基于图像分析的人体微循环参数测量及识别研究
|
摘要
微循环是反映人体健康的重要指标，在许多生理和病理状态下有着重要的参考价值，对其进行可靠有效的自动检测，在预防疾病的发生和药物疗效检测方面有着极其重要的作用。在过去微循环的测量由人工完成，这不仅花费大量人力物力，而且无法保证测量精度，为了克服这些缺点，一些研究人员使用计算机技术开展了微循环的自动化测量研究。
虽然基于计算机的微循环自动化测量在一些方面取得了较大的进展，但依然有许多问题有待进一步研究。为了促进微循环学科的发展，推进微循环的计算机自动测量与识别工作，本文进行了以下几个方面的研究：
1、针对光学无损方式采集的微循环图像具有光照不均、噪声大、对比度低等特点，研究了基于多尺度分析的光照不均匀图像的校正方法，提出了基于Contourlet变换的微循环图像增强方法，实现了微循环图像的增强，改善了微循环图像的可视化效果。
2、为了实现微循环血管形态参数的自动测量，提出了基于视频图像序列的微循环参数自动测量方法，该方法实现了微循环形态参数的自动测量。研究了有血管区域和无血管区域的判断准则；设计了血管中心线自动迭代提取算法，包括种子点的自动选取、中心线迭代算法的设计以及停止条件判断准则；研究了血管边界和直径以及血管曲率的自动测量方法。分析了测量参数对微循环病变识别的统计特性。
3、针对不同类型微循环血管流态的复杂性，研究了基于ST图的流速测量方法。提出了基于正交滤波器组测量微循环流速的方法。比较了提出方法与现有方法的测量精度和测量鲁棒性，讨论了各种方法测量失败的原因，结果验证了提出方法的优越性。
4、为了实现微循环的血液细胞跟踪与测量，提出了基于ST图的细胞跟踪与测量方法。设计了基于多尺度方向滤波器的ST图像增强方法，设计了噪声滤波函数和方向滤波函数，设计了轨迹细化和分岔处理算法，实现了细胞的跟踪和流速测量。分析了滤波器参数的取值方案，讨论了单条跟踪线对细胞跟踪的局限性。
5、针对单条跟踪线无法跟踪微循环血液细胞复杂运动的情况，研究了基于三条跟踪线的细胞跟踪方法。提出了多候选轨迹自动分组准则和多候选轨迹的融合准则，实现了细胞的自动跟踪。为了验证细胞跟踪的有效性，提出了细胞跟踪有效性验证准则。针对三条跟踪线无法跟踪较大血管细胞运动的情况，研究了多跟踪线的细胞跟踪方法。提出了多跟踪线的轨迹融合准则以及最优跟踪线数量的选择准则。讨论了多跟踪线的方向选择问题。
6、为了实现微循环的计算机自动辅助诊断，研究了微循环的自动识别方法。在微循环血管参数自动测量的基础上，以测量参数作为特征向量，利用模式识别方法对微循环血管进行分类与识别，结果显示，本文研究的微循环自动识别方法能够有效地应用在疾病的辅助诊断中。
The parameters of the microcirculation are the indictors for the health of the human, which shown theimportant reference value in pathological and physiological aspects. Automatic detecting andrecognizing the patterns of microcirculation securely and efficiently have important effect in preventingthe disease occurrence and the therapeutic drug monitoring. However, the traditional way for theparameters of microcirculation detection was via manual measurement, which was not onlytime-consuming, but also lack of measurement accuracy. To handle this shortcoming, some researchersdeveloped the techniques for automatic detection of the parameters of microcirculation by usingcomputer analysis.
Although great advantage progress obtained in the automatic detection of the parameters ofmicrocirculation based on computer analysis, there are still lots of problems should be furtherresearched. In order to improve the development of microcirculation, and promote the research ofautomatic detection and recognition of microcirculation based on computer analysis, we have doneseveral studies in the following aspects.
First, according to the fact that the microcirculation images captured by non-destructive opticalimaging method were usually with uneven illumination background, strong noise and low contrast, theillumination correction method was studied, and then the microcirculation images enhancement methodbased on Contourlet transform was proposed. The enhancement of microcirculation images wererealized, which improved the images visualization effect.
Second, in order to realize the parameters of microcirculation automatic detection, the parameters ofmicrocirculation automatic detection method based on video frame sequence was developed. By usingthe developed method, the automatic measurements of geometric parameters were realized. Thedecision criteria for the area that with a vascular or not was proposed; the algorithm for automaticiterative extraction of blood vessels centerline was proposed, which including automatic selection ofthe seed points, the iterative algorithm design and stopping criteria establishment; the fast calculationmethod for the boundary, diameter and curvature of blood vessel were researched. The statisticalcharacters of the measured parameters for abnormal microcirculation recognition were analyzed.Third, aim at the complication of the measurement of blood flow velocity in different types ofmicrocirculation blood vessels, the method for velocity measurement based on ST image wasresearched. A new method for measurement of the flow velocity of microcirculation based on a quadrature filter banks was proposed. The precision and robustness of the proposed method were alsocompared with the existed methods. The reasons for the failure measurement were also discussed. Theresults showed the superiority of the proposed method.
Fourth, in order to realized the automatic tracking and measurement of the motion of blood cells ofmicrocirculation, the method for blood cells tracking and measurement based on ST image wasproposed. The ST image enhancement method based on multiscale directional filters was designed, thenoise suppression function and orientation filtering function were designed, the traces thinning andbifurcation traces cutting algorithm were designed, and then the blood cells tracking and velocitymeasurement were realized. The way of the parameter selection of the filter was analyzed. Thelimitations that a single trackpath for blood cells tracking were discussed.
Fifth, to resolve the helpless tracking of the complicated motion of blood cells in microcirculation byusing a single trackpath, a method for blood cells tracking based on three trackpaths was researched.The automatic grouping criteria of traces candidates was proposed, the fusion criteria of tracescandidates was proposed, which realized the automatic blood cells tracking. In order to verify thevalidation of the tracking results of blood cells, the validation verification criteria of blood cellstracking was proposed. For the situation that three trackpaths were not enough for tracking the motionof blood cells in larger blood vessel in microcirculation, a method based on multiple trackpaths wasresearched. The traces fusion criteria of multiple trackpaths was proposed and the criteria of optimalnumber of trackpaths selection was proposed. Finally, the direction of the multiple trackpaths selectionwas discussed.
Sixth, in order to realize the computer aided diagnosis for microcirculation, the automated recognitionmethod was researched. After the parameters of microcirculation were measured automatically, theparemeters were formed as the feature vectors and the pattern recognition method were employed toautomatically classify and recognize the microcirculation. The results show the proposed method canbe applied in disease assistant diagnosis efficiently.
