妇产科早期诊断中超声图像的分析与处理研究
|
摘要
超声诊断是目前最重要的医学影像诊断方式之一,具有无损、实时、非侵入式等特点,在妇产科诊断中得到了广泛应用。妇产科超声诊断能有效检测母体和胎儿的生理健康,是提高诊断准确率与客观性的重要手段。妇产科超声诊断现阶段的一个研究热点是针对疾病早期的检测,它能有利于进一步的医学处理,但同时又增大了诊断的难度。目前临床超声诊断主要存在对医生经验依赖性高、检测过多人工操作以及信息处理相对困难等问题,这对临床诊断中超声图像自动分析、处理的研究提出了要求。
由于超声成像过程中回波间存在相互干扰,形成的斑点噪声影响了进一步图像分析、处理算法的性能,因此斑点噪声的处理以及目标模型的建立是超声图像分析、处理研究必须要考虑的两个基本问题。
本论文针对妇产科早期诊断中的三个热点问题,以计算机辅助诊断为目标,对超声图像的分析、处理方法进行研究。
针对多囊卵巢内小囊胞的检测问题,提出自适应形态滤波的斑点噪声去除方法,该方法能对斑点噪声在图像上表现出的像素值突变进行有效抑制：提出改进的带标记分水岭算法,分割出候选的小囊胞,并提出基于剩余谱估计的感兴趣区域自动选取算法；进一步提出目标生长算法,实现了对卵巢内小囊胞的自动识别。实验表明该方法的识别率和误识率分别为89.4%和7.45%,与其他方法的比较验证了该方法的优越性。
针对胎儿早期心脏结构的检测问题,提出基于运动累加图的感兴趣区域自动选取方法,该方法能在超声图像序列信噪比较低的条件下对胎儿心脏区域进行准确提取；针对早期胎心图像的低信噪比以及检测时对运动信息的需要,提出瑞利均值各向异性扩散方法；为准确检测早期胎儿心脏结构,进一步提出能同时考虑胎儿心脏结构与运动信息的活动心脏模型,通过优化模型的结构保证了推断过程的收敛性。在胎儿早期心脏结构检测的实验中,90%的检测结果其误差小于13个像素。
针对颈项透明层的自动识别问题,提出一个具有三层结构的分层模型。该模型针对颈项透明层检测的具体需要,采用基于梯度方向直方图特征的支撑向量机来表征图像上的相关目标,并建立相应的空间模型来描述不同目标间的相互关联,通过动态规划以及广义距离变换对模型的全局最优解进行求解。实验结果表明,该模型对颈项透明层的自动识别可以达到约60%的准确率。
Ultrasound diagnosis is one of the most important diagnostic imaging techniques, which has been widely applied in the diagnosis of gynecology and obstetrics due to its merits of harmlessness, real-time imaging and noninvasiveness. Ultrasound diagnosis of gynecology and obstetrics can be effectively used to evaluate the physiologic health of expectant mothers and fetuses, which is the important way to improve the accuracy and objectivity of the diagnosis. Nowadays one hot research topic of ultrasound diagnosis of gynecology and obstetrics is the detection for the early disease. This early diagnosis can benefit the further medical process but also increases the difficulty of diagnosis. The current problems of such clinical ultrasound diagnosis mainly come from the high dependence of the experience of doctors, the manual operations for detections and the difficulty of processing the information. Therefore it is required for the researches to set up an automatic analysis and processing system for ultrasound images.
Because of the interferences of ultrasound echo signals during the imaging, the formed speckle may affect the performance of further image analysis and processing algorithms. Therefore the two key problems of the analysis and processing methods for ultrasound images are the processing of speckle and the establishment of object models.
This dissertation focuses on three hot topics of the early diagnosis of gynecology and obstetrics. To automatically aid the diagnosis, the studies are carried out on the analysis and processing methods for ultrasound images.
For the detection of follicles of polycystic ovary syndrome, the adaptive morphological filtering is first proposed for despeckling, which can effectively depresse the abrupt variations of pixel values due to the speckle. Then the enhanced labeled watershed algorithm is proposed to segment the candidates of follicles and the iterative algorithm of automatically selecting the region of interest is proposed based on the spectral residual approach. Finally the object growing algoritm is proposed to realize the automated detection of follicles inside the ovaries. Compared with other methods, experimental results demonstrate the better performance of this proposed method which achieves the 89.4% recognition rate and 7.45% misidentification rate.
