视神经纤维自动识别与分析关键技术研究
|
摘要
目前,在有关人和动物的神经科学研究中,神经纤维形态分析被广泛应用于正常或病理状态下的神经组织研究或诊断中。神经纤维及轴突的形态分析,对于对正确理解神经发育、损伤及退化程度,掌握神经纤维形态特征规律及分布具有重要意义。
神经纤维形态分析能否客观反映神经科学现象,关键取决于兴趣区域(如轴突或髓鞘)的选择提取是否科学、准确。在神经纤维形态分析研究之初,这项工作依赖手动方式提取兴趣区域,即由有经验的人员从显微图像中勾画出兴趣区域的轮廓及边界。随着研究的深入,手动方式的弊端明显体现:第一,手动方式费时费力,分割结果的优劣很大程度上取决于操作者的经验知识,客观性和可重复性较差;第二,对于数量庞大的神经纤维,少量采样可以缓解科研人员的繁重劳动,但是获取数据的科学性和可靠性却受影响。
因而,神经纤维形态的自动识别与分析已成为图像处理和神经科学领域科研工作者共同关注的研究热点。从上世纪80年代,相关的神经纤维识别算法和商业化软件不断被推出和改进,使神经纤维的识别效果不断提高。
精确的神经纤维形态识别和分析是建立在准确的图像分割基础之上。由于神经系统组织成分复杂多变,给神经纤维识别带来诸多困难,例如细小神经纤维的识别、复杂背景下特征的提取、不规则神经纤维的提取等。这些困难在神经纤维分布密集的神经(如视神经)中表现尤为突出。
本课题研究的首要目标是开发出适合视神经纤维分割的有效方法。在纤维识别中,我们充分利用神经纤维的解剖结构特点,先获取纤维髓鞘的中心线,即粗略锁定神经纤维;在此基础上通过中心线的内移、外移及曲线演化,进而获得轴突和髓鞘的精细轮廓。这一技术思想也是本研究的创新主体。
在上文所述创新思想的驱动之下,本研究采用改进后的Watersnake进行神经纤维分割。在实验中分两步进行:第一步,由Watershed生成连续且拓扑保持的神经纤维的初始骨架,并剔除假性纤维和边界位置的不完整纤维;第二步,由Snake将初始骨架引导到轴突和髓鞘的精细位置上。本算法提取的神经纤维保持了位置的准确和外形的光滑。
在算法的性能评价实验中,随机抽取纤维图像,将自动分割结果与采用PHOTOSHOP软件手动分割结果进行对照分析。在纤维识别率分析中,自动识别正确率95.7%,假阳性率3.3%。在轴突直径频数分布对照分析中,自动识别与手动识别方式下的轴突直径频数分布直方图相吻合,波峰位置未有偏移。
从目前的实验结果来看,本研究的识别率稍高于Romero等人的研究(94.8%),而假阳性率方面不及前者(1.0%)。研究中发现,假阳性纤维主要来源于拥挤纤维簇之间形成的闭合区域。在Romero等人的研究中,其研究对象是坐骨神经纤维,而坐骨神经纤维的分布比视神经纤维的分布稀疏,这也许是其假阳性率低于本研究的原因之一。
本研究中的图像来源于分辨率较高的透射电镜底片,Watersnake技术对分辨率低的图像(如光镜图像)是否同样适用,在后期研究中我们将继续探索和改进,拓宽该技术的应用范围。
Presently, in the neurological research related to human and animal, histological examination of nerve fibers is often complemented by morphometric analysis in both clinical and research settings. Nerve morphometric analysis could provide researcher some valuable parameters.
The accurate isolation of the ROI (Region of Interesting) is the key to the nerve morphometric studies. In the early investigation of nerve morphometry, the ROI is achieved manually i. e. the experienced neuroscientists draw the outline of the ROI in the microscopy image. Gradually, the disadvantage of manual morphometry is noticeable. Manual nerve morphometry is extremely tedious, labour intensive and time-consuming, and segmentation of ROI depend on the subjective decision and experience of operator. To overcome this there have been efforts to devise representative sampling schemes to reduce the amount of data analysis required. However, the accuracy of results is dubious.
As a result, automatic identification of nerve fibers has draws much attention from image processing and neuroscience communities. Since the eighties of the last century, algorithms and commercial softwares related to nerve fibers detection were reported and promoted to improve the efficiency of fiber detection.
Nevertheless, precise segmentation is the basis of the fiber analysis. In the process of fiber detection, the failure always results from the diversity of nerve fiber, for instance, lack of prominent features and irregular in shape. In the nerve with dense population, for example the optic nerve, the detection becomes more difficult.
At present investigation, an original scheme for automatic segmentation of optic nerve fiber is proposed. Most importantly, the anatomical structure of fiber is taken into account. First, the center line of myelin sheath is picked up; therefore, the location of fiber is determined. Next, the contour is moved in, moved out, and finally, the fine contour is achieved by evolution of contour.
Motivated by the above original scheme, we introduced watersnake to segment nerve fibers. Initially, watershed extracts continuous and topological reserving sketch of the nerve fibers and the false fibers are get rid of. In the following step, the initial contours are steered to be good fit to the fine location of axon and myelin sheath. The final contours are smooth and accurate.
The proposed method has been tested using nerve image by random sampling; the results from automation were compared with those of manual method with the help of PHOTOSHOP software. The overall detection rate and false alarm rate were found to be 95. 7% and 3. 3%, respectively. The axon diameter frequency distribution was comparable to that done manually, and the peak has no offset.
The current results indicate that the detection rate is slightly superior to the research of Romero (94.8%) , but the false alarm rate is inferior to that (1.0%) . It was found that the false fibers primarily originate from the close region among the crowded nerve fibers. Probably the sciatic nerve fibers adopted in Romero's research are sparse, which result in the false alarm rate is lower than ours.
In our investigation, we adopted electron microscopy photographs with high resolution. In the following research, we would continue our investigation and made the technique of watersnake to be generally applied, so that it could be adaptable to the images with low resolution (light microscopy).
神经纤维形态分析能否客观反映神经科学现象,关键取决于兴趣区域(如轴突或髓鞘)的选择提取是否科学、准确。在神经纤维形态分析研究之初,这项工作依赖手动方式提取兴趣区域,即由有经验的人员从显微图像中勾画出兴趣区域的轮廓及边界。随着研究的深入,手动方式的弊端明显体现:第一,手动方式费时费力,分割结果的优劣很大程度上取决于操作者的经验知识,客观性和可重复性较差;第二,对于数量庞大的神经纤维,少量采样可以缓解科研人员的繁重劳动,但是获取数据的科学性和可靠性却受影响。
因而,神经纤维形态的自动识别与分析已成为图像处理和神经科学领域科研工作者共同关注的研究热点。从上世纪80年代,相关的神经纤维识别算法和商业化软件不断被推出和改进,使神经纤维的识别效果不断提高。
精确的神经纤维形态识别和分析是建立在准确的图像分割基础之上。由于神经系统组织成分复杂多变,给神经纤维识别带来诸多困难,例如细小神经纤维的识别、复杂背景下特征的提取、不规则神经纤维的提取等。这些困难在神经纤维分布密集的神经(如视神经)中表现尤为突出。
本课题研究的首要目标是开发出适合视神经纤维分割的有效方法。在纤维识别中,我们充分利用神经纤维的解剖结构特点,先获取纤维髓鞘的中心线,即粗略锁定神经纤维;在此基础上通过中心线的内移、外移及曲线演化,进而获得轴突和髓鞘的精细轮廓。这一技术思想也是本研究的创新主体。
在上文所述创新思想的驱动之下,本研究采用改进后的Watersnake进行神经纤维分割。在实验中分两步进行:第一步,由Watershed生成连续且拓扑保持的神经纤维的初始骨架,并剔除假性纤维和边界位置的不完整纤维;第二步,由Snake将初始骨架引导到轴突和髓鞘的精细位置上。本算法提取的神经纤维保持了位置的准确和外形的光滑。
在算法的性能评价实验中,随机抽取纤维图像,将自动分割结果与采用PHOTOSHOP软件手动分割结果进行对照分析。在纤维识别率分析中,自动识别正确率95.7%,假阳性率3.3%。在轴突直径频数分布对照分析中,自动识别与手动识别方式下的轴突直径频数分布直方图相吻合,波峰位置未有偏移。
从目前的实验结果来看,本研究的识别率稍高于Romero等人的研究(94.8%),而假阳性率方面不及前者(1.0%)。研究中发现,假阳性纤维主要来源于拥挤纤维簇之间形成的闭合区域。在Romero等人的研究中,其研究对象是坐骨神经纤维,而坐骨神经纤维的分布比视神经纤维的分布稀疏,这也许是其假阳性率低于本研究的原因之一。
本研究中的图像来源于分辨率较高的透射电镜底片,Watersnake技术对分辨率低的图像(如光镜图像)是否同样适用,在后期研究中我们将继续探索和改进,拓宽该技术的应用范围。
Presently, in the neurological research related to human and animal, histological examination of nerve fibers is often complemented by morphometric analysis in both clinical and research settings. Nerve morphometric analysis could provide researcher some valuable parameters.