虽然基于计算机的微循环自动化测量在一些方面取得了较大的进展，但依然有许多问题有待进一步研究。为了促进微循环学科的发展，推进微循环的计算机自动测量与识别工作，本文进行了以下几个方面的研究：
1、针对光学无损方式采集的微循环图像具有光照不均、噪声大、对比度低等特点，研究了基于多尺度分析的光照不均匀图像的校正方法，提出了基于Contourlet变换的微循环图像增强方法，实现了微循环图像的增强，改善了微循环图像的可视化效果。
2、为了实现微循环血管形态参数的自动测量，提出了基于视频图像序列的微循环参数自动测量方法，该方法实现了微循环形态参数的自动测量。研究了有血管区域和无血管区域的判断准则；设计了血管中心线自动迭代提取算法，包括种子点的自动选取、中心线迭代算法的设计以及停止条件判断准则；研究了血管边界和直径以及血管曲率的自动测量方法。分析了测量参数对微循环病变识别的统计特性。
3、针对不同类型微循环血管流态的复杂性，研究了基于ST图的流速测量方法。提出了基于正交滤波器组测量微循环流速的方法。比较了提出方法与现有方法的测量精度和测量鲁棒性，讨论了各种方法测量失败的原因，结果验证了提出方法的优越性。
4、为了实现微循环的血液细胞跟踪与测量，提出了基于ST图的细胞跟踪与测量方法。设计了基于多尺度方向滤波器的ST图像增强方法，设计了噪声滤波函数和方向滤波函数，设计了轨迹细化和分岔处理算法，实现了细胞的跟踪和流速测量。分析了滤波器参数的取值方案，讨论了单条跟踪线对细胞跟踪的局限性。
5、针对单条跟踪线无法跟踪微循环血液细胞复杂运动的情况，研究了基于三条跟踪线的细胞跟踪方法。提出了多候选轨迹自动分组准则和多候选轨迹的融合准则，实现了细胞的自动跟踪。为了验证细胞跟踪的有效性，提出了细胞跟踪有效性验证准则。针对三条跟踪线无法跟踪较大血管细胞运动的情况，研究了多跟踪线的细胞跟踪方法。提出了多跟踪线的轨迹融合准则以及最优跟踪线数量的选择准则。讨论了多跟踪线的方向选择问题。
6、为了实现微循环的计算机自动辅助诊断，研究了微循环的自动识别方法。在微循环血管参数自动测量的基础上，以测量参数作为特征向量，利用模式识别方法对微循环血管进行分类与识别，结果显示，本文研究的微循环自动识别方法能够有效地应用在疾病的辅助诊断中。
The parameters of the microcirculation are the indictors for the health of the human, which shown theimportant reference value in pathological and physiological aspects. Automatic detecting andrecognizing the patterns of microcirculation securely and efficiently have important effect in preventingthe disease occurrence and the therapeutic drug monitoring. However, the traditional way for theparameters of microcirculation detection was via manual measurement, which was not onlytime-consuming, but also lack of measurement accuracy. To handle this shortcoming, some researchersdeveloped the techniques for automatic detection of the parameters of microcirculation by usingcomputer analysis.
Although great advantage progress obtained in the automatic detection of the parameters ofmicrocirculation based on computer analysis, there are still lots of problems should be furtherresearched. In order to improve the development of microcirculation, and promote the research ofautomatic detection and recognition of microcirculation based on computer analysis, we have doneseveral studies in the following aspects.
First, according to the fact that the microcirculation images captured by non-destructive opticalimaging method were usually with uneven illumination background, strong noise and low contrast, theillumination correction method was studied, and then the microcirculation images enhancement methodbased on Contourlet transform was proposed. The enhancement of microcirculation images wererealized, which improved the images visualization effect.
Second, in order to realize the parameters of microcirculation automatic detection, the parameters ofmicrocirculation automatic detection method based on video frame sequence was developed. By usingthe developed method, the automatic measurements of geometric parameters were realized. Thedecision criteria for the area that with a vascular or not was proposed; the algorithm for automaticiterative extraction of blood vessels centerline was proposed, which including automatic selection ofthe seed points, the iterative algorithm design and stopping criteria establishment; the fast calculationmethod for the boundary, diameter and curvature of blood vessel were researched. The statisticalcharacters of the measured parameters for abnormal microcirculation recognition were analyzed.Third, aim at the complication of the measurement of blood flow velocity in different types ofmicrocirculation blood vessels, the method for velocity measurement based on ST image wasresearched. A new method for measurement of the flow velocity of microcirculation based on a quadrature filter banks was proposed. The precision and robustness of the proposed method were alsocompared with the existed methods. The reasons for the failure measurement were also discussed. Theresults showed the superiority of the proposed method.
Fourth, in order to realized the automatic tracking and measurement of the motion of blood cells ofmicrocirculation, the method for blood cells tracking and measurement based on ST image wasproposed. The ST image enhancement method based on multiscale directional filters was designed, thenoise suppression function and orientation filtering function were designed, the traces thinning andbifurcation traces cutting algorithm were designed, and then the blood cells tracking and velocitymeasurement were realized. The way of the parameter selection of the filter was analyzed. Thelimitations that a single trackpath for blood cells tracking were discussed.
Fifth, to resolve the helpless tracking of the complicated motion of blood cells in microcirculation byusing a single trackpath, a method for blood cells tracking based on three trackpaths was researched.The automatic grouping criteria of traces candidates was proposed, the fusion criteria of tracescandidates was proposed, which realized the automatic blood cells tracking. In order to verify thevalidation of the tracking results of blood cells, the validation verification criteria of blood cellstracking was proposed. For the situation that three trackpaths were not enough for tracking the motionof blood cells in larger blood vessel in microcirculation, a method based on multiple trackpaths wasresearched. The traces fusion criteria of multiple trackpaths was proposed and the criteria of optimalnumber of trackpaths selection was proposed. Finally, the direction of the multiple trackpaths selectionwas discussed.
Sixth, in order to realize the computer aided diagnosis for microcirculation, the automated recognitionmethod was researched. After the parameters of microcirculation were measured automatically, theparemeters were formed as the feature vectors and the pattern recognition method were employed toautomatically classify and recognize the microcirculation. The results show the proposed method canbe applied in disease assistant diagnosis efficiently.
引文
[1]陈蕾,章恩耀,孙利群.正交偏振光谱微循环成像方法及装置.应用光学,2007,28(2):169-172.
[2]吕瑞林,吴伯瑜.皮肤微循环检测方法及其新进展.医学综述,2003,12(2):124-128.
[3]陈蕾,章恩耀,王佳.皮肤微循环无损伤光学成像技术的新进展.光学技术,2003,29(6):690-692.
[4] Leahy, M.J., J.G. Enfield, N.T. Clancy, et al. Biophotonic methods in microcirculation imaging.Medical Laser Application,2007,22(2):105-126.
[5] Awan, Z., T. Wester,K. Kvernebo. Human microvascular imaging: a review of skin and tonguevideomicroscopy techniques and analysing variables. Clinical physiology and functional imaging,2010,30(2):79-88.
[6] Goedhart, P., M. Khalilzada, R. Bezemer, et al. Sidestream Dark Field (SDF) imaging: a novelstroboscopic LED ring-based imaging modality for clinical assessment of the microcirculation.Optics express,2007,15(23):15101-15114.
[7]许谦,雷俊锋,曾立波.正交偏振多光谱成像术应用于活体微循环观察研究.光谱学与光谱分析,2010,30(7):1886-1889.
[8] Martin, D.S., C. Ince, P. Goedhart, et al. Abnormal blood flow in the sublingual microcirculationat high altitude. European journal of applied physiology,2009,106(3):473-478.
[9] Boerma, E.C., M. Koopmans, A. Konijn, et al. Effects of nitroglycerin on sublingualmicrocirculatory blood flow in patients with severe sepsis/septic shock after a strict resuscitationprotocol: a double-blind randomized placebo controlled trial. Critical care medicine,2010,38(1):93-100.
[10] Dobbe, J.G.G., G. Streekstra, B. Atasever, et al. Measurement of functional microcirculatorygeometry and velocity distributions using automated image analysis. Medical and BiologicalEngineering and Computing,2008,46(7):659-670.