For the detection of the structure of early fetal hearts, the automatic selection algorithm for the region of interest is first proposed based on the accumulated motion image. This algorithm can overcome the low signal-to-noise ratio of the ultrasound image sequences and accurately extract the region of fetal hearts. Then the Rayleigh-trimmed anisotropic diffusion is proposed to deal with the low signal-to-noise ratio of the ultrasound images of fetal hearts and emphasize the motion information for the next processing. Finally the active cardiac model is proposed for the automated detection of early fetal cardiac structure. Both the structure and the motion information of fetal hearts are considered simultaneously with this model. The convergence of the inference of the model is guaranteed through optimizing the structure of the model. According to the experimental results of detecting the early fetal cardiac structures, the error of 90 percent of detections of this proposed method is less than 13 pixels.
For the automated detection of the nuchal translucency region, a three-layer hierarchical model is proposed. In this model, the support vector machine is applied to represent the related objects based on the features of the histogram of oriented gradient. Then the corresponding spatial model is established to define the spatial constrains between different objects. The optimal solution for the inference of the model can be obtained by applying the dynamic programming and generalized distance transform. Experimental results demonstrate that the model can achieve the accuracy of about 60% for the automated detection of the nuchal translucency.
由于超声成像过程中回波间存在相互干扰,形成的斑点噪声影响了进一步图像分析、处理算法的性能,因此斑点噪声的处理以及目标模型的建立是超声图像分析、处理研究必须要考虑的两个基本问题。
本论文针对妇产科早期诊断中的三个热点问题,以计算机辅助诊断为目标,对超声图像的分析、处理方法进行研究。
针对多囊卵巢内小囊胞的检测问题,提出自适应形态滤波的斑点噪声去除方法,该方法能对斑点噪声在图像上表现出的像素值突变进行有效抑制：提出改进的带标记分水岭算法,分割出候选的小囊胞,并提出基于剩余谱估计的感兴趣区域自动选取算法；进一步提出目标生长算法,实现了对卵巢内小囊胞的自动识别。实验表明该方法的识别率和误识率分别为89.4%和7.45%,与其他方法的比较验证了该方法的优越性。
针对胎儿早期心脏结构的检测问题,提出基于运动累加图的感兴趣区域自动选取方法,该方法能在超声图像序列信噪比较低的条件下对胎儿心脏区域进行准确提取；针对早期胎心图像的低信噪比以及检测时对运动信息的需要,提出瑞利均值各向异性扩散方法；为准确检测早期胎儿心脏结构,进一步提出能同时考虑胎儿心脏结构与运动信息的活动心脏模型,通过优化模型的结构保证了推断过程的收敛性。在胎儿早期心脏结构检测的实验中,90%的检测结果其误差小于13个像素。
针对颈项透明层的自动识别问题,提出一个具有三层结构的分层模型。该模型针对颈项透明层检测的具体需要,采用基于梯度方向直方图特征的支撑向量机来表征图像上的相关目标,并建立相应的空间模型来描述不同目标间的相互关联,通过动态规划以及广义距离变换对模型的全局最优解进行求解。实验结果表明,该模型对颈项透明层的自动识别可以达到约60%的准确率。
Ultrasound diagnosis is one of the most important diagnostic imaging techniques, which has been widely applied in the diagnosis of gynecology and obstetrics due to its merits of harmlessness, real-time imaging and noninvasiveness. Ultrasound diagnosis of gynecology and obstetrics can be effectively used to evaluate the physiologic health of expectant mothers and fetuses, which is the important way to improve the accuracy and objectivity of the diagnosis. Nowadays one hot research topic of ultrasound diagnosis of gynecology and obstetrics is the detection for the early disease. This early diagnosis can benefit the further medical process but also increases the difficulty of diagnosis. The current problems of such clinical ultrasound diagnosis mainly come from the high dependence of the experience of doctors, the manual operations for detections and the difficulty of processing the information. Therefore it is required for the researches to set up an automatic analysis and processing system for ultrasound images.
