现了细胞计数。
最后,本文研究了斑马鱼视网膜七类细胞的特征及分类规则,提取了细胞的彩色光密度特征和形态特征,并对特征的选择和分类器的设计进行了讨论和研究。选用最小距离分类器对斑马鱼视网膜细胞进行分类。
Counting and classification of zebrafish retinal cells are important gist in the inspection of cell mutation, have important biological significance. Previous counting and classification of zebrafish retinal cells are mainly based on manual operation. Because of heavy workload, automatic methods should be developed to finish above task. In this thesis, in the view of image analysis of zebrafish retinal cell, following issues are researched: image segmentation, cell counting,feature extraction and selection,and cell classification.
For image segmentation,gradient- flow-tracking based method is adopted, which is composed of three key steps: gradient vector diffusion,gradient flow tracking and adaptive thresholding. After gradient vector diffusion and gradient flow tracking, the cell image is separated into some small regions, each region containing one cell and its background. Local adaptive thresholding is performed for each small region, the single cell can be extracted from the background. Above method favorably overcomes the shortcoming of over-segmentation and under-segmentation by other algorithms for the segmentation of touching cells On the basis of above cell image segmentation, boundary tracking based algorithm is used for cell counting, which refers to image labeling algorithm and 8-connected boundary tracking.
Finally, cell features and classification rules are studied, color density features and morphological features of zebrafish retinal cells are extracted. Then the problems of feature selection and the design of classifier are studied. The least distance classifier is used to classify the zebrafish retinal cells.
引文
[1] K.D.Poss, L.G.Wilson & M.T.Keating. Heart Regeneration in Zebrafish. Science. 2002, 298: 2188-2190.
[2] I.C.Scott & D.Y.R. Stainier.Fishing Out a New Heart. Science. 2002, 298: 2141-2142
[3] Langenau DM, Traver D, Ferrando AA, Kutok JL, Aster JC, Kanki JP, LinS, Prochownik E, Trede NS, Zon LI, Look AT. Myc-induced T-cell leukemia in transgenic zebrafish. Science. 2003, 299: 887-890
[4]张之南.血液病诊断及疗效标准.北京:科学出版社,1998
[5]柯行斌,王汝传.白细胞图像分割的研究与实现.南京邮电学院学报,2003, 23(3): 53-56
[6]洪沁,何振亚,吴承武,王太君.胃癌脱落细胞图像的一种新的识别方法.中国生物医学工程学报,1993,12(1): 56-61
[7] Thomas Schindewlof, Wilhelm Stolz, Rene Albert, Wolfgang Abmayr, Harry Harms. "Classification of Melanocytic Lesions with Color and Texture Analysis Using Digital Image processing". A nal.Quantum Cyto.l Vol.15, pp.1-11, 1993
[8]容观澳.计算机图像处理,北京:清华大学出版社,2000
[9]阮秋琦.数字图像处理学,北京:电子工业出版社,2001
[10]龚声蓉,刘纯平等.数字图像处理与分析,北京:清华大学出版社, 2000
[11] Milan Sonka, Vaclav Hlavac, Roger Boyle.图像处理、分析与机器视觉.艾海舟,武勃译.北京:人民邮电出版社,2003
[12]王润生.图像理解,长沙:国防科技大学出版,1995
[13]章毓晋.图像分割评价技术分类和比较,中国图形图像学报,1996,1(2): 151-158
[14]章毓晋.图象分割.北京科学出版社, 2001-02
[15] Yanowitz S.D.Bruckstein A.M.. A New Method for Image Segmentation. Computer Vision,Graphics,and Image Processing,1989,46(1): 82-95
[16] Rubeto Di C, Dempster A, Khan S, Jarra B. Segmentation of blood images using morphological operators [A]. Proceedings.15th International Conference on Pattern Recognition [C]. 2000, 3: 397-400.