[11] De Backer, D., S. Hollenberg, C. Boerma, et al. How to evaluate the microcirculation: report of around table conference. Critical Care,2007,11(5):101-109.
[12]赵爱婷,杨瑞华.雷诺现象患者的区域血流量及微循环变化.微循环学杂志,2006,16(4):48-49.
[13] Cutolo, M., W. Grassi,M. Matucci Cerinic. Raynaud's phenomenon and the role of capillaroscopy.Arthritis&Rheumatism,2003,48(11):3023-3030.
[14]赵征,黄烽,赵秀梅.甲襞微循环在系统性硬化症中的临床意义及特点.军医进修学院学报,2009,30(1):12-14.
[15]吴启富,肖长虹,许文学.类风湿关节炎不同阶段甲襞微循环及血液流变学改变的临床研究.中国微循环,2003,7(4):236-237.
[16]董晓雁,林桂珍.高血压患者微循环改变及血小板聚集性的关系.高血压杂志,1998,6(1):42-45.
[17]胡俊.糖尿病人甲襞微循环分析.微循环学杂志,2006,16(4):71.
[18] Bateman, R., M. Sharpe,C. Ellis. Bench-to-bedside review: microvascular dysfunction insepsis–hemodynamics, oxygen transport, and nitric oxide. Critical Care,2003,7(5):359-373.
[19] Ince, C. The microcirculation is the motor of sepsis. Critical Care London,2005,9(4):13-19.
[20] De Backer, D., J. Creteur, M.J. Dubois, et al. Microvascular alterations in patients with acutesevere heart failure and cardiogenic shock. American heart journal,2004,147(1):91-99.
[21] Grassi, W., P. Core, G. Carlino, et al. Effects of peripheral cold exposure on microvasculardynamics in systemic sclerosis. Arthritis&Rheumatism,1994,37(3):384-390.
[22] Miniati, I., S. Guiducci, M.L. Conforti, et al. Autologous stem cell transplantation improvesmicrocirculation in systemic sclerosis. Annals of the rheumatic diseases,2009,68(1):94.
[23]张北玉,刘惠明.灯盏花素对冠心病患者甲襞微循环及血液流变学的影响.广东医学,2010,31(9):1191-1192.
[24]王宝才,邓翔,范传新.复方川芎胶囊对冠心病心绞痛甲襞微循环的影响.医药导报,2007,26(12):1460-1461.
[25]黄明炜,陶连方,桂程丽.桂蜡膏对老年糖尿病微血管病变患者甲襞微循环及血液流变学的影响.中国微循环,2008,12(1):36-42.
[26] Albayrak, S., S. Ordu, H. Yuksel, et al. Efficacy of nebivolol on flow-mediated dilation in patientswith slow coronary flow. International heart journal,2009,50(5):545-553.
[27] Boerma, E.C., K. Mathura, P. van der Voort, et al. Quantifying bedside-derived imaging ofmicrocirculatory abnormalities in septic patients: a prospective validation study. Critical Care,2005,9(6):601-606.
[28] Rosina, P., M.R. Zamperetti, A. Giovannini, et al. Videocapillaroscopy in the differential diagnosisbetween psoriasis and seborrheic dermatitis of the scalp. Dermatology,2007,214(1):21-24.
[29] Trzeciak, S., R.P. Dellinger, J.E. Parrillo, et al. Early microcirculatory perfusion derangements inpatients with severe sepsis and septic shock: Relationship to hemodynamics, oxygen transport,and survival. Annals of emergency medicine,2007,49(1):88-98.
[30]田牛,微循环方法学1993:原子能出版社.
[31] de Angelis, R., W. Grassi,M. Cutolo. A growing need for capillaroscopy in rheumatology. Arthritis&Rheumatism: Arthritis Care&Research,2009,61(3):405-410.
[32] Cutolo, M., A. Sulli, C. Pizzorni, et al. Capillaroscopy as an Outcome Measure for Clinical Trialson the Peripheral Vasculopathy in SSc—Is It Useful? International Journal of Rheumatology,2010:In Press. doi:10.1155/2010/784947.
[33] Kwasnicka, H.,M. Paradowski. Capillaroscopy Image Analysis as an Automatic Image AnnotationProblem. International Conference on Computer Information Systems and Industrial ManagementApplications.2007,266-271.
[34] Paradowski, M., H. Kwasnicka,K. Borysewicz, Avascular area detection in nailfold capillaryimages, in Proceedings of the International Multiconference on Computer Science andInformation Technology2009, IEEE. p.419-424.
[35] Xu, Y., H. Zhang, H. Li, et al. An improved algorithm for vessel centerline tracking in coronaryangiograms. Computer methods and programs in biomedicine,2007,88(2):131-143.
[36] Aylward, S.R.,E. Bullitt. Initialization, noise, singularities, and scale in height ridge traversal fortubular object centerline extraction. IEEE Transactions on Medical Imaging,2002,21(2):61-75.
[37] Metz, C., M. Schaap, A. Weustink, et al. Coronary centerline extraction from CT coronaryangiography images using a minimum cost path approach. Medical physics,2009,36(12):5568-5579.
[38] Ersahin, K., I.G. Cumming,R.K. Ward. Segmentation of polarimetric SAR data using contourinformation via spectral graph partitioning. Poland,2007,2240-2243.
[39] Hamar, G., G. Horvath, Z. Tarjan, et al. Markov Chain Based Edge Detection Algorithm forEvaluation of Capillary Microscopic Images.11th Mediterranean Conference on Medical andBiomedical Engineering and Computing.2007,16818-821.
[40] Michael, F., S. Uchida,K. Messlinger. Measurement of meningeal blood vessel diameter in vivowith a plug-in for ImageJ. Microvascular research,2010,80(2):258-266.
[41] Shahidi, M., J. Wanek, B. Gaynes, et al. Quantitative assessment of conjunctival microvascularcirculation of the human eye. Microvascular research,2010,79(2):109-113.
[42] Beux, F., S. Carmassi, M.V. Salvetti, et al. Automatic evaluation of arterial diameter variationfrom vascular echographic images. Ultrasound in medicine&biology,2001,27(12):1621-1629.
[43] Davis, M.J. An improved, computer-based method to automatically track internal and externaldiameter of isolated microvessels. Microcirculation,2005,12(4):361-372.
[44] Grisan, E., M. Foracchia,A. Ruggeri. A novel method for the automatic grading of retinal vesseltortuosity. IEEE Transactions on Medical Imaging,2008,27(3):310-319.
[45] Grisan, E., M. Foracchia,A. Ruggeri. A novel method for the automatic evaluation of retinal vesseltortuosity. Proceedings of the25th Annual International Conference.2003,1866-869.
[46] Hart, W.E.,M. Goldbaum. Automated measurement of retinal vascular tortuosity. Proceedings ofthe AMIA Annual Fall Symposium.1997,1459-463.
[47] Jones, B., M. Oral, C. Morris, et al. A proposed taxonomy for nailfold capillaries based on theirmorphology. IEEE Transactions on Medical Imaging,2001,20(4):333-341.
[48] Paradowski, M., H. Kwasnicka,K. Borysewicz. Capillary blood vessel tortuosity measurementusing graph analysis. Knowledge-Based and Intelligent Information and Engineering Systems,2009:135-142.