The accurate isolation of the ROI (Region of Interesting) is the key to the nerve morphometric studies. In the early investigation of nerve morphometry, the ROI is achieved manually i. e. the experienced neuroscientists draw the outline of the ROI in the microscopy image. Gradually, the disadvantage of manual morphometry is noticeable. Manual nerve morphometry is extremely tedious, labour intensive and time-consuming, and segmentation of ROI depend on the subjective decision and experience of operator. To overcome this there have been efforts to devise representative sampling schemes to reduce the amount of data analysis required. However, the accuracy of results is dubious.
As a result, automatic identification of nerve fibers has draws much attention from image processing and neuroscience communities. Since the eighties of the last century, algorithms and commercial softwares related to nerve fibers detection were reported and promoted to improve the efficiency of fiber detection.
Nevertheless, precise segmentation is the basis of the fiber analysis. In the process of fiber detection, the failure always results from the diversity of nerve fiber, for instance, lack of prominent features and irregular in shape. In the nerve with dense population, for example the optic nerve, the detection becomes more difficult.
At present investigation, an original scheme for automatic segmentation of optic nerve fiber is proposed. Most importantly, the anatomical structure of fiber is taken into account. First, the center line of myelin sheath is picked up; therefore, the location of fiber is determined. Next, the contour is moved in, moved out, and finally, the fine contour is achieved by evolution of contour.
Motivated by the above original scheme, we introduced watersnake to segment nerve fibers. Initially, watershed extracts continuous and topological reserving sketch of the nerve fibers and the false fibers are get rid of. In the following step, the initial contours are steered to be good fit to the fine location of axon and myelin sheath. The final contours are smooth and accurate.
The proposed method has been tested using nerve image by random sampling; the results from automation were compared with those of manual method with the help of PHOTOSHOP software. The overall detection rate and false alarm rate were found to be 95. 7% and 3. 3%, respectively. The axon diameter frequency distribution was comparable to that done manually, and the peak has no offset.
The current results indicate that the detection rate is slightly superior to the research of Romero (94.8%) , but the false alarm rate is inferior to that (1.0%) . It was found that the false fibers primarily originate from the close region among the crowded nerve fibers. Probably the sciatic nerve fibers adopted in Romero's research are sparse, which result in the false alarm rate is lower than ours.
In our investigation, we adopted electron microscopy photographs with high resolution. In the following research, we would continue our investigation and made the technique of watersnake to be generally applied, so that it could be adaptable to the images with low resolution (light microscopy).
引文
[1]杨晓敏,罗立民,韦钰.人体白细胞自动分类方法与系统实现[J].计算机学报,1994,17(2):130-36.
[2]Pascal B,Brian L.Unsupervised cell nucleus segmentation with active contours.Signal Processing.1998,71(2):203-213
[3]Jiang TZ,Yang FG.An evolutionary tabu search for cell image segmentation[J].IEEE Transactions on Systems,Man,and Cybernetics,2002,32(5):675-678.
[4]Theerapattanakrul J,Plodpai J,Pintavirooj J.An efficient method for segmentation step of automated white blood cell classifications[J].IEEE Trans Pattern Analysis and Machine Intelligence,2004,1:21-24.
[5]Vivek S,Yongchang J,Dan CM.A parallel algorithmfor automatic particle identification in electron micrographs[J].LNCS,2005,3402:354-367.
[6]张石,王军辉,董建威,齐晓龙.医学显微图像分割方法研究进展[J].中国生物医学工程学报,2007,26(4):623-629.
[7]Brown HG,Martin JR,Asbury AK.Painful diabetic neuropathy.A morphometric study[J].Arch Neurol,1976,33:164-171.
[8]Pollock M,Nukada H,Allpress S,et al.Peripheral nerve morphometry in stroke patients[J].J Neurol Sci,1984,65:341-352.
[9]Thomas PK,Fraher JP,O'Leary D,et al.Relative growth and maturation of axon size and myelin thickness in the tibial nerve of the rat.Ⅱ.Effect of streptozotocin-induced diabetes[J].Acta Neuropathol,1990,79:375-386.
[10]杨柳,李美玉.正常人眼视神经内神经纤维分布[J].眼科研究,1998,16(3):187-189.
[11]Fressinaud C,Vigneron I,Letournel F,et al.Cytoskeleton abnormalities in axonopathies of unknown aetiology:correlations with morphometry[J].Journal of the Neurological Sciences,2002,196:53-61.
[12]Gu XZ,Zhang ZP,Qi L,et al.Morphometry of Axons in Optic Nerves of Siamese's Twins[J].Eye Science,2002,18(3):169-172.
[13]Walsh C.Age-related fiber order in the ferret's optic nerve and optic chiasm[J].J.Neurosci,1986,6:1635-1642.
[14] Wakakuwa K, Watanabe M, Sugimoto T,et al. An electron microscopic analysis of the optic nerve of the eastern chipmunk (Tamias sibiricus asiaticus): Total fiber count and retinotopic organisation [J]. Vis. Res, 1987,27: 1891-1901.
[15] Cepurnaa WO, Kaytonb RJ, Johnsona EC, et al. Age related optic nerve axonal loss in adult Brown Norway rats [J]. Experimental Eye Research, 2005, 80: 877-884.
[16] Williams RW, Chalupa LM. An analysis of axon caliber within the optic nerve of the cat: evidence of size groupings and regional organization [J]. The journal of Neuroscience, 1983,3(8): 1554-1564.
[17] Saito HA. Morphology of physiologically identified X-, Y-, and W-type retinal ganglion cells of the cat [J]. J. Comp. Neurol, 1983, 221:279-288.
[18] Stone J, Campion JE. Estimate of the number of myelinated axons in the cat's optic nerve [J]. J. Comp. Neurol, 1978,180:799-806.
[19] Jonas JB, Mueller-Bergh JA,Schloetzer-Schrehardt UM, et al. Histomorphometry of the human optic nerve [J]. Invest Ophthalmol Vis Sci, 1990, 31(4): 736-744.
[20] Jonas JB, Schmidt AM, Muller-Bergh JA, et al. Human optic nerve fiber count and optic disc size [J]. Invest Ophthalmol Vis Sci, 1992, 33: 2012-2018.
[21] Mayhew TM, Sharma AK. Sampling schemes for estimating nerve fibre size . I. Methods for nerve trunks of mixed fascicularity [J]. J Anat, 1984a, 139:59-66.
[22] Mayhew TM, Sharma AK. Sampling schemes for estimating nerve fibre size. II. Methods for unifascicular nerve trunks [J]. J Anat 1984b, 139: 59-66.
[23] Rainer L, Dieter M, Christine Ernzerhofa. Automated and representative fascicle selection for computer-assisted morphometry of myelinated nerve fibers in peripheral nerves [J]. Computers in Biology and Medicine, 2002, 32: 1-11.
[24] Canpolat Leyla, Kiikner A, Canpolat I, et al. Ultrastructural and Morphometric Analysis of Peripheral Nerve Regeneration Within Silicone Tubes [J]. Tr. J. of Medical Sciences. 1999: 29:203-209.
[25] Cull G, Sci BA, Cioffi GA, et al. Estimating Normal Optic Nerve Axon Numbers in Non-Human [J]. Journal of Glaucoma 2003, 12:301-306.