Because of the interferences of ultrasound echo signals during the imaging, the formed speckle may affect the performance of further image analysis and processing algorithms. Therefore the two key problems of the analysis and processing methods for ultrasound images are the processing of speckle and the establishment of object models.
This dissertation focuses on three hot topics of the early diagnosis of gynecology and obstetrics. To automatically aid the diagnosis, the studies are carried out on the analysis and processing methods for ultrasound images.
For the detection of follicles of polycystic ovary syndrome, the adaptive morphological filtering is first proposed for despeckling, which can effectively depresse the abrupt variations of pixel values due to the speckle. Then the enhanced labeled watershed algorithm is proposed to segment the candidates of follicles and the iterative algorithm of automatically selecting the region of interest is proposed based on the spectral residual approach. Finally the object growing algoritm is proposed to realize the automated detection of follicles inside the ovaries. Compared with other methods, experimental results demonstrate the better performance of this proposed method which achieves the 89.4% recognition rate and 7.45% misidentification rate.
For the detection of the structure of early fetal hearts, the automatic selection algorithm for the region of interest is first proposed based on the accumulated motion image. This algorithm can overcome the low signal-to-noise ratio of the ultrasound image sequences and accurately extract the region of fetal hearts. Then the Rayleigh-trimmed anisotropic diffusion is proposed to deal with the low signal-to-noise ratio of the ultrasound images of fetal hearts and emphasize the motion information for the next processing. Finally the active cardiac model is proposed for the automated detection of early fetal cardiac structure. Both the structure and the motion information of fetal hearts are considered simultaneously with this model. The convergence of the inference of the model is guaranteed through optimizing the structure of the model. According to the experimental results of detecting the early fetal cardiac structures, the error of 90 percent of detections of this proposed method is less than 13 pixels.
For the automated detection of the nuchal translucency region, a three-layer hierarchical model is proposed. In this model, the support vector machine is applied to represent the related objects based on the features of the histogram of oriented gradient. Then the corresponding spatial model is established to define the spatial constrains between different objects. The optimal solution for the inference of the model can be obtained by applying the dynamic programming and generalized distance transform. Experimental results demonstrate that the model can achieve the accuracy of about 60% for the automated detection of the nuchal translucency.
引文
[1]常才.妇产科超声新技术的现状和进展[J].中华医学超声杂志,2006,3(5)：257-258.
[2]陈欣林,许杨青,杨小红.妇产科超声造影的应用现状及研究进展[J].现代实用医学,2009,21(4)：300-301.
[3]郎景和.中国妇产科学的现状与发展.国际妇产科学杂志[J].2008,35(1)：3-5.
[4]周启昌,彭清海,章鸣,张静,孙巍,曹丹鸣,马丽萍,肖永志,谭宜.产前超声筛选胎儿早期心脏病的方法学研究[J].中华超声影像学杂志,2007,16(1)：43-46.
[5]Medifocus guidebook:polycystic ovary syndrome [EB]. www.medifocus.com.
[6]S Franks. Polycystic ovary syndrome [J]. Medicine,2005,33(11):38-40.
[7]CB Burckhardt. Speckle in ultrasound B-mode scans [J]. IEEE Trans. Sonics and Ultrasonics, 1978,25(1):1-6.
[8]CP Loizou, CS Pattichis, CI Christodoulou, RSH Istepanian, M Pantziaris, A Nicolaides. Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,2005,52(10):1653-1669.
[9]R Muzzolini, YH Yang, R Pierson. Multiresolution texture segmentation with application to diagnostic ultrasound images [J]. IEEE Trans. Medical Imaging,1993,12(1):108-123.
[10]RA Pierson, GP Adams. Computer-assisted image analysis, diagnostic ultrasonography and ovulation induction:Strange bedfellows [J]. Theriogenology,1995,43(1):105-112.
[11]GE Sarty, W Liang, M Sonka, RA Pierson. Semiautomated segmentation of ovarian follicular ultrasound images using a knowledge based algorithm [J]. Ultrasound in Medicine and Biology,1998,24(1):27-42.