[49]李光明,田捷,赵明昌.基于Hessian矩阵的中心路径提取算法.软件学报,2003,14(12):2074-2081.
[50]许燕,胡广书,商丽华.基于Hessian矩阵的冠状动脉中心线的跟踪算法.清华大学学报（自然科学版）,2007,47(6):34-36.
[51]吕新荣,高新波,邹华.基于医学影像的血管快速提取与可视化.中国生物医学工程学报,2009,28(004):527-534.
[52]李颖超,刘越,王涌天.基于多尺度Hessian矩阵和Gabor滤波的造影图像冠脉中心线提取.中国医学影像技术,2007,23(1):133-136.
[53]江贵平,周寿军.利用模糊识别算法分析冠状动脉造影图像中的血管结构.计算机学报,2008,31(1):170-175.
[54]陆建荣,斯海臣,郁道银.冠状动脉血管直径测量方法的研究.中国生物医学工程学报,2005,24(4):510-512.
[55]姚畅,陈后金.一种基于先验知识的视网膜血管宽度测量方法.中国科技论文在线,2009,4(1):64-68.
[56]陆荣生,易红,倪中华.基于弹性小球动态平衡的血管中心线和直径的测量.中国生物医学工程学报,2009,28(5):668-673.
[57] Bollinger, A., P. Butti, J.P. Barras, et al. Red blood cell velocity in nailfold capillaries of manmeasured by a television microscopy technique. Microvascular research,1974,7(1):61-72.
[58] Watanabe, M., M. Matsubara, T. Sanada, et al. High Speed Digital Video Capillaroscopy: NailfoldCapillary Shape Analysis and Red Blood Cell Velocity Measurement. Journal of BiomechanicalScience and Engineering,2007,2(2):81-92.
[59] Mawson, D.,A. Shore. Comparison of CapiFlow and frame by frame analysis for the assessmentof capillary red blood cell velocity. Journal of medical engineering&technology,1998,22(2):53-63.
[60] Tsukada, K., H. Minamitani, E. Sekizuka, et al. Image correlation method for measuring bloodflow velocity in microcirculation: correlation window's imulation and in vivo image analysis.Physiological measurement,2000,21(4):459-471.
[61] Lee, J.Y., H.S. Ji,S.J. Lee. Micro-PIV measurements of blood flow in extraembryonic bloodvessels of chicken embryos. Physiological measurement,2007,28(10):1149-1162.
[62] Wu, C.C., G. Zhang, T.C. Huang, et al. Red blood cell velocity measurements of completecapillary in finger nail-fold using optical flow estimation. Microvascular research,2009,78(3):319-324.
[63] Wu, C.C., W.C. Lin, G. Zhang, et al. Accuracy evaluation of RBC velocity measurement innail-fold capillaries. Microvascular research,2011,81(3):252-260.
[64] Huang, T.C., W.C. Lin, G. Zhang, et al. Experimental estimation of blood flow velocity throughsimulation of intravital microscopic imaging in micro-vessels by different image processingmethods. Microvascular research,2010,80(3):477-483.
[65] Horn, B.K.P.,B.G. Schunck. Determining optical flow. Artificial intelligence,1981,17(1-3):185-203.
[66] Mukherjee, D.P., N. Ray,S.T. Acton. Level set analysis for leukocyte detection and tracking. IEEETransactions on Image Processing,2004,13(4):562-572.
[67] Watanabe, M., Y. Senga, T. Shiga, et al. The time-space correlation method for measurement oferythrocyte velocity in microvessels using a CCD linear image sensor. Microvascular research,1991,41(1):41-46.
[68] Ellis, C.G., M.L. Ellsworth, R.N. Pittman, et al. Application of image analysis for evaluation ofred blood cell dynamics in capillaries. Microvascular research,1992,44(2):214-225.
[69] Sato, Y., J. Chen, S. Yamamoto, et al. Measuring microcirculation using spatiotemporal imageanalysis. Lecture Notes in Computer Science.1995,302-308.
[70] Yamamoto, S., Y. Nakajima, S. Tamura, et al. Extraction of fluorescent dot traces from a scanninglaser ophthalmoscope image sequence by spatio-temporal image analysis: Gabor filter and radontransform filtering. IEEE Transactions on Biomedical Engineering,1999,46(11):1357-1363.
[71] Wang, C.,Z. Zhang. Velocity measurement in microcirculation: An estimation-theoretic methodfrom microcirculatory temporospatial image. The23th Annual EMBS International Conference.2001,32574-2576.
[72] Kempczynski, A.,B. Grzegorzewski. Estimation of red blood cell aggregate velocity duringsedimentation using the Hough transform. Optics Communications,2008,281(21):5487-5491.
[73] Chaigneau, E., M. Oheim, E. Audinat, et al. Two-photon imaging of capillary blood flow inolfactory bulb glomeruli. Proceedings of the National Academy of Sciences,2003,100(22):13081.
[74] Schaffer, C.B., B. Friedman, N. Nishimura, et al. Two-photon imaging of cortical surfacemicrovessels reveals a robust redistribution in blood flow after vascular occlusion. PLoS biology,2006,4(2):258-270.
[75] Kleinfeld, D., P.P. Mitra, F. Helmchen, et al. Fluctuations and stimulus-induced changes in bloodflow observed in individual capillaries in layers2through4of rat neocortex. Proceedings of theNational Academy of Sciences,1998,95(26):15741-15746.
[76] Sourice, A., G. Plantier,J.L. Saumet. Red blood cell velocity estimation in microvessels using thespatiotemporal autocorrelation. Measurement Science and Technology,2005,16(11):2229-2240.
[77] Drew, P.J., P. Blinder,G. Cauwenberghs. Rapid determination of particle velocity from space-timeimages using the Radon transform. Journal of Computational Neuroscience,2010,29(1):5-11.
[78] Marion, A.,D. Vray. Spatiotemporal filtering of sequences of ultrasound images to estimate adense field of velocities. Pattern Recognition,2009,42(11):2989-2997.
[79] Japee, S.A., R.N. Pittman,C.G. Ellis. Automated method for tracking individual red blood cellswithin capillaries to compute velocity and oxygen saturation. Microcirculation,2005,12(6):507-515.
[80] Japee, S.A., R.N. Pittman,C.G. Ellis. A new video image analysis system to study red blood celldynamics and oxygenation in capillary networks. Microcirculation,2005,12(6):489-506.
[81] Sato, Y., J. Chen, R.A. Zoroofi, et al. Automatic extraction and measurement of leukocyte motionin microvessels using spatiotemporal image analysis. IEEE Transactions on BiomedicalEngineering,1997,44(4):225-236.
[82] Ray, N.,S.T. Acton. Data acceptance for automated leukocyte tracking through segmentation ofspatiotemporal images. IEEE Transactions on Biomedical Engineering,2005,52(10):1702-1712.
[83]沈国键,李瑛.甲襞微循环定量分析系统.武汉测绘科技大学学报,1996,21(4):371-374.
[84]廖永宁,项世法.微机数字图像处理系统用于甲襞微循环流速的测量.光电工程,1990,17(3):1-7.
[85]文伟宁,周兆英.微循环流速测量技术的发展与临床应用简况.北京生物医学工程,1995,14(2):116-120.
[86]沈兵,刁越,曾衍钧.微循环血液流速测量的研究.中国生物医学工程学报,2005,24(6):717-722.
[87]彭明飞,张志广.微循环血流的二维运动分析.微循环学杂志,2000,10(4):9-11.