[26] Karim S, Clark RA, Vadims P, et al. Demonstration of Systematic Variation in Human Intraorbital Optic Nerve Size by Quantitative Magnetic Resonance Imaging and Histology [J]. Investigative Ophthalmology & Visual Science, 2004, 45(4): 1047-1051.
[27] Demir N, Akkoyunlu G, Yargicoglu P, et al. Fiber Structure of Optic Nerve in Cadmium-Exposed Diabetic Rats: An UltraStructural Study [J]. Intern. J. Neuroscience, 2003, 113:323-337.
[28] Weyn B, Remoortere MV, Nuydens R. A multiparametric assay for quantitative nerve regeneration evaluation [J]. Journal of Microscopy, 2005, 219(2): 95-101.
[29] Jonas JB, Muller-Bergh JA, Schlorzer-Schrehardr UM, et al. Histomorphometry of the Human Optic Nerve [J]. Investigative Ophthalmology & Visual Science, 1990, 31(4):736-744.
[30] Mathews MA. An electron microscopic study of the relationship between axon diameter and the initiation of myelin production in the peripheral nervous system [J]. AnatRec, 1968, 161:337-352.
[31] Williams RW, Bastiani MJ, Chalupa L. Loss of axons in the cat optic nerve following fetal unilateral enucleation: an electron microscopic analysis [J]. The Journal of Neuroscienc, 1983,3(1): 133-144.
[32] Cepurnaa WO, Kaytonb RJ, Johnson EC, et al. Age related optic nerve axonal loss in adult Brown Norway rats [J]. Experimental Eye Research, 2005, 80: 877-884.
[33] Drenhaus U, Thomas K, Rager G. The course of later generated axons in the developing optic nerve of the chick embryo: A morphometric electron microscopic study [J]. Developmental Brain Research, 2000, 121: 35-53.
[34] Gonzalez RC, Woods RE. Digital Image Processing (3rd Edition) [M]. New York: Addison Wesley, 1992:136-141.
[35] Sonka M, Hlavac V, Boyle R. Image Processing, Analysis, and Machine Vision (2nd Edition) [M]. 北京：人民邮电出版社,2002：232-235．
[36] 章毓晋．图像分割[M]．北京：科学技术出版社,2006．
[37] Thomas W, Jens S, Dietrich ME, et al., Robust automaticcoregistration, segmentation, and classification of cell nucleiin multimodal cytopathological microscopic images [J].Computerized Medical Imaging and Graphics, 2004, 28(1): 87-98.
[38] Nattkemper TW, Wersing H, Schubert W, et al. A neural network architecture for automatic segmentation of fluorescence micrographs [J]. Neurocomputing, 2002, 48(1-4):357-367.
[39] Sanchez RM, Dunkelberger GR, Quigley HA. The number and diameter distribution of axons in the monkey optic nerve [J]. Invest Ophthalmol Vis Sci., 1986, 27:1342-1350.
[40] Mezin P, Tenaud C, Bosson JL, Stoebner P. Morphometric analysis of the peripheral nerve: advantages of the semi-automated interactive method [J]. J Neurosci Methods,1994,51:163-169.
[41]Malbouisson AMB,Ghabriel MN,Allt G.Axonal microtubules:a computer-linked quantitative analysis[J].Anat Embryol,1985,171:339-344.
[42]Auer RN.Automated nerve fibre size and myelin sheath measurement using microcomputer-based digital image analysis:theory,method and results[J].J Neurosci Methods,1994,51:229-238.
[43]Wang JF,Schr(o|¨)der JM.Comparative morphometric evaluation of peripheral nerves and muscle fibers in myotonic dystrophy[J].Acta Neuropathol,2000,99:39-47.
[44]Campadelli P,Gangai C,Pasquale F.Automated morphometric analysis in peripheral neuropathies,Comput.Biol.Med,1999,29:147-155.
[45]Urso-Baiarda F,Grobbelaar AO.Practical nerve morphometry[J].Journal of Neuroscience Methods,2006,156(1-2):333-341.
[46]Brenner JF,Zahniser D J,Ziegelmiller DW,Adelman LS,et.al.Automated system for the analysis of muscle and nerve biopsies.Applied Optics,1987,26(16):3398-3407.
[47]Girish V,Vijayalakshmi A.Affordable image analysis using NIH Image/Image [J].J Indian J Cancer 2004,41:47-52.
[48]Vita G,Santoro M,Trombetta G,Leonardi L,Messina C.A computer-assisted automatic method for myelinated nerve fiber morphometry[J].Acta Neurol Scand.,1992,85:18-22.
[49]Silva APD,Jordao CER,Fazan VPS.Peripheral nerve morphometry:Comparison between manual and semi-automated methods in the analysis of a small nerve[J].Journal of Neuroscience Methods,2007,159(1):153-157.
[50]Klemencic A,Kovacic S.Automated Segmentation of Muscle Fiber Images Using Active Contour Models[J].Cytometry,1998,32:317-326.
[51]Campadelli P,Gangai C,Pasquale F.Automated morphometric analysis in peripheral neuropathies[J].Comp Biol Med.,1999,29:147-156.
[52]Fok YL,Chan JCK,Chin RT.Automated Analysis of Nerve-Cell Images Automated Analysis of Nerve-Cell Images[J].IEEE Transactions on medical imaging,1996,15(3):353-368.
[53]Romero E,Cuisenaire O.Automatic morphometry of nerve histological sections [J].Journal of Neuroscience Methods,2000,97:111-122.
[54]朗斯塔夫.神经科学(中译本)[M].北京:科学出版社,2006,10-12.
[55]韩济生.神经科学原理(第二版,上册)[M].北京:北京医科大学出版社,1999,141-150.
[56]Drenhaus U,Gunten AV,Rager G.Classes of Axons and Their Distribution in the Optic Nerve of the Tree Shrew(Tupaia belangeri)[J].The anatomical record.1997,249:103-116.
[57]Johnson PT,Geller SF,Reese BE.Distribution,size and number of axons in the optic pathway of ground squirrels[J].Exp Brain Res.1998,118:93-104.
[58]Brooks DE,Strubbe DT.Histomorphometry of the Optic Nerves of Normal Dogs and Dogs with Hereditary Glaucoma[J].Expl Eye Res.,1995,60:71-89.
[59]Cull G,Sci BA.Estimating Normal Optic Nerve Axon Numbers in Non-Human [J].Journal of Glaucoma,2003,12:301-306.
[60]Cepurnaa WO,Kaytonb RJ,Elaine C,et al.Age related optic nerve axonal loss in adult Brown Norway rats[J].Experimental Eye Research.,2005,80:877-884.
[61]Williams PL,Wendell-Smith CP.The Use of Fixed and Stained Sections in Quantitative Studies of Peripheral Nerve[J].Quarterly Journal of Microscopical Science,1960,101(1):43-54.
[62]Vilai C,Phinidda Cha-oumphol DVM,MSc,Athitaya Kaewsema BSc,et al.Morphometric Data of Normal Sural Nerve in Thai Adults[J].J Med Assoc Thai,2006,89(5):670-674.
[63]刘印锋,葛华勇,王保华.医学显微图像的数字化技术[J].中国医疗器械信息,2005,11(3):24-27.
[64]彭宣戈,欧阳春娟,欧阳迎春,朱兵.多方向一维小波变换的显微图像去噪[J].计算机工程,2007,43(12):31-35.
[65]Caselles V,Lisani JL,Morel JM,et al.Shape Preserving Local Histogram Modification[J].IEEE transactions on image processing,1999,8(2):220-229
[66]Chan FHY,Lam FK,Zhu H.Adaptive thresholding by variational method[J].IEEE Trans.Image Process.1998,7(3):468-473.
[67]Sahoo PK,Arora G.Image thresholding using two dimensional Tsallis-Havrda-Charvart entropy[J].Pattern Recogn.Lett.2006,27:520-528.
[68]Otsu N.A threshold selection method from gray level histograms[J].IEEE Trans Syst Man Cyber.,1979,9(1):62-66.
[69]Abutaleb AS.Automatic thresholding of gray-level pictures using two-dimensional entropy[J].Comput.Vis.Graphics Image Process.1989,47:22-32.