[12]A Krivanek, M Sonka. Ovarian ultrasound image analysis:follicle segmentation [J]. IEEE Trans. Medical Imaging,1998,17(6):935-944.
[13]B Potocnik, D Zazula. Automated ovarian follicle segmentation using region growing [C]. Proceedings of First Int'l Workshop on Image and Signal Processing and Analysis, Pula, Croatia,2000,157-162.
[14]B Potocnik, D Zazula. Automated analysis of a sequence of ovarian ultrasound images. Part Ⅰ: segmentation of single 2D images [J]. Image and Vision Computing,2002,20(3):217-225.
[15]B Potocnik, D Zazula. Automated analysis of a sequence of ovarian ultrasound images. Part Ⅱ:prediction-based object recognition from a sequence of images [J]. Image and Vision Computing,2002,20(3):227-235.
[16]B Cigale, D Zazula. Segmentation of ovarian ultrasound images using cellular neural networks [J]. International Journal of Pattern Recognition and Artificial Intelligence,2004, 18(4):563-581.
[17]Z Tao, HD Tagare. Tunneling descent for m.a.p. active contours in ultrasound segmentation [J]. Medical Image Analysis,2007,11(3):266-281.
[18]KW Sum, PYS Cheung. Boundary vector field for parametric active contours [J]. Pattern Recognition,2007,40(6):1635-1645.
[19]杨晓霜,汪源源,王涌,王怡.基于改进变分水平集法提取超声图像乳腺肿瘤边缘[J].航天医学与医学工程,2008,21(6)：500-504.
[20]XF Jiang, Z Yi, JC Lv. Fuzzy SVM with a new membership function [J]. Neural Computing and Applications,2006,15(3):268-276.
[21]ZH Man, HR Wu, S Liu, XH Yu. A new adaptive backpropagation algorithm based on Lyapunov stability theory for Neural Networks [J]. IEEE Trans. Neural Networks,2006, 17(6):1580-1591.
[22]MN Do, M Vetterli. The contourlet transform:an efficient directional multiresolution image representation [J]. IEEE Trans. Image Processing,2005,14(12):2091-2106.
[23]H Szu,张立明.智能视觉图象处理[M].上海：上海科技教育出版社,2002.
[24]JIE Hoffman, S Kaplan. The incidence of congenital heart disease [J]. Journal of the American College of Cardiology,2002,39(12):1890-1900.
[25]R Becher, RD Wegner. Detailed screening for fetal anomalies and cardiac defects at the 11-13-week scan [J]. Ultrasound in Obstetrics and Gynecology,2006,27(6):613-618.
[26]TA Lassige, PJ Benkeser, D Fyfe, S Sharma. Comparison of septal defects in 2D and 3D echocardiography using active contour models [J]. Computerized Medical Imaging and Graphics,2000,24(6):377-388.
[27]ML Siqueira, J Scharcanski, POA Navaux. Echocardiographic image sequence segmentation and analysis using self-organizing maps [J]. Journal of VLSI Signal Processing,2002,32(1): 135-145.
[28]I Dindoyal, T Lambrou, J Deng, A Todd-Pokropek. Level set snake algorithms on the fetal heart [C]. Proceedings of IEEE International Symposium on Biomedical Imaging, Washington DC, USA,2007,864-867.
[29]SV Rasiah, M Publicover, AK Ewer, KS Khan, MD Kilby, J Zamora. A systematic review of the accuracy of first-trimester ultrasound examination for detecting major congenital heart disease [J]. Ultrasound in Obstetrics and Gynecology,2006,28(1):110-116.
[30]KW Fong, A Toi, S Salem, LK Hornberger, D Chitayat, SJ Keating, F McAuliffe, J Johnson. Detection of fetal structural abnormalities with US during early pregnancy [J]. RadioGraphics,2004,24:157-174.
[31]A Machlitt, KS Heling, R Chaoui. Increased cardiac atrial-to-ventricular length ratio in the fetal four-chamber view:a new marker for atrioventricular septal defects [J]. Ultrasound in Obstetrics and Gynecology,2004,24:618-622.