[88]闫家青,潘燕,李桥. Labview在微循环流速测量中的应用.实验室研究与探索,2008,27(2):16-19.
[89] LeRoy, E.C.,T.A. Medsger. Criteria for the classification of early systemic sclerosis. The Journalof rheumatology,2001,28(7):1573.
[90] Ferri, C., G. Valentini, F. Cozzi, et al. Systemic sclerosis: demographic, clinical, and serologicfeatures and survival in1,012Italian patients. Medicine,2002,81(2):139.
[91] Wen, C.H., W.D. Liao,K.C. Li. Classification framework for nailfold capillary microscopy images.IEEE Region10Conference Taipei,2007,1-4.
[92] Paradowski, M., U. Markowska-Kaczmar, H. Kwasnicka, et al. Capillary Abnormalities DetectionUsing Vessel Thickness and Curvature Analysis. Knowledge-Based and Intelligent Informationand Engineering Systems,2009:151-158.
[93] Allen, P., C. Taylor, A. Herrick, et al. Image Analysis of Nail Fold Capillary Patterns. MedicalImage Understanding and Analysis,Lecture Notes in Computer Science.1998,698-705.
[94] Allen, P., V. Hillier, T. Moore, et al. Computer based system for acquisition and analysis ofnailfold capillary images. Medical Image Understanding and Analysis.2003,149-152.
[95] Li, K.C., C.N. Chen, C.H. Wen, et al. Nailfold Capillary Microscopy High-Resolution ImageAnalysis Framework for Connective Tissue Disease Diagnosis Using Grid Computing Technology.Computational Science and Its Applications-ICCSA2006,2006:1107-1115.
[96] Wen, C.H., T.Y. Hsieh, W.D. Liao, et al. A novel method for classification of high-resolutionnailfold capillary microscopy images. Ubi-Media Computing, IEEE. LanZhou,2008,513-518.
[97] Zimmerman, J.B., S.M. Pizer, E.V. Staab, et al. An evaluation of the effectiveness of adaptivehistogram equalization for contrast enhancement. IEEE Transactions on Medical Imaging,1988,7(4):304-312.
[98]杨词银,尚海波,贾晨光.基于区域分割的自适应反锐化掩模算法.光学精密工程,2003,11(2):188-192.
[99]刘敬,刘衍聪,闫成新.局部归一化的人脸光照处理方法.郑州大学学报,2008,40(3):98-101.
[100] Jung, C.R.,J. Scharcanski. Wavelet transform approach to adaptive image denoising andenhancement. Journal of Electronic Imaging,2004,13(2):278-285.
[101] Feng, P., Y. Pan, B. Wei, et al. Enhancing retinal image by the Contourlet transform. Patternrecognition letters,2007,28(4):516-522.
[102] Mallat, S.G. A theory for multiresolution signal decomposition: The wavelet representation. IEEETransactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693.
[103] Do, M.N.,M. Vetterli. The contourlet transform: an efficient directional multiresolution imagerepresentation. IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[104] Yuan, C., Z. Zhi-min, L. Lei, et al. A New Method for Human Microcirculation ImageEnhancement. Chinese Journal of Biomedical Engineering,2008,17(4):219-233.
[105] Po, D.D.Y.,M.N. Do. Directional multiscale modeling of images using the contourlet transform.IEEE Transactions on Image Processing,2006,15(6):1610-1620.
[106] Laine, A., J. Fan,W. Yang. Wavelets for contrast enhancement of digital mammography.Engineering in Medicine and Biology Magazine, IEEE,1995,14(5):536-550.
[107] Lu, Z., T. Jiang, G. Hu, et al. Contourlet based mammographic image enhancement. FifthInternational Conference on Photonics and Imaging in Biology and Medicine. Wuhan,2007,65341-8.
[108] Bezemer, R., J.G. Dobbe, S.A. Bartels, et al. Rapid automatic assessment of microvascular densityin sidestream dark field images. Medical and Biological Engineering and Computering,2011,49(11):1269-1278.
[109]陈远,赵志敏,郑敏.人体微小管状血管血液流速自动测量方法研究.计量学报,2010,31(2):123-126.
[110] Bezemer, R., J.G. Dobbe, S.A. Bartels, et al. Rapid automatic assessment of microvascular densityin sidestream dark field images. Medical and Biological Engineering and Computing,2011,49(11):1-10.
[111] Chen, Y.,et al. Automatic tracking and measurement of the motion of blood cells in microvesselsbased on analysis of multiple spatiotemporal images. Measurement Science and Technology,2011,22(4):045803doi:10.1088/0957-0233/22/4/045803.
[112] Frangi, A., W. Niessen, K. Vincken, et al. Multiscale vessel enhancement filtering. Medical ImageComputing and Computer Assisted Interventation-MICCAI98,1998,1496:130-137.
[113] Jacob, M.,M. Unser. Design of steerable filters for feature detection using canny-like criteria.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1007-1019.
[114] Sofka, M.,C.V. Stewart. Retinal vessel centerline extraction using multiscale matched filters,confidence and edge measures. IEEE Transactions on Medical Imaging,2006,25(12):1531-1546.
[115] Bouaynaya, N.,S. Member. Spatially Variant Morphological Restoration and SkeletonRepresentation. IEEE Transactions On Image Processing,2006,15(11):3579-3591.
[116]陈远,赵志敏,刘磊.基于ST图的微循环血细胞自动跟踪与测量技术研究.东南大学学报,2011,41(1):72-76.
[117] Cover, T.,P. Hart. Nearest neighbor pattern classification. IEEE Transactions on InformationTheory,1967,13(1):21-27.
[118] Dudani, S.A. The distance-weighted k-nearest-neighbor rule. IEEE Transactions on Systems, Manand Cybernetics,1976,(4):325-327.
[119] Zhang, Y., X. Ding, Y. Liu, et al. An artificial neural network approach to transformer faultdiagnosis. IEEE Transactions on Power Delivery,1996,11(4):1836-1841.
[120]陆丽.基于人脸图像的性别识别与年龄估计研究,[博士学位论文].上海:上海交通大学,2010.
[121] Suykens, J.A.K.,J. Vandewalle. Least squares support vector machine classifiers. Neuralprocessing letters,1999,9(3):293-300.
[122]刘立波.基于图像的水稻叶部病害诊断技术研究,[博士学位论文].北京:中国农业科学院,2010.
[123]刘志刚,李德仁,秦前清.支持向量机在多类分类问题中的推广.计算机工程与应用,2004,4(7):10-13.
[2]吕瑞林,吴伯瑜.皮肤微循环检测方法及其新进展.医学综述,2003,12(2):124-128.
[3]陈蕾,章恩耀,王佳.皮肤微循环无损伤光学成像技术的新进展.光学技术,2003,29(6):690-692.
[4] Leahy, M.J., J.G. Enfield, N.T. Clancy, et al. Biophotonic methods in microcirculation imaging.Medical Laser Application,2007,22(2):105-126.
[5] Awan, Z., T. Wester,K. Kvernebo. Human microvascular imaging: a review of skin and tonguevideomicroscopy techniques and analysing variables. Clinical physiology and functional imaging,2010,30(2):79-88.
[6] Goedhart, P., M. Khalilzada, R. Bezemer, et al. Sidestream Dark Field (SDF) imaging: a novelstroboscopic LED ring-based imaging modality for clinical assessment of the microcirculation.Optics express,2007,15(23):15101-15114.