[17]戴青云,余英林.数学形态学在图像处理中的应用进展.控制理论与应用, 2001,18(4): 478-482
[18] Thiran Jean-Philippe et al. Automatic recognition of cancerous cells using mathematical morphology. In: Proc of SPIE, 1994: 392-401
[19]杨晓敏,罗立民,韦钰.人体白细胞自动分类方法与实现系统.计算机学报,1994,17(2): 130-136
[20]陆建峰,杨静宇,唐振民等.重叠细胞图像分离算法的设计.计算机研究与发展,2000,37(2): 228-232
[21]马东,曹培杰,潘凯丽,程敬之.分割重叠细胞核的方法及比较研究.北京生物医学工程,1999,18(3): 142-147
[22] Xu C, Prince J :Snakes, shapes, and gradient vector flow. IEEE Trans Image Processing 1998, 7: 359-369
[23] Davatzikos C, Prince J, Bryan R: Image Registration Based on Boundary Mapping. IEEE Trans Med Imaging 1996, 15: 112-115
[24] Bajcsy R, Kovacic S. Multiresolution elastic matching. Computer Vision, Graphics and Image Processing 1989, 46: 1-21
[25] A.K.Join.Fundamentals of Digital Image Processing. Englewood Clis,NJ:Prentice-Hall,1989
[26] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man and Cybenretic, 1979, SMC-9(1): 62-66
[27]周洪堂.细胞自动计数中的一种图像标号算法.生物医学工程杂志,1992,9 (3): 307- 310
[28]刘俊丽,薛河儒.基于图像处理的牛奶体细胞计数方法的研究.内蒙古农业大学学报,2006,27(4): 140-144
[29]周孝宽.实用微机图像处理.北京:北京航空航天大学出版社,1994
[30]张勇.彩色白细胞显微图像分析与识别.西安交通大学博士学位论文.1999
[31]杨晓敏,罗立民,韦钮.血液白细胞计算机分类中的特征提取研究.应用科学学报, 1994,12(2): 120-126
[32] Chen CC, Daponte JS, Fox MD. Fractal Feature Analysis and Classification in Medical Image. IEEE Trans.On Medical Imaging,1989,8(2): 133-142
[33] K.R.Castleman, T.P.Riopka and Q.Wu. FISH Image Analysis. IEEE Engineering in Medicine and Biology,1996: 67-75
[34]边肇祺,张学工.模式识别.北京:清华大学出版社,2001
[35] Anil K. Jain,Robert P.W. Duin, JianChang Mao. Statistical Pattern Recognition:A Review.IEEE Trans.on PAMI-22,No.l, Jan 2000: 4-37
[36] S.F.Bikhet, A.M.Darwish. Segmentation and Classification of White Blood Cell. IEEE International Conference on Acoustics,Speech,and Signal Processing, 2000, Vol.4: 226-259
[37] Domingos P,Pazzani M. On the Optimality of the Simple Bayesian Classifier under Zero-one Loss[J]. Machine Learning,1997,29(2/3): 103-130
[38] Vapnik V. The nature of statistical learning theory. New York:Springer-Verlag, 1999
[39]张学工译.统计学习理论的本质.北京:清华大学出版社,2000
[40]朱建华,刘政凯,俞能海.一种多光谱遥感图像的自适应最小距离分类方法.中国图像图形学报,2000,5(1): 21-24
[41] Li G, Liu T, Nie J et al. Detection of Blob Objects in Microscopic Zebrafish Images Based on Gradient Vector Diffusion. Cytometry Part A, 2007, 71A : 835-845
[2] I.C.Scott & D.Y.R. Stainier.Fishing Out a New Heart. Science. 2002, 298: 2141-2142
[3] Langenau DM, Traver D, Ferrando AA, Kutok JL, Aster JC, Kanki JP, LinS, Prochownik E, Trede NS, Zon LI, Look AT. Myc-induced T-cell leukemia in transgenic zebrafish. Science. 2003, 299: 887-890
[4]张之南.血液病诊断及疗效标准.北京:科学出版社,1998
[5]柯行斌,王汝传.白细胞图像分割的研究与实现.南京邮电学院学报,2003, 23(3): 53-56
[6]洪沁,何振亚,吴承武,王太君.胃癌脱落细胞图像的一种新的识别方法.中国生物医学工程学报,1993,12(1): 56-61
[7] Thomas Schindewlof, Wilhelm Stolz, Rene Albert, Wolfgang Abmayr, Harry Harms. "Classification of Melanocytic Lesions with Color and Texture Analysis Using Digital Image processing". A nal.Quantum Cyto.l Vol.15, pp.1-11, 1993
[8]容观澳.计算机图像处理,北京:清华大学出版社,2000
[9]阮秋琦.数字图像处理学,北京:电子工业出版社,2001
[10]龚声蓉,刘纯平等.数字图像处理与分析,北京:清华大学出版社, 2000
[11] Milan Sonka, Vaclav Hlavac, Roger Boyle.图像处理、分析与机器视觉.艾海舟,武勃译.北京:人民邮电出版社,2003
[12]王润生.图像理解,长沙:国防科技大学出版,1995
[13]章毓晋.图像分割评价技术分类和比较,中国图形图像学报,1996,1(2): 151-158
[14]章毓晋.图象分割.北京科学出版社, 2001-02
[15] Yanowitz S.D.Bruckstein A.M.. A New Method for Image Segmentation. Computer Vision,Graphics,and Image Processing,1989,46(1): 82-95
[16] Rubeto Di C, Dempster A, Khan S, Jarra B. Segmentation of blood images using morphological operators [A]. Proceedings.15th International Conference on Pattern Recognition [C]. 2000, 3: 397-400.