[70]Synder W,Bilbro G.Optimal thresholding:a new approach[J].Pattern Recog. Lett.1990,11:803-810.
[71]Liu D,Jiang Z,Feng H.A novel fuzzy classification entropy approach to image thresholding[J].Pattern Recognition Letters,2006,27:1968-1975.
[72]Sezgin M,Sankur B.Survey over image thresholding techniques and quantitative performance evaluation[J].J.Electronic Imaging,2004,13(1):146-165.
[73]Zahara E,Fan SS,Tsai D.Optimal multi-thresholding using a hybrid optimisation approach[J].Pattern Recogn.Lett.2005,26(8):1082-1095.
[74]章毓晋.图像分割[M].北京:科学技术出版社,2006,9-14.
[75]Gonzalez RC,Woods RE.Digital Image Processing(3rd Edition)[M].New York:Addison Wesley,1992:496-498.
[76]Adams R,Bischof L.Seeded region growing[J].IEEE Trans Pattern Anal Machine Intell,1994,16:641-647.
[77]Jaeyoun Y,Jong Beom R.A locally adaptive region growing algorithm for vascular segmentation[J].International Journal of Imaging Systems and Technology,2003,13(4):208-214.
[78]Nicolas Passat MSc,Christian R,Joseph B.Region-Growing Segmentation of Brain Vessels:An Atlas-Based Automatic Approach[J].Journal of magnetic resonance imaging,2005,21:715-725.
[79]陆剑锋,林海,潘志庚.自适应区域生长算法在医学图像分割中的应用[J].计算机辅助设计与图形学学报,2005,17(10):2168-2173.
[80]Chatzis V,Pitas I.Fuzzy cell hough transform for curve detection[J].Pattern Recognition,1997,30(12):2031-2042.
[81]Lu W,Tan JL.Detection of incomplete ellipse in images with strong noise by iterative[J].Pattern Recognition,2008,41:1268-1279.
[82]Satzoda RK,Suchitra S,Srikanthan T.Parallelizing the Hough Transform Computation[J].IEEE signal processing letters,2008,15:297-300.
[83]He XF,Shi PF.A new segmentation approach for iris recognition based on hand-held capture device[J].Pattern Recognition,2007,40:1326-1333.
[84]Fernandes LAF,Oliveira MM.Real-time line detection through an improved Hough transform voting scheme[J].Pattern Recognition,2008,41:299-314.
[85]Gonzalez-Linares JM,Guil N,Zapata EL.An efficient 2D deformable objects detection and location algorithm[J].Pattern Recognition,2003,36:2543-2556.
[86]Walsh D,Raftery AE.Accurate and efficient curve detection in images:the importance sampling Hough transform[J].Pattern Recognition,2002,35:1421-1431.
[87]Bhandarkar SM.A Fuzzy Probabilistic Model for the Generalized Hough Transform[J].IEEE Transactions on systems,man,and cybernetics,1994,24(5):745-759.
[88]McLaughlin RA.Randomized Hough Transform:Improved ellipse detection with comparison[J].Pattern Recognition Letters,1998,19:299-305.
[89]Xu L,Oja E,Kultaned P.A new curve detection method:randomized Hough transform(RHT).Pattern Recognition Letters,1990,11(5):331-338.
[90]屈稳太.基于弦中点Hough变换的椭圆检测方法[J].浙江大学学报(工学版)2005 39(8):1132-1136.
[91]黎自强,滕弘飞.广义Hough变换:多个圆的快速随机检测[J].2006,18(1):27-33.
[92]陈燕新,戚飞虎.一种新的基于随机Hough变换的椭圆检测方法[J].2000,19(1):43-47.
[93]Crespoa J,Serrab J,Schafer RW.Theoretical aspects of morphological filters by reconstruction[J].Signal Processing,1995,47:201-225.
[94]Heijmans HJAM.Connected Morphological Operators for Binary Images[J].Computer Vision and Image Understanding,1999,73(1):99-120.
[95]Chen T,Wu QH,Rahmani-Torkaman R,et al.A pseudo top-hat mathematical morphological approach to edge detection in dark regions[J].Pattern Recognition,2002,35(1):199-210.
[96]Paglieroni DW.Distance Transforms:Properties and Machine Vision Applications[J].CVGIP:Graphical Models and Image Processing,1992,54(1):56-74.
[97]车武军,杨勋年,汪国昭.动态骨架算法[J].软件学报,2003,14(4):818-823.
[98]Arcelli C,Baja GS.Ridge points in Euclidean distance maps[J].Pattern Recognition Letters,1992,13(4):237-243.
[99]Pan Y,Hamdi M,Li KQ.Euclidean Distance Transform for Binary Images on Reconfigurable Mesh-Connected Computers[J].IEEE Transactions on systems,man,and cybernetics-part b:cybernetics,2000,30(1):240-245.
[100]Breu H,Gil J,Kirkpatrick D,et al.Linear Time Euclidean Distance Transform Algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(5):529-533.
[101]Saito T,Toriwaki JI.New algorithms for Euclidean Distance Transformation of an n-Dimensional Digitized Picture with Applications[J].Pattern recognition,1994,27(11):1551-1565.
[102]Lee YH,Horng SJ,Seitzer J.Parallel computation of the Euclidean distance transform on a three-dimensional image array[J].IEEE Transactions on Parallel and Distributed Systems,2003,14(3):203-212.
[103]Mullikin JC.The Vector Distance Transform in Two and Three Dimensions[J].CVGIP:Graphical models and Image Processing,1992,54(6):526-535.
[104]Borgefors G.Distance Transformations in Arbitrary Dimensions[J].Computer Vision,Graphics,and Image Processing,1984,27:321-345.
[105]Borgefors G.Distance Transformation in Digital images[J].Computer Vision,Graphics,and Image Processing,1986,34:344-371.
[106]Danielsson PE.Euclidean Distance Mapping[J].Computer Graphics and Image Processing,1980,14:227-248.
[107]Piper J,Granum E.Computing distance transformations in convex and nonconvex domains[J].Pattern Recognition,1987,20:599-615.
[108]Vincent L.Exact Euclidean Distance Function By Chain Propagations[C].Proc.IEEE Computer Vision and Pattern Recognition'91,Maui,Hawaii,June 1991,520-525.
[109]Ragnemalm I.Neighborhoods for Distance Transformations UsingOrdered Propagation[J].CVGIP:Image Understanding.1992,56(3):399-409.
[110]Eggers H.Two fast Euclidean distance transformations in Z2 based on sufficient propagation[J].Comput.Vision Image Understanding,1998,69(1):106-116.
[111]Cuisenaire O,Macq B.Fast Euclidean Distance Transformation by Propagation Using Multiple Neighborhoods[J].Computer Vision and Image Understanding,1999,76(2):163-172.
[112]Datta A,Soundaralakshmi S,Fast parallel algorithm for distance transforms[C].Parallel and Distributed Processing Symposium,Proceedings 15th International,Apr 2001:1130-1134.
[113]Cuisenaire O,Macq B.Fast Euclidean Distance Transformation by Propagation Using Multiple Neighborhoods[J].Computer Vision and Image Understanding,1999,76(2):163-172.
[114]崔峰,汪雪林,彭思龙.近似欧氏距离变换的一种并行算法[J].中国图象图形学报,2004,9(6):694-698.
[115]Park J,Keller JM..Snakes on the Watershed[J].IEEE Transactions on pattern analysis and machine intelligence,2001,23(10):1201-1205.
[116]Kiran V,Bora PK.Watersnake:intergating the watershed and the active contour algorithms [A]. In: IEEE TENCON 2003-Conference on Convergent Technologies for Asia-Pacific Region. New Delphi, India: Allied Publishers Pvt Ltd, 2003, 2: 868-871.
[117] Nguyen HT, Worring M, Boomgaard RVD. Watersnakes: Energy-Driven Watershed Segmentation [J]. IEEE transactions on pattern analysis and machine intelligence, 2003, 25(3):330-342.
[118] Elmoataz A, Schupp S, Clouard R, et al. Using active contours and mathematical morphology tools for quanti(?)ation of immunohistochemical images [J]. Signal Processing, 1998, 71:215-226.
[119] Kass M, Witkin A. Terzopoulos. Snakes: active contour models [J]. Int.J.Comp.Vis, 1987,1(4):321-331.