[7]许谦,雷俊锋,曾立波.正交偏振多光谱成像术应用于活体微循环观察研究.光谱学与光谱分析,2010,30(7):1886-1889.
[8] Martin, D.S., C. Ince, P. Goedhart, et al. Abnormal blood flow in the sublingual microcirculationat high altitude. European journal of applied physiology,2009,106(3):473-478.
[9] Boerma, E.C., M. Koopmans, A. Konijn, et al. Effects of nitroglycerin on sublingualmicrocirculatory blood flow in patients with severe sepsis/septic shock after a strict resuscitationprotocol: a double-blind randomized placebo controlled trial. Critical care medicine,2010,38(1):93-100.
[10] Dobbe, J.G.G., G. Streekstra, B. Atasever, et al. Measurement of functional microcirculatorygeometry and velocity distributions using automated image analysis. Medical and BiologicalEngineering and Computing,2008,46(7):659-670.
[11] De Backer, D., S. Hollenberg, C. Boerma, et al. How to evaluate the microcirculation: report of around table conference. Critical Care,2007,11(5):101-109.
[12]赵爱婷,杨瑞华.雷诺现象患者的区域血流量及微循环变化.微循环学杂志,2006,16(4):48-49.
[13] Cutolo, M., W. Grassi,M. Matucci Cerinic. Raynaud's phenomenon and the role of capillaroscopy.Arthritis&Rheumatism,2003,48(11):3023-3030.
[14]赵征,黄烽,赵秀梅.甲襞微循环在系统性硬化症中的临床意义及特点.军医进修学院学报,2009,30(1):12-14.
[15]吴启富,肖长虹,许文学.类风湿关节炎不同阶段甲襞微循环及血液流变学改变的临床研究.中国微循环,2003,7(4):236-237.
[16]董晓雁,林桂珍.高血压患者微循环改变及血小板聚集性的关系.高血压杂志,1998,6(1):42-45.
[17]胡俊.糖尿病人甲襞微循环分析.微循环学杂志,2006,16(4):71.
[18] Bateman, R., M. Sharpe,C. Ellis. Bench-to-bedside review: microvascular dysfunction insepsis–hemodynamics, oxygen transport, and nitric oxide. Critical Care,2003,7(5):359-373.
[19] Ince, C. The microcirculation is the motor of sepsis. Critical Care London,2005,9(4):13-19.
[20] De Backer, D., J. Creteur, M.J. Dubois, et al. Microvascular alterations in patients with acutesevere heart failure and cardiogenic shock. American heart journal,2004,147(1):91-99.
[21] Grassi, W., P. Core, G. Carlino, et al. Effects of peripheral cold exposure on microvasculardynamics in systemic sclerosis. Arthritis&Rheumatism,1994,37(3):384-390.
[22] Miniati, I., S. Guiducci, M.L. Conforti, et al. Autologous stem cell transplantation improvesmicrocirculation in systemic sclerosis. Annals of the rheumatic diseases,2009,68(1):94.
[23]张北玉,刘惠明.灯盏花素对冠心病患者甲襞微循环及血液流变学的影响.广东医学,2010,31(9):1191-1192.
[24]王宝才,邓翔,范传新.复方川芎胶囊对冠心病心绞痛甲襞微循环的影响.医药导报,2007,26(12):1460-1461.
[25]黄明炜,陶连方,桂程丽.桂蜡膏对老年糖尿病微血管病变患者甲襞微循环及血液流变学的影响.中国微循环,2008,12(1):36-42.
[26] Albayrak, S., S. Ordu, H. Yuksel, et al. Efficacy of nebivolol on flow-mediated dilation in patientswith slow coronary flow. International heart journal,2009,50(5):545-553.
[27] Boerma, E.C., K. Mathura, P. van der Voort, et al. Quantifying bedside-derived imaging ofmicrocirculatory abnormalities in septic patients: a prospective validation study. Critical Care,2005,9(6):601-606.
[28] Rosina, P., M.R. Zamperetti, A. Giovannini, et al. Videocapillaroscopy in the differential diagnosisbetween psoriasis and seborrheic dermatitis of the scalp. Dermatology,2007,214(1):21-24.
[29] Trzeciak, S., R.P. Dellinger, J.E. Parrillo, et al. Early microcirculatory perfusion derangements inpatients with severe sepsis and septic shock: Relationship to hemodynamics, oxygen transport,and survival. Annals of emergency medicine,2007,49(1):88-98.
[30]田牛,微循环方法学1993:原子能出版社.
[31] de Angelis, R., W. Grassi,M. Cutolo. A growing need for capillaroscopy in rheumatology. Arthritis&Rheumatism: Arthritis Care&Research,2009,61(3):405-410.
[32] Cutolo, M., A. Sulli, C. Pizzorni, et al. Capillaroscopy as an Outcome Measure for Clinical Trialson the Peripheral Vasculopathy in SSc—Is It Useful? International Journal of Rheumatology,2010:In Press. doi:10.1155/2010/784947.
[33] Kwasnicka, H.,M. Paradowski. Capillaroscopy Image Analysis as an Automatic Image AnnotationProblem. International Conference on Computer Information Systems and Industrial ManagementApplications.2007,266-271.
[34] Paradowski, M., H. Kwasnicka,K. Borysewicz, Avascular area detection in nailfold capillaryimages, in Proceedings of the International Multiconference on Computer Science andInformation Technology2009, IEEE. p.419-424.
[35] Xu, Y., H. Zhang, H. Li, et al. An improved algorithm for vessel centerline tracking in coronaryangiograms. Computer methods and programs in biomedicine,2007,88(2):131-143.
[36] Aylward, S.R.,E. Bullitt. Initialization, noise, singularities, and scale in height ridge traversal fortubular object centerline extraction. IEEE Transactions on Medical Imaging,2002,21(2):61-75.
[37] Metz, C., M. Schaap, A. Weustink, et al. Coronary centerline extraction from CT coronaryangiography images using a minimum cost path approach. Medical physics,2009,36(12):5568-5579.
[38] Ersahin, K., I.G. Cumming,R.K. Ward. Segmentation of polarimetric SAR data using contourinformation via spectral graph partitioning. Poland,2007,2240-2243.
[39] Hamar, G., G. Horvath, Z. Tarjan, et al. Markov Chain Based Edge Detection Algorithm forEvaluation of Capillary Microscopic Images.11th Mediterranean Conference on Medical andBiomedical Engineering and Computing.2007,16818-821.
[40] Michael, F., S. Uchida,K. Messlinger. Measurement of meningeal blood vessel diameter in vivowith a plug-in for ImageJ. Microvascular research,2010,80(2):258-266.
[41] Shahidi, M., J. Wanek, B. Gaynes, et al. Quantitative assessment of conjunctival microvascularcirculation of the human eye. Microvascular research,2010,79(2):109-113.
[42] Beux, F., S. Carmassi, M.V. Salvetti, et al. Automatic evaluation of arterial diameter variationfrom vascular echographic images. Ultrasound in medicine&biology,2001,27(12):1621-1629.
[43] Davis, M.J. An improved, computer-based method to automatically track internal and externaldiameter of isolated microvessels. Microcirculation,2005,12(4):361-372.
[44] Grisan, E., M. Foracchia,A. Ruggeri. A novel method for the automatic grading of retinal vesseltortuosity. IEEE Transactions on Medical Imaging,2008,27(3):310-319.