[32]MA Zoppi, RM Ibba, M Floris, F Manca, C Axiana, G Monni. Changes in nuchal translucency thickness in normal and abnormal karyotype fetuses [J]. BJOG:an International Journal of Obstetrics and Gynaecology,2003,110(6):584-588.
[33]N Montenegro, A Matias, JC Areas, S Castedo, H Barros. Increased fetal nuchal translucency: possible involvement of early cardiac failure [J]. Ultrasound in Obstetrics and Gynecology, 1997,10(4):265-268.
[34]AP Souka, E Krampl, S Bakalis, V Heath, KH Nicolaides. Outcome of pregnancy in chromosomally normal fetuses with increased nuchal translucency in the first trimester [J]. Ultrasound in Obstetrics and Gynecology,2001,18(1):9-17.
[35]RJ Snijders, P Noble, N Sebire, A Souka, KH Nicolaides. UK multicentre project on assessment of risk of trisomy 21 by maternal age and fetal nuchal translucency thickness at 10-14 weeks of gestation [J]. The Lancet,1998,352(9125):343-346.
[36]F Bernadino, R Cardoso, N Montenegro, J Bernardes, J Marques de Sa. Semiautomated ultrasonographic measurement of fetal nuchal translucency using a computer software tool [J]. Ultrasound in Medicine and Biology,1998,24(1):51-54.
[37]Y Lee, M Kim, M Kim. Robust border enhancement and detection for measurement of fetal nuchal translucency in ultrasound images [J]. Medical and Biological Engineering and Computing,2007,45(11):1143-1152.
[38]Y Lee, Y Choi, M Kim. Boundary detection in carotid ultrasound images using dynamic programming and a directional Haar-like filter [J]. Computers in Biology and Medicine,2010, 40(8):687-697.
[39]E Catanzariti, G Fusco, F Isgro, S Masecchia, R Prevete, M Santoro. A semi-automated method for the measurement of the fetal nuchal translucency in ultrasound images [J]. Lecture Notes in Computer Science,2009,5716:613-622
[40]JU Quistqaard. Signal acquisition and processing in medical diagnostic ultrasound [J]. IEEE Signal Processing Magazine,1997,14(1):67-74.
[41]N Gupta, MNS Swamy, E Plotkin. Despeckling of medical ultrasound images using data and rate adaptive lossy compression [J]. IEEE Trans. Medical Imaging,2005,24(6):743-754.
[42]DL Donoho. De-noising by soft-thresholding [J]. IEEE Trans. Information Theory,1995, 41(3):613-627.
[43]Y Yu, ST Acton. Speckle reducing anisotropic diffusion [J]. IEEE Trans. Image Processing, 2002,11(11):1260-1270.
[44]KZ Abd-Elmoniem, ABM Youssef, YM Kadah. Real-time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion [J]. IEEE Trans. Biomedical Engineering,2002,49(9):997-1014.
[45]P Perona, J Malik. Scale-space and edge detection using anisotropic diffusion [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[46]Y Yue, MM Croitoru, A Bidani, JB Zwishchenberger, JW Clark. Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images [J]. IEEE Trans. Medical Imaging,2006,25(3):297-311.
[47]M Karaman, AM Kutay, G Bozdagi. An adaptive speckle suppression filter for medical ultrasonic imaging [J]. IEEE Trans. Medical Image,1995,14(2):283-292.
[48]CP Loizou, CS Pattichis, CI Christodoulou, RSH Istepanian, M Pantziaris, A Nicolaides. Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,2005,52(10):1653-1669.
[49]TC Aysal, K.E Barner. Rayleigh-maximum-likelihood filtering for speckle reduction of ultrasound images [J]. IEEE Trans. Medical Imaging,2007,26(5):712-727.
[50]TR Crimmins. Geometric filter for speckle reduction [J]. Applied Optics,1985,24(10): 1438-1443.
[51]J Busse, TR Crimmins, JR Fienup. A model based approach to improve the performance of the geometric filtering speckle reduction algorithm [C]. Proceedings of IEEE Ultrasonics Symposium, Seattle, USA,1995,2:1353-1356.
[52]J Montagnat, M Sermesant, H Delingette, G Malandain, N Ayache. Anisotropic filtering for model-based segmentation of 4D cylindrical echocardiographic images [J]. Pattern Recognition Letters,2003,24(4):815-828.