[120] Klemencic A, Kovacic S, Pernus F. Automated Segmentation of Muscle Fiber Images Using Active Contour Models [J]. Cytometry 1998, 32:317-326.
[121] He Y, Luo YP, Hu D. Seeded Region Merging Based on Gradient Vector Flow for Image Segmentation [J]. J. Blanc-Talon et al. (Eds.): ACIVS 2006, LNCS 4179, 2006, 846-854.
[122] Lapeer RJ, Tan AC, Aldridge R. Active Watersheds: Combining 3D Watershed Segmentation and Active Contours to Extract Abdominal Organs from MR Images [J]. T. Dohi and R. Kikinis (Eds.): MICCAI 2002, LNCS 2488, 2002: 596-603.
[123] Zhao CG, Zhuang TG. A hybrid boundary detection algorithm based on watershed and snake [J]. Pattern Recognition Letters, 2005, 26:1256-1265.
[124] Cheng JR, Foo SW, Krishnan SM. Watershed-Presegmented Snake for Boundary Detection and Tracking of Left Ventricle in Echocardiographic Images [J]. IEEE Transactions on information technology in biomedicine, 2006, 10(2): 414-416.
[125] Jackway PT. Gradient Watersheds in Morphological Scale-Space [J]. IEEE Transactions on image processing, 1996, 5(6): 913-921.
[126] Roerdink JB, Meijster A. The watershed transform: definitions, algorithms and parallelization strategies [J]. Fundamental Informatics, 2000, 41:187-228.
[127] Malpica N, Solorzano CO, JoseVaquero J. Applying Watershed Algorithms to the Segmentation of Clustered Nuclei [J]. Cytometry, 1997, 28:289-297.
[128] Lin G, Adiga U, Olson K. A Hybrid 3D Watershed Algorithm Incorporating Gradient Cues and Object Models for Automatic Segmentation of Nuclei in Confocal Image Stacks [J]. Cytometry Part A, 2003, 56A:23-36.
[129] Bicego M, Cristani M, Fusiello A, et al. Watershed-Based Unsupervised Clustering [J]. A. Rangarajan et al. (Eds.): EMMCVPR 2003, LNCS 2683, 2003: 83-94.
[130]康维,欧阳成,王广志,丁辉.基于分水岭变换的彩色细胞图像分割[J].清华大学学报,2006,46(3):414-417.
[131]Wang DM.A multiscale gradient algorithm for image segmentation using watersheds[J].Pattern Recognition,1997,30(12):2043-2052.
[132]Gauch JM,Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies[J].IEEE transactions on image processing,1999,8(1):69-80.
[133]Cares JE,Whitaker RT,Jones GM.Case study:an evaluation of user-assisted hierarchical watershed segmentation[J].Medical Image Analysis,2005,9:566-578.
[134]杨文明,陈国斌,沈晔湖,刘济林.一种基于分水岭变换的图像分割方案[J].浙江大学学报,2006,40(9):1504-1509.
[135]Grau V,Mewes AUJ,Alcafiiz M.Improved Watershed Transform for Medical Image Segmentation Using Prior Information[J].IEEE transactions on medical imaging,2004,23(4):447-458.
[136]Osma-Ruiz V,Godino-Llorente JI,Nicolas Saenz-Lechon,Segmentation of the glottal space from laryngeal images using the watershed transform[J].Computerized Medical Imaging and Graphics,2008,32:193-201.
[137]Vincent L,Pierre S.Watersheds in Digital Spaces:An efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[138]McInerney T,Terzopoulos D.Deformable models in medical image analysis:a survey[J].Medical Image Analysis,1996,1(2):91-108.
[139]李培华,张田文.主动轮廓线模型(蛇模型)综述[J].软件学报,2000,11(6):751-757.
[140]孙志宏,王洪剑,彭思龙.基于距离变换的快速收敛Snake模型[J].计算机辅助设计与图形学学报,2005,17(16):1263-1267.
[141]Lorigo LM,Faugerasa OD,Grimson WEL,et al.Curves:Curve evolution for vessel segmentation[J].Medical Image Analysis,2001,5:195-206.
[142]Tang JS,Acton ST.Vessel Boundary Tracking for Intravital Microscopy Via Multiscale Gradient Vector Flow Snakes[J].IEEE Transactions on biomedical engineering,2004,5(12):316-324.
[143]张俊华,汪源源,施心陵,董怡,王怡.基于边缘流的改进梯度矢量流算法及其在淋巴结超声图像分割中的应用[J].航天医学与医学工程,2006,19(3):212-216.
[144]Korzynska A,Strojny W,Hoppe A.Segmentation of microscope images of living cells[J].Pattern Anal Applic,2007,10:301-319.
[145]Yang L,Meer P,Foran DJ.Unsupervised Segmentation Based on Robust Estimation and Color Active Contour Models[J].IEEE Transactions on information technology in biomedicine,2005,9(3):475-486.
[146]Xu CY,Prince JL.Snakes,shapes,and gradient vector flow[J].IEEE Transactions on Image Processing,1998,7(3):359-369.
[147]Cheng JR,Foo SW.Dynamic Directional Gradient Vector Flow for Snakes[J].IEEE Transactions on image processing,2006,15(6):1563-1572.
[148]田捷,包尚联,周明全.医学影像处理与分析[M].北京:电子工业出版社.2003:71-80.
[149]Fukui Y,Hayasakat S,Bedit KS.Quantitative study of the development of the optic nerve in ratsreared in the dark during early postnatal life[J].J.Anat,1991,174:37-47.
[150]Mazzatenta A,Caleo M,Emilio N,et al.A comparative morphometric analysis of the optic nerve in two cetacean species,the striped dolphin(Stenella coeruleoalba)and fin whale(Balaenoptera physalus)[J].Visual Neuroscience,2001,18:319-325.
[2]Pascal B,Brian L.Unsupervised cell nucleus segmentation with active contours.Signal Processing.1998,71(2):203-213
[3]Jiang TZ,Yang FG.An evolutionary tabu search for cell image segmentation[J].IEEE Transactions on Systems,Man,and Cybernetics,2002,32(5):675-678.
[4]Theerapattanakrul J,Plodpai J,Pintavirooj J.An efficient method for segmentation step of automated white blood cell classifications[J].IEEE Trans Pattern Analysis and Machine Intelligence,2004,1:21-24.
[5]Vivek S,Yongchang J,Dan CM.A parallel algorithmfor automatic particle identification in electron micrographs[J].LNCS,2005,3402:354-367.
[6]张石,王军辉,董建威,齐晓龙.医学显微图像分割方法研究进展[J].中国生物医学工程学报,2007,26(4):623-629.
[7]Brown HG,Martin JR,Asbury AK.Painful diabetic neuropathy.A morphometric study[J].Arch Neurol,1976,33:164-171.
[8]Pollock M,Nukada H,Allpress S,et al.Peripheral nerve morphometry in stroke patients[J].J Neurol Sci,1984,65:341-352.
[9]Thomas PK,Fraher JP,O'Leary D,et al.Relative growth and maturation of axon size and myelin thickness in the tibial nerve of the rat.Ⅱ.Effect of streptozotocin-induced diabetes[J].Acta Neuropathol,1990,79:375-386.
[10]杨柳,李美玉.正常人眼视神经内神经纤维分布[J].眼科研究,1998,16(3):187-189.
[11]Fressinaud C,Vigneron I,Letournel F,et al.Cytoskeleton abnormalities in axonopathies of unknown aetiology:correlations with morphometry[J].Journal of the Neurological Sciences,2002,196:53-61.
[12]Gu XZ,Zhang ZP,Qi L,et al.Morphometry of Axons in Optic Nerves of Siamese's Twins[J].Eye Science,2002,18(3):169-172.
[13]Walsh C.Age-related fiber order in the ferret's optic nerve and optic chiasm[J].J.Neurosci,1986,6:1635-1642.
[14] Wakakuwa K, Watanabe M, Sugimoto T,et al. An electron microscopic analysis of the optic nerve of the eastern chipmunk (Tamias sibiricus asiaticus): Total fiber count and retinotopic organisation [J]. Vis. Res, 1987,27: 1891-1901.