[45] Grisan, E., M. Foracchia,A. Ruggeri. A novel method for the automatic evaluation of retinal vesseltortuosity. Proceedings of the25th Annual International Conference.2003,1866-869.
[46] Hart, W.E.,M. Goldbaum. Automated measurement of retinal vascular tortuosity. Proceedings ofthe AMIA Annual Fall Symposium.1997,1459-463.
[47] Jones, B., M. Oral, C. Morris, et al. A proposed taxonomy for nailfold capillaries based on theirmorphology. IEEE Transactions on Medical Imaging,2001,20(4):333-341.
[48] Paradowski, M., H. Kwasnicka,K. Borysewicz. Capillary blood vessel tortuosity measurementusing graph analysis. Knowledge-Based and Intelligent Information and Engineering Systems,2009:135-142.
[49]李光明,田捷,赵明昌.基于Hessian矩阵的中心路径提取算法.软件学报,2003,14(12):2074-2081.
[50]许燕,胡广书,商丽华.基于Hessian矩阵的冠状动脉中心线的跟踪算法.清华大学学报（自然科学版）,2007,47(6):34-36.
[51]吕新荣,高新波,邹华.基于医学影像的血管快速提取与可视化.中国生物医学工程学报,2009,28(004):527-534.
[52]李颖超,刘越,王涌天.基于多尺度Hessian矩阵和Gabor滤波的造影图像冠脉中心线提取.中国医学影像技术,2007,23(1):133-136.
[53]江贵平,周寿军.利用模糊识别算法分析冠状动脉造影图像中的血管结构.计算机学报,2008,31(1):170-175.
[54]陆建荣,斯海臣,郁道银.冠状动脉血管直径测量方法的研究.中国生物医学工程学报,2005,24(4):510-512.
[55]姚畅,陈后金.一种基于先验知识的视网膜血管宽度测量方法.中国科技论文在线,2009,4(1):64-68.
[56]陆荣生,易红,倪中华.基于弹性小球动态平衡的血管中心线和直径的测量.中国生物医学工程学报,2009,28(5):668-673.
[57] Bollinger, A., P. Butti, J.P. Barras, et al. Red blood cell velocity in nailfold capillaries of manmeasured by a television microscopy technique. Microvascular research,1974,7(1):61-72.
[58] Watanabe, M., M. Matsubara, T. Sanada, et al. High Speed Digital Video Capillaroscopy: NailfoldCapillary Shape Analysis and Red Blood Cell Velocity Measurement. Journal of BiomechanicalScience and Engineering,2007,2(2):81-92.
[59] Mawson, D.,A. Shore. Comparison of CapiFlow and frame by frame analysis for the assessmentof capillary red blood cell velocity. Journal of medical engineering&technology,1998,22(2):53-63.
[60] Tsukada, K., H. Minamitani, E. Sekizuka, et al. Image correlation method for measuring bloodflow velocity in microcirculation: correlation window's imulation and in vivo image analysis.Physiological measurement,2000,21(4):459-471.
[61] Lee, J.Y., H.S. Ji,S.J. Lee. Micro-PIV measurements of blood flow in extraembryonic bloodvessels of chicken embryos. Physiological measurement,2007,28(10):1149-1162.
[62] Wu, C.C., G. Zhang, T.C. Huang, et al. Red blood cell velocity measurements of completecapillary in finger nail-fold using optical flow estimation. Microvascular research,2009,78(3):319-324.
[63] Wu, C.C., W.C. Lin, G. Zhang, et al. Accuracy evaluation of RBC velocity measurement innail-fold capillaries. Microvascular research,2011,81(3):252-260.
[64] Huang, T.C., W.C. Lin, G. Zhang, et al. Experimental estimation of blood flow velocity throughsimulation of intravital microscopic imaging in micro-vessels by different image processingmethods. Microvascular research,2010,80(3):477-483.
[65] Horn, B.K.P.,B.G. Schunck. Determining optical flow. Artificial intelligence,1981,17(1-3):185-203.
[66] Mukherjee, D.P., N. Ray,S.T. Acton. Level set analysis for leukocyte detection and tracking. IEEETransactions on Image Processing,2004,13(4):562-572.
[67] Watanabe, M., Y. Senga, T. Shiga, et al. The time-space correlation method for measurement oferythrocyte velocity in microvessels using a CCD linear image sensor. Microvascular research,1991,41(1):41-46.
[68] Ellis, C.G., M.L. Ellsworth, R.N. Pittman, et al. Application of image analysis for evaluation ofred blood cell dynamics in capillaries. Microvascular research,1992,44(2):214-225.
[69] Sato, Y., J. Chen, S. Yamamoto, et al. Measuring microcirculation using spatiotemporal imageanalysis. Lecture Notes in Computer Science.1995,302-308.
[70] Yamamoto, S., Y. Nakajima, S. Tamura, et al. Extraction of fluorescent dot traces from a scanninglaser ophthalmoscope image sequence by spatio-temporal image analysis: Gabor filter and radontransform filtering. IEEE Transactions on Biomedical Engineering,1999,46(11):1357-1363.
[71] Wang, C.,Z. Zhang. Velocity measurement in microcirculation: An estimation-theoretic methodfrom microcirculatory temporospatial image. The23th Annual EMBS International Conference.2001,32574-2576.
[72] Kempczynski, A.,B. Grzegorzewski. Estimation of red blood cell aggregate velocity duringsedimentation using the Hough transform. Optics Communications,2008,281(21):5487-5491.
[73] Chaigneau, E., M. Oheim, E. Audinat, et al. Two-photon imaging of capillary blood flow inolfactory bulb glomeruli. Proceedings of the National Academy of Sciences,2003,100(22):13081.
[74] Schaffer, C.B., B. Friedman, N. Nishimura, et al. Two-photon imaging of cortical surfacemicrovessels reveals a robust redistribution in blood flow after vascular occlusion. PLoS biology,2006,4(2):258-270.
[75] Kleinfeld, D., P.P. Mitra, F. Helmchen, et al. Fluctuations and stimulus-induced changes in bloodflow observed in individual capillaries in layers2through4of rat neocortex. Proceedings of theNational Academy of Sciences,1998,95(26):15741-15746.
[76] Sourice, A., G. Plantier,J.L. Saumet. Red blood cell velocity estimation in microvessels using thespatiotemporal autocorrelation. Measurement Science and Technology,2005,16(11):2229-2240.
[77] Drew, P.J., P. Blinder,G. Cauwenberghs. Rapid determination of particle velocity from space-timeimages using the Radon transform. Journal of Computational Neuroscience,2010,29(1):5-11.
[78] Marion, A.,D. Vray. Spatiotemporal filtering of sequences of ultrasound images to estimate adense field of velocities. Pattern Recognition,2009,42(11):2989-2997.
[79] Japee, S.A., R.N. Pittman,C.G. Ellis. Automated method for tracking individual red blood cellswithin capillaries to compute velocity and oxygen saturation. Microcirculation,2005,12(6):507-515.
[80] Japee, S.A., R.N. Pittman,C.G. Ellis. A new video image analysis system to study red blood celldynamics and oxygenation in capillary networks. Microcirculation,2005,12(6):489-506.
[81] Sato, Y., J. Chen, R.A. Zoroofi, et al. Automatic extraction and measurement of leukocyte motionin microvessels using spatiotemporal image analysis. IEEE Transactions on BiomedicalEngineering,1997,44(4):225-236.