[17]戴青云,余英林.数学形态学在图像处理中的应用进展.控制理论与应用, 2001,18(4): 478-482
[18] Thiran Jean-Philippe et al. Automatic recognition of cancerous cells using mathematical morphology. In: Proc of SPIE, 1994: 392-401
[19]杨晓敏,罗立民,韦钰.人体白细胞自动分类方法与实现系统.计算机学报,1994,17(2): 130-136
[20]陆建峰,杨静宇,唐振民等.重叠细胞图像分离算法的设计.计算机研究与发展,2000,37(2): 228-232
[21]马东,曹培杰,潘凯丽,程敬之.分割重叠细胞核的方法及比较研究.北京生物医学工程,1999,18(3): 142-147
[22] Xu C, Prince J :Snakes, shapes, and gradient vector flow. IEEE Trans Image Processing 1998, 7: 359-369
[23] Davatzikos C, Prince J, Bryan R: Image Registration Based on Boundary Mapping. IEEE Trans Med Imaging 1996, 15: 112-115
[24] Bajcsy R, Kovacic S. Multiresolution elastic matching. Computer Vision, Graphics and Image Processing 1989, 46: 1-21
[25] A.K.Join.Fundamentals of Digital Image Processing. Englewood Clis,NJ:Prentice-Hall,1989
[26] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man and Cybenretic, 1979, SMC-9(1): 62-66
[27]周洪堂.细胞自动计数中的一种图像标号算法.生物医学工程杂志,1992,9 (3): 307- 310
[28]刘俊丽,薛河儒.基于图像处理的牛奶体细胞计数方法的研究.内蒙古农业大学学报,2006,27(4): 140-144
[29]周孝宽.实用微机图像处理.北京:北京航空航天大学出版社,1994
[30]张勇.彩色白细胞显微图像分析与识别.西安交通大学博士学位论文.1999
[31]杨晓敏,罗立民,韦钮.血液白细胞计算机分类中的特征提取研究.应用科学学报, 1994,12(2): 120-126
[32] Chen CC, Daponte JS, Fox MD. Fractal Feature Analysis and Classification in Medical Image. IEEE Trans.On Medical Imaging,1989,8(2): 133-142
[33] K.R.Castleman, T.P.Riopka and Q.Wu. FISH Image Analysis. IEEE Engineering in Medicine and Biology,1996: 67-75
[34]边肇祺,张学工.模式识别.北京:清华大学出版社,2001
[35] Anil K. Jain,Robert P.W. Duin, JianChang Mao. Statistical Pattern Recognition:A Review.IEEE Trans.on PAMI-22,No.l, Jan 2000: 4-37
[36] S.F.Bikhet, A.M.Darwish. Segmentation and Classification of White Blood Cell. IEEE International Conference on Acoustics,Speech,and Signal Processing, 2000, Vol.4: 226-259
[37] Domingos P,Pazzani M. On the Optimality of the Simple Bayesian Classifier under Zero-one Loss[J]. Machine Learning,1997,29(2/3): 103-130
[38] Vapnik V. The nature of statistical learning theory. New York:Springer-Verlag, 1999
[39]张学工译.统计学习理论的本质.北京:清华大学出版社,2000
[40]朱建华,刘政凯,俞能海.一种多光谱遥感图像的自适应最小距离分类方法.中国图像图形学报,2000,5(1): 21-24
[41] Li G, Liu T, Nie J et al. Detection of Blob Objects in Microscopic Zebrafish Images Based on Gradient Vector Diffusion. Cytometry Part A, 2007, 71A : 835-845