[15] Cepurnaa WO, Kaytonb RJ, Johnsona EC, et al. Age related optic nerve axonal loss in adult Brown Norway rats [J]. Experimental Eye Research, 2005, 80: 877-884.
[16] Williams RW, Chalupa LM. An analysis of axon caliber within the optic nerve of the cat: evidence of size groupings and regional organization [J]. The journal of Neuroscience, 1983,3(8): 1554-1564.
[17] Saito HA. Morphology of physiologically identified X-, Y-, and W-type retinal ganglion cells of the cat [J]. J. Comp. Neurol, 1983, 221:279-288.
[18] Stone J, Campion JE. Estimate of the number of myelinated axons in the cat's optic nerve [J]. J. Comp. Neurol, 1978,180:799-806.
[19] Jonas JB, Mueller-Bergh JA,Schloetzer-Schrehardt UM, et al. Histomorphometry of the human optic nerve [J]. Invest Ophthalmol Vis Sci, 1990, 31(4): 736-744.
[20] Jonas JB, Schmidt AM, Muller-Bergh JA, et al. Human optic nerve fiber count and optic disc size [J]. Invest Ophthalmol Vis Sci, 1992, 33: 2012-2018.
[21] Mayhew TM, Sharma AK. Sampling schemes for estimating nerve fibre size . I. Methods for nerve trunks of mixed fascicularity [J]. J Anat, 1984a, 139:59-66.
[22] Mayhew TM, Sharma AK. Sampling schemes for estimating nerve fibre size. II. Methods for unifascicular nerve trunks [J]. J Anat 1984b, 139: 59-66.
[23] Rainer L, Dieter M, Christine Ernzerhofa. Automated and representative fascicle selection for computer-assisted morphometry of myelinated nerve fibers in peripheral nerves [J]. Computers in Biology and Medicine, 2002, 32: 1-11.
[24] Canpolat Leyla, Kiikner A, Canpolat I, et al. Ultrastructural and Morphometric Analysis of Peripheral Nerve Regeneration Within Silicone Tubes [J]. Tr. J. of Medical Sciences. 1999: 29:203-209.
[25] Cull G, Sci BA, Cioffi GA, et al. Estimating Normal Optic Nerve Axon Numbers in Non-Human [J]. Journal of Glaucoma 2003, 12:301-306.
[26] Karim S, Clark RA, Vadims P, et al. Demonstration of Systematic Variation in Human Intraorbital Optic Nerve Size by Quantitative Magnetic Resonance Imaging and Histology [J]. Investigative Ophthalmology & Visual Science, 2004, 45(4): 1047-1051.
[27] Demir N, Akkoyunlu G, Yargicoglu P, et al. Fiber Structure of Optic Nerve in Cadmium-Exposed Diabetic Rats: An UltraStructural Study [J]. Intern. J. Neuroscience, 2003, 113:323-337.
[28] Weyn B, Remoortere MV, Nuydens R. A multiparametric assay for quantitative nerve regeneration evaluation [J]. Journal of Microscopy, 2005, 219(2): 95-101.
[29] Jonas JB, Muller-Bergh JA, Schlorzer-Schrehardr UM, et al. Histomorphometry of the Human Optic Nerve [J]. Investigative Ophthalmology & Visual Science, 1990, 31(4):736-744.
[30] Mathews MA. An electron microscopic study of the relationship between axon diameter and the initiation of myelin production in the peripheral nervous system [J]. AnatRec, 1968, 161:337-352.
[31] Williams RW, Bastiani MJ, Chalupa L. Loss of axons in the cat optic nerve following fetal unilateral enucleation: an electron microscopic analysis [J]. The Journal of Neuroscienc, 1983,3(1): 133-144.
[32] Cepurnaa WO, Kaytonb RJ, Johnson EC, et al. Age related optic nerve axonal loss in adult Brown Norway rats [J]. Experimental Eye Research, 2005, 80: 877-884.
[33] Drenhaus U, Thomas K, Rager G. The course of later generated axons in the developing optic nerve of the chick embryo: A morphometric electron microscopic study [J]. Developmental Brain Research, 2000, 121: 35-53.
[34] Gonzalez RC, Woods RE. Digital Image Processing (3rd Edition) [M]. New York: Addison Wesley, 1992:136-141.
[35] Sonka M, Hlavac V, Boyle R. Image Processing, Analysis, and Machine Vision (2nd Edition) [M]. 北京：人民邮电出版社,2002：232-235．
[36] 章毓晋．图像分割[M]．北京：科学技术出版社,2006．
[37] Thomas W, Jens S, Dietrich ME, et al., Robust automaticcoregistration, segmentation, and classification of cell nucleiin multimodal cytopathological microscopic images [J].Computerized Medical Imaging and Graphics, 2004, 28(1): 87-98.
[38] Nattkemper TW, Wersing H, Schubert W, et al. A neural network architecture for automatic segmentation of fluorescence micrographs [J]. Neurocomputing, 2002, 48(1-4):357-367.
[39] Sanchez RM, Dunkelberger GR, Quigley HA. The number and diameter distribution of axons in the monkey optic nerve [J]. Invest Ophthalmol Vis Sci., 1986, 27:1342-1350.
[40] Mezin P, Tenaud C, Bosson JL, Stoebner P. Morphometric analysis of the peripheral nerve: advantages of the semi-automated interactive method [J]. J Neurosci Methods,1994,51:163-169.
[41]Malbouisson AMB,Ghabriel MN,Allt G.Axonal microtubules:a computer-linked quantitative analysis[J].Anat Embryol,1985,171:339-344.
[42]Auer RN.Automated nerve fibre size and myelin sheath measurement using microcomputer-based digital image analysis:theory,method and results[J].J Neurosci Methods,1994,51:229-238.
[43]Wang JF,Schr(o|¨)der JM.Comparative morphometric evaluation of peripheral nerves and muscle fibers in myotonic dystrophy[J].Acta Neuropathol,2000,99:39-47.
[44]Campadelli P,Gangai C,Pasquale F.Automated morphometric analysis in peripheral neuropathies,Comput.Biol.Med,1999,29:147-155.
[45]Urso-Baiarda F,Grobbelaar AO.Practical nerve morphometry[J].Journal of Neuroscience Methods,2006,156(1-2):333-341.
[46]Brenner JF,Zahniser D J,Ziegelmiller DW,Adelman LS,et.al.Automated system for the analysis of muscle and nerve biopsies.Applied Optics,1987,26(16):3398-3407.
[47]Girish V,Vijayalakshmi A.Affordable image analysis using NIH Image/Image [J].J Indian J Cancer 2004,41:47-52.
[48]Vita G,Santoro M,Trombetta G,Leonardi L,Messina C.A computer-assisted automatic method for myelinated nerve fiber morphometry[J].Acta Neurol Scand.,1992,85:18-22.
[49]Silva APD,Jordao CER,Fazan VPS.Peripheral nerve morphometry:Comparison between manual and semi-automated methods in the analysis of a small nerve[J].Journal of Neuroscience Methods,2007,159(1):153-157.
[50]Klemencic A,Kovacic S.Automated Segmentation of Muscle Fiber Images Using Active Contour Models[J].Cytometry,1998,32:317-326.
[51]Campadelli P,Gangai C,Pasquale F.Automated morphometric analysis in peripheral neuropathies[J].Comp Biol Med.,1999,29:147-156.
[52]Fok YL,Chan JCK,Chin RT.Automated Analysis of Nerve-Cell Images Automated Analysis of Nerve-Cell Images[J].IEEE Transactions on medical imaging,1996,15(3):353-368.
[53]Romero E,Cuisenaire O.Automatic morphometry of nerve histological sections [J].Journal of Neuroscience Methods,2000,97:111-122.
[54]朗斯塔夫.神经科学(中译本)[M].北京:科学出版社,2006,10-12.
[55]韩济生.神经科学原理(第二版,上册)[M].北京:北京医科大学出版社,1999,141-150.
[56]Drenhaus U,Gunten AV,Rager G.Classes of Axons and Their Distribution in the Optic Nerve of the Tree Shrew(Tupaia belangeri)[J].The anatomical record.1997,249:103-116.
[57]Johnson PT,Geller SF,Reese BE.Distribution,size and number of axons in the optic pathway of ground squirrels[J].Exp Brain Res.1998,118:93-104.