[82] Ray, N.,S.T. Acton. Data acceptance for automated leukocyte tracking through segmentation ofspatiotemporal images. IEEE Transactions on Biomedical Engineering,2005,52(10):1702-1712.
[83]沈国键,李瑛.甲襞微循环定量分析系统.武汉测绘科技大学学报,1996,21(4):371-374.
[84]廖永宁,项世法.微机数字图像处理系统用于甲襞微循环流速的测量.光电工程,1990,17(3):1-7.
[85]文伟宁,周兆英.微循环流速测量技术的发展与临床应用简况.北京生物医学工程,1995,14(2):116-120.
[86]沈兵,刁越,曾衍钧.微循环血液流速测量的研究.中国生物医学工程学报,2005,24(6):717-722.
[87]彭明飞,张志广.微循环血流的二维运动分析.微循环学杂志,2000,10(4):9-11.
[88]闫家青,潘燕,李桥. Labview在微循环流速测量中的应用.实验室研究与探索,2008,27(2):16-19.
[89] LeRoy, E.C.,T.A. Medsger. Criteria for the classification of early systemic sclerosis. The Journalof rheumatology,2001,28(7):1573.
[90] Ferri, C., G. Valentini, F. Cozzi, et al. Systemic sclerosis: demographic, clinical, and serologicfeatures and survival in1,012Italian patients. Medicine,2002,81(2):139.
[91] Wen, C.H., W.D. Liao,K.C. Li. Classification framework for nailfold capillary microscopy images.IEEE Region10Conference Taipei,2007,1-4.
[92] Paradowski, M., U. Markowska-Kaczmar, H. Kwasnicka, et al. Capillary Abnormalities DetectionUsing Vessel Thickness and Curvature Analysis. Knowledge-Based and Intelligent Informationand Engineering Systems,2009:151-158.
[93] Allen, P., C. Taylor, A. Herrick, et al. Image Analysis of Nail Fold Capillary Patterns. MedicalImage Understanding and Analysis,Lecture Notes in Computer Science.1998,698-705.
[94] Allen, P., V. Hillier, T. Moore, et al. Computer based system for acquisition and analysis ofnailfold capillary images. Medical Image Understanding and Analysis.2003,149-152.
[95] Li, K.C., C.N. Chen, C.H. Wen, et al. Nailfold Capillary Microscopy High-Resolution ImageAnalysis Framework for Connective Tissue Disease Diagnosis Using Grid Computing Technology.Computational Science and Its Applications-ICCSA2006,2006:1107-1115.
[96] Wen, C.H., T.Y. Hsieh, W.D. Liao, et al. A novel method for classification of high-resolutionnailfold capillary microscopy images. Ubi-Media Computing, IEEE. LanZhou,2008,513-518.
[97] Zimmerman, J.B., S.M. Pizer, E.V. Staab, et al. An evaluation of the effectiveness of adaptivehistogram equalization for contrast enhancement. IEEE Transactions on Medical Imaging,1988,7(4):304-312.
[98]杨词银,尚海波,贾晨光.基于区域分割的自适应反锐化掩模算法.光学精密工程,2003,11(2):188-192.
[99]刘敬,刘衍聪,闫成新.局部归一化的人脸光照处理方法.郑州大学学报,2008,40(3):98-101.
[100] Jung, C.R.,J. Scharcanski. Wavelet transform approach to adaptive image denoising andenhancement. Journal of Electronic Imaging,2004,13(2):278-285.
[101] Feng, P., Y. Pan, B. Wei, et al. Enhancing retinal image by the Contourlet transform. Patternrecognition letters,2007,28(4):516-522.
[102] Mallat, S.G. A theory for multiresolution signal decomposition: The wavelet representation. IEEETransactions on Pattern Analysis and Machine Intelligence,1989,11(7):674-693.
[103] Do, M.N.,M. Vetterli. The contourlet transform: an efficient directional multiresolution imagerepresentation. IEEE Transactions on Image Processing,2005,14(12):2091-2106.
[104] Yuan, C., Z. Zhi-min, L. Lei, et al. A New Method for Human Microcirculation ImageEnhancement. Chinese Journal of Biomedical Engineering,2008,17(4):219-233.
[105] Po, D.D.Y.,M.N. Do. Directional multiscale modeling of images using the contourlet transform.IEEE Transactions on Image Processing,2006,15(6):1610-1620.
[106] Laine, A., J. Fan,W. Yang. Wavelets for contrast enhancement of digital mammography.Engineering in Medicine and Biology Magazine, IEEE,1995,14(5):536-550.
[107] Lu, Z., T. Jiang, G. Hu, et al. Contourlet based mammographic image enhancement. FifthInternational Conference on Photonics and Imaging in Biology and Medicine. Wuhan,2007,65341-8.
[108] Bezemer, R., J.G. Dobbe, S.A. Bartels, et al. Rapid automatic assessment of microvascular densityin sidestream dark field images. Medical and Biological Engineering and Computering,2011,49(11):1269-1278.
[109]陈远,赵志敏,郑敏.人体微小管状血管血液流速自动测量方法研究.计量学报,2010,31(2):123-126.
[110] Bezemer, R., J.G. Dobbe, S.A. Bartels, et al. Rapid automatic assessment of microvascular densityin sidestream dark field images. Medical and Biological Engineering and Computing,2011,49(11):1-10.
[111] Chen, Y.,et al. Automatic tracking and measurement of the motion of blood cells in microvesselsbased on analysis of multiple spatiotemporal images. Measurement Science and Technology,2011,22(4):045803doi:10.1088/0957-0233/22/4/045803.
[112] Frangi, A., W. Niessen, K. Vincken, et al. Multiscale vessel enhancement filtering. Medical ImageComputing and Computer Assisted Interventation-MICCAI98,1998,1496:130-137.
[113] Jacob, M.,M. Unser. Design of steerable filters for feature detection using canny-like criteria.IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1007-1019.
[114] Sofka, M.,C.V. Stewart. Retinal vessel centerline extraction using multiscale matched filters,confidence and edge measures. IEEE Transactions on Medical Imaging,2006,25(12):1531-1546.
[115] Bouaynaya, N.,S. Member. Spatially Variant Morphological Restoration and SkeletonRepresentation. IEEE Transactions On Image Processing,2006,15(11):3579-3591.
[116]陈远,赵志敏,刘磊.基于ST图的微循环血细胞自动跟踪与测量技术研究.东南大学学报,2011,41(1):72-76.
[117] Cover, T.,P. Hart. Nearest neighbor pattern classification. IEEE Transactions on InformationTheory,1967,13(1):21-27.
[118] Dudani, S.A. The distance-weighted k-nearest-neighbor rule. IEEE Transactions on Systems, Manand Cybernetics,1976,(4):325-327.
[119] Zhang, Y., X. Ding, Y. Liu, et al. An artificial neural network approach to transformer faultdiagnosis. IEEE Transactions on Power Delivery,1996,11(4):1836-1841.
[120]陆丽.基于人脸图像的性别识别与年龄估计研究,[博士学位论文].上海:上海交通大学,2010.
[121] Suykens, J.A.K.,J. Vandewalle. Least squares support vector machine classifiers. Neuralprocessing letters,1999,9(3):293-300.
[122]刘立波.基于图像的水稻叶部病害诊断技术研究,[博士学位论文].北京:中国农业科学院,2010.
[123]刘志刚,李德仁,秦前清.支持向量机在多类分类问题中的推广.计算机工程与应用,2004,4(7):10-13.