[53]V Grau, JA Noble. Motion-guided anisotropic filtering of ultrasound sequences [C]. Proceedings of the 3rd IEEE International Symposium on Biomedical Imaging, Arlington, USA,2006,209-212.
[54]Y Yu, ST Acton. Edge detection in ultrasound imagery using the instantaneous coefficient of variation [J]. IEEE Trans. Image Processing,2004,13(12):1640-1655.
[55]SH Okazawa, R Ebrahimi, J Chuang, RN Rohing, SE Salcudean. Methods for segmenting curved needles in ultrasound images [J]. Medical Image Analysis,2006,10(3):330-342.
[56]D Shi, L Zheng, J Liu. Advanced hough transform using a multilayer fractional fourier method [J]. IEEE Trans. Image Processing,2010,19(6):1558-1566.
[57]M Moradi, P Abolmaesumi, DR Siemens, EE Sauerbrei, AH Boag, P Mousavi. Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series [J]. IEEE Trans. Biomedical Engineering,2009,56(9):2214-2224.
[58]G Carneiro, B Georgescu, S Good, D Comaniciu. Detection and measurement of fetal anatomies from ultrasound images using a constrained probabilistic boosting tree [J]. IEEE Trans. Medical Imaging,2008,27(9):1342-1355.
[59]J Yu, Y Wang, P Chen, Y Shen. Fetal abdominal contour extraction and measurement in ultrasound images [J]. Ultrasound in Medicine and Biology,2008,34(2):169-182.
[60]C Xu, JL Prince. Snake, shapes, and gradient vector flow [J]. IEEE Trans. Image Processing, 1998,7(3):359-369.
[61]MA Savelonas, DK. lakovidis, I Legakis, D Maroulis. Active contours guided by echogenicity and texture for delineation of thyroid nodules in ultrasound images [J]. IEEE Trans. Information technology in Biomedicine,2009,13(4):519-527.
[62]JJ Corso, A Yuille. NL Sicotte, A Toga. Detection and segmentation of pathological structures by the extended graph-shifts algorithm [C]. Proceedings of Medical Image Computing and Computer Aided Intervention, Brisbane, Australia,2007,985-993.
[63]JJ Corso, E Sharon, S Dube, S El-Saden, U Sinha, A Yuille. Efficient multilevel brain tumor segmentation with integrated Bayesian model classification [J]. IEEE Trans. Medical Imaging,2008,27(5):629-640.
[64]JJ Corso, Z Tu, A Yuille, A Toga. Segmentation of Sub-Cortical Structures by the Graph-Shifts Algorithm [C]. Proceedings of Information Processing in Medical Imaging, Roiduc Abbey, Netherlands.2007,20(1):183-197.
[65]J Pearl. Causality:models, reasoning, and inference (second edition) [M]. New York: Cambridge University Press,2009.
[66]RC Gonzalez, RE Woods. Digital image processing (second edition) [M], Upper Saddle River, NJ:Prentice Hall,2002.
[67]X Hou, L Zhang. Saliency detection:a spectral residual approach [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, Minneapolis,2007,1-8.
[68]L Itti, C Koch. A saliency-based search mechanism for overt and covert shifts of visual attention [J]. Vision Research,2000,40(10):1489-1506.
[69]J Wolfe, A Oliva, T Horowitz, S Butcher, A Bompas. Segmentation of objects from backgrounds in visual search tasks [J]. Vision Research,2002,42(28):2985-3004.
[70]CB Barber, DP Dobkin, HT Huhdanpaa. The quickhull algorithm for convex hulls [J]. ACM Trans. Mathematical Software,1996,22:469-483.
[71]Y Chen, SB Broschat, PJ Flynn. Phase insensitive homomorphic image processing for speckle reduction [J]. Ultrasonic Imaging,1996,18(2):122-139.
[72]JA Jensen, NB Svendsen. Calculation of pressure fields from arbitrarily shaped, apodized, and excited ultrasound transducers [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,1992,39(2):262-267.
[73]CJV Rijsbergen. Information Retrieval [M]. Newton, MA:Butterworth-Heinemann