[58]Brooks DE,Strubbe DT.Histomorphometry of the Optic Nerves of Normal Dogs and Dogs with Hereditary Glaucoma[J].Expl Eye Res.,1995,60:71-89.
[59]Cull G,Sci BA.Estimating Normal Optic Nerve Axon Numbers in Non-Human [J].Journal of Glaucoma,2003,12:301-306.
[60]Cepurnaa WO,Kaytonb RJ,Elaine C,et al.Age related optic nerve axonal loss in adult Brown Norway rats[J].Experimental Eye Research.,2005,80:877-884.
[61]Williams PL,Wendell-Smith CP.The Use of Fixed and Stained Sections in Quantitative Studies of Peripheral Nerve[J].Quarterly Journal of Microscopical Science,1960,101(1):43-54.
[62]Vilai C,Phinidda Cha-oumphol DVM,MSc,Athitaya Kaewsema BSc,et al.Morphometric Data of Normal Sural Nerve in Thai Adults[J].J Med Assoc Thai,2006,89(5):670-674.
[63]刘印锋,葛华勇,王保华.医学显微图像的数字化技术[J].中国医疗器械信息,2005,11(3):24-27.
[64]彭宣戈,欧阳春娟,欧阳迎春,朱兵.多方向一维小波变换的显微图像去噪[J].计算机工程,2007,43(12):31-35.
[65]Caselles V,Lisani JL,Morel JM,et al.Shape Preserving Local Histogram Modification[J].IEEE transactions on image processing,1999,8(2):220-229
[66]Chan FHY,Lam FK,Zhu H.Adaptive thresholding by variational method[J].IEEE Trans.Image Process.1998,7(3):468-473.
[67]Sahoo PK,Arora G.Image thresholding using two dimensional Tsallis-Havrda-Charvart entropy[J].Pattern Recogn.Lett.2006,27:520-528.
[68]Otsu N.A threshold selection method from gray level histograms[J].IEEE Trans Syst Man Cyber.,1979,9(1):62-66.
[69]Abutaleb AS.Automatic thresholding of gray-level pictures using two-dimensional entropy[J].Comput.Vis.Graphics Image Process.1989,47:22-32.
[70]Synder W,Bilbro G.Optimal thresholding:a new approach[J].Pattern Recog. Lett.1990,11:803-810.
[71]Liu D,Jiang Z,Feng H.A novel fuzzy classification entropy approach to image thresholding[J].Pattern Recognition Letters,2006,27:1968-1975.
[72]Sezgin M,Sankur B.Survey over image thresholding techniques and quantitative performance evaluation[J].J.Electronic Imaging,2004,13(1):146-165.
[73]Zahara E,Fan SS,Tsai D.Optimal multi-thresholding using a hybrid optimisation approach[J].Pattern Recogn.Lett.2005,26(8):1082-1095.
[74]章毓晋.图像分割[M].北京:科学技术出版社,2006,9-14.
[75]Gonzalez RC,Woods RE.Digital Image Processing(3rd Edition)[M].New York:Addison Wesley,1992:496-498.
[76]Adams R,Bischof L.Seeded region growing[J].IEEE Trans Pattern Anal Machine Intell,1994,16:641-647.
[77]Jaeyoun Y,Jong Beom R.A locally adaptive region growing algorithm for vascular segmentation[J].International Journal of Imaging Systems and Technology,2003,13(4):208-214.
[78]Nicolas Passat MSc,Christian R,Joseph B.Region-Growing Segmentation of Brain Vessels:An Atlas-Based Automatic Approach[J].Journal of magnetic resonance imaging,2005,21:715-725.
[79]陆剑锋,林海,潘志庚.自适应区域生长算法在医学图像分割中的应用[J].计算机辅助设计与图形学学报,2005,17(10):2168-2173.
[80]Chatzis V,Pitas I.Fuzzy cell hough transform for curve detection[J].Pattern Recognition,1997,30(12):2031-2042.
[81]Lu W,Tan JL.Detection of incomplete ellipse in images with strong noise by iterative[J].Pattern Recognition,2008,41:1268-1279.
[82]Satzoda RK,Suchitra S,Srikanthan T.Parallelizing the Hough Transform Computation[J].IEEE signal processing letters,2008,15:297-300.
[83]He XF,Shi PF.A new segmentation approach for iris recognition based on hand-held capture device[J].Pattern Recognition,2007,40:1326-1333.
[84]Fernandes LAF,Oliveira MM.Real-time line detection through an improved Hough transform voting scheme[J].Pattern Recognition,2008,41:299-314.
[85]Gonzalez-Linares JM,Guil N,Zapata EL.An efficient 2D deformable objects detection and location algorithm[J].Pattern Recognition,2003,36:2543-2556.
[86]Walsh D,Raftery AE.Accurate and efficient curve detection in images:the importance sampling Hough transform[J].Pattern Recognition,2002,35:1421-1431.
[87]Bhandarkar SM.A Fuzzy Probabilistic Model for the Generalized Hough Transform[J].IEEE Transactions on systems,man,and cybernetics,1994,24(5):745-759.
[88]McLaughlin RA.Randomized Hough Transform:Improved ellipse detection with comparison[J].Pattern Recognition Letters,1998,19:299-305.
[89]Xu L,Oja E,Kultaned P.A new curve detection method:randomized Hough transform(RHT).Pattern Recognition Letters,1990,11(5):331-338.
[90]屈稳太.基于弦中点Hough变换的椭圆检测方法[J].浙江大学学报(工学版)2005 39(8):1132-1136.
[91]黎自强,滕弘飞.广义Hough变换:多个圆的快速随机检测[J].2006,18(1):27-33.
[92]陈燕新,戚飞虎.一种新的基于随机Hough变换的椭圆检测方法[J].2000,19(1):43-47.
[93]Crespoa J,Serrab J,Schafer RW.Theoretical aspects of morphological filters by reconstruction[J].Signal Processing,1995,47:201-225.
[94]Heijmans HJAM.Connected Morphological Operators for Binary Images[J].Computer Vision and Image Understanding,1999,73(1):99-120.
[95]Chen T,Wu QH,Rahmani-Torkaman R,et al.A pseudo top-hat mathematical morphological approach to edge detection in dark regions[J].Pattern Recognition,2002,35(1):199-210.
[96]Paglieroni DW.Distance Transforms:Properties and Machine Vision Applications[J].CVGIP:Graphical Models and Image Processing,1992,54(1):56-74.
[97]车武军,杨勋年,汪国昭.动态骨架算法[J].软件学报,2003,14(4):818-823.
[98]Arcelli C,Baja GS.Ridge points in Euclidean distance maps[J].Pattern Recognition Letters,1992,13(4):237-243.
[99]Pan Y,Hamdi M,Li KQ.Euclidean Distance Transform for Binary Images on Reconfigurable Mesh-Connected Computers[J].IEEE Transactions on systems,man,and cybernetics-part b:cybernetics,2000,30(1):240-245.
[100]Breu H,Gil J,Kirkpatrick D,et al.Linear Time Euclidean Distance Transform Algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1995,17(5):529-533.
[101]Saito T,Toriwaki JI.New algorithms for Euclidean Distance Transformation of an n-Dimensional Digitized Picture with Applications[J].Pattern recognition,1994,27(11):1551-1565.
[102]Lee YH,Horng SJ,Seitzer J.Parallel computation of the Euclidean distance transform on a three-dimensional image array[J].IEEE Transactions on Parallel and Distributed Systems,2003,14(3):203-212.
[103]Mullikin JC.The Vector Distance Transform in Two and Three Dimensions[J].CVGIP:Graphical models and Image Processing,1992,54(6):526-535.
[104]Borgefors G.Distance Transformations in Arbitrary Dimensions[J].Computer Vision,Graphics,and Image Processing,1984,27:321-345.
[105]Borgefors G.Distance Transformation in Digital images[J].Computer Vision,Graphics,and Image Processing,1986,34:344-371.
[106]Danielsson PE.Euclidean Distance Mapping[J].Computer Graphics and Image Processing,1980,14:227-248.
[107]Piper J,Granum E.Computing distance transformations in convex and nonconvex domains[J].Pattern Recognition,1987,20:599-615.
[108]Vincent L.Exact Euclidean Distance Function By Chain Propagations[C].Proc.IEEE Computer Vision and Pattern Recognition'91,Maui,Hawaii,June 1991,520-525.
[109]Ragnemalm I.Neighborhoods for Distance Transformations UsingOrdered Propagation[J].CVGIP:Image Understanding.1992,56(3):399-409.
[110]Eggers H.Two fast Euclidean distance transformations in Z2 based on sufficient propagation[J].Comput.Vision Image Understanding,1998,69(1):106-116.
[111]Cuisenaire O,Macq B.Fast Euclidean Distance Transformation by Propagation Using Multiple Neighborhoods[J].Computer Vision and Image Understanding,1999,76(2):163-172.
[112]Datta A,Soundaralakshmi S,Fast parallel algorithm for distance transforms[C].Parallel and Distributed Processing Symposium,Proceedings 15th International,Apr 2001:1130-1134.
[113]Cuisenaire O,Macq B.Fast Euclidean Distance Transformation by Propagation Using Multiple Neighborhoods[J].Computer Vision and Image Understanding,1999,76(2):163-172.
[114]崔峰,汪雪林,彭思龙.近似欧氏距离变换的一种并行算法[J].中国图象图形学报,2004,9(6):694-698.
[115]Park J,Keller JM..Snakes on the Watershed[J].IEEE Transactions on pattern analysis and machine intelligence,2001,23(10):1201-1205.
[116]Kiran V,Bora PK.Watersnake:intergating the watershed and the active contour algorithms [A]. In: IEEE TENCON 2003-Conference on Convergent Technologies for Asia-Pacific Region. New Delphi, India: Allied Publishers Pvt Ltd, 2003, 2: 868-871.
[117] Nguyen HT, Worring M, Boomgaard RVD. Watersnakes: Energy-Driven Watershed Segmentation [J]. IEEE transactions on pattern analysis and machine intelligence, 2003, 25(3):330-342.
[118] Elmoataz A, Schupp S, Clouard R, et al. Using active contours and mathematical morphology tools for quanti(?)ation of immunohistochemical images [J]. Signal Processing, 1998, 71:215-226.
[119] Kass M, Witkin A. Terzopoulos. Snakes: active contour models [J]. Int.J.Comp.Vis, 1987,1(4):321-331.
[120] Klemencic A, Kovacic S, Pernus F. Automated Segmentation of Muscle Fiber Images Using Active Contour Models [J]. Cytometry 1998, 32:317-326.
[121] He Y, Luo YP, Hu D. Seeded Region Merging Based on Gradient Vector Flow for Image Segmentation [J]. J. Blanc-Talon et al. (Eds.): ACIVS 2006, LNCS 4179, 2006, 846-854.
[122] Lapeer RJ, Tan AC, Aldridge R. Active Watersheds: Combining 3D Watershed Segmentation and Active Contours to Extract Abdominal Organs from MR Images [J]. T. Dohi and R. Kikinis (Eds.): MICCAI 2002, LNCS 2488, 2002: 596-603.
[123] Zhao CG, Zhuang TG. A hybrid boundary detection algorithm based on watershed and snake [J]. Pattern Recognition Letters, 2005, 26:1256-1265.
[124] Cheng JR, Foo SW, Krishnan SM. Watershed-Presegmented Snake for Boundary Detection and Tracking of Left Ventricle in Echocardiographic Images [J]. IEEE Transactions on information technology in biomedicine, 2006, 10(2): 414-416.
[125] Jackway PT. Gradient Watersheds in Morphological Scale-Space [J]. IEEE Transactions on image processing, 1996, 5(6): 913-921.
[126] Roerdink JB, Meijster A. The watershed transform: definitions, algorithms and parallelization strategies [J]. Fundamental Informatics, 2000, 41:187-228.
[127] Malpica N, Solorzano CO, JoseVaquero J. Applying Watershed Algorithms to the Segmentation of Clustered Nuclei [J]. Cytometry, 1997, 28:289-297.
[128] Lin G, Adiga U, Olson K. A Hybrid 3D Watershed Algorithm Incorporating Gradient Cues and Object Models for Automatic Segmentation of Nuclei in Confocal Image Stacks [J]. Cytometry Part A, 2003, 56A:23-36.
[129] Bicego M, Cristani M, Fusiello A, et al. Watershed-Based Unsupervised Clustering [J]. A. Rangarajan et al. (Eds.): EMMCVPR 2003, LNCS 2683, 2003: 83-94.
[130]康维,欧阳成,王广志,丁辉.基于分水岭变换的彩色细胞图像分割[J].清华大学学报,2006,46(3):414-417.
[131]Wang DM.A multiscale gradient algorithm for image segmentation using watersheds[J].Pattern Recognition,1997,30(12):2043-2052.
[132]Gauch JM,Image Segmentation and Analysis via Multiscale Gradient Watershed Hierarchies[J].IEEE transactions on image processing,1999,8(1):69-80.
[133]Cares JE,Whitaker RT,Jones GM.Case study:an evaluation of user-assisted hierarchical watershed segmentation[J].Medical Image Analysis,2005,9:566-578.
[134]杨文明,陈国斌,沈晔湖,刘济林.一种基于分水岭变换的图像分割方案[J].浙江大学学报,2006,40(9):1504-1509.
[135]Grau V,Mewes AUJ,Alcafiiz M.Improved Watershed Transform for Medical Image Segmentation Using Prior Information[J].IEEE transactions on medical imaging,2004,23(4):447-458.
[136]Osma-Ruiz V,Godino-Llorente JI,Nicolas Saenz-Lechon,Segmentation of the glottal space from laryngeal images using the watershed transform[J].Computerized Medical Imaging and Graphics,2008,32:193-201.
[137]Vincent L,Pierre S.Watersheds in Digital Spaces:An efficient algorithm based on immersion simulations[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(6):583-598.
[138]McInerney T,Terzopoulos D.Deformable models in medical image analysis:a survey[J].Medical Image Analysis,1996,1(2):91-108.
[139]李培华,张田文.主动轮廓线模型(蛇模型)综述[J].软件学报,2000,11(6):751-757.
[140]孙志宏,王洪剑,彭思龙.基于距离变换的快速收敛Snake模型[J].计算机辅助设计与图形学学报,2005,17(16):1263-1267.
[141]Lorigo LM,Faugerasa OD,Grimson WEL,et al.Curves:Curve evolution for vessel segmentation[J].Medical Image Analysis,2001,5:195-206.
[142]Tang JS,Acton ST.Vessel Boundary Tracking for Intravital Microscopy Via Multiscale Gradient Vector Flow Snakes[J].IEEE Transactions on biomedical engineering,2004,5(12):316-324.
[143]张俊华,汪源源,施心陵,董怡,王怡.基于边缘流的改进梯度矢量流算法及其在淋巴结超声图像分割中的应用[J].航天医学与医学工程,2006,19(3):212-216.
[144]Korzynska A,Strojny W,Hoppe A.Segmentation of microscope images of living cells[J].Pattern Anal Applic,2007,10:301-319.
[145]Yang L,Meer P,Foran DJ.Unsupervised Segmentation Based on Robust Estimation and Color Active Contour Models[J].IEEE Transactions on information technology in biomedicine,2005,9(3):475-486.
[146]Xu CY,Prince JL.Snakes,shapes,and gradient vector flow[J].IEEE Transactions on Image Processing,1998,7(3):359-369.
[147]Cheng JR,Foo SW.Dynamic Directional Gradient Vector Flow for Snakes[J].IEEE Transactions on image processing,2006,15(6):1563-1572.
[148]田捷,包尚联,周明全.医学影像处理与分析[M].北京:电子工业出版社.2003:71-80.
[149]Fukui Y,Hayasakat S,Bedit KS.Quantitative study of the development of the optic nerve in ratsreared in the dark during early postnatal life[J].J.Anat,1991,174:37-47.
[150]Mazzatenta A,Caleo M,Emilio N,et al.A comparative morphometric analysis of the optic nerve in two cetacean species,the striped dolphin(Stenella coeruleoalba)and fin whale(Balaenoptera physalus)[J].Visual Neuroscience,2001,18:319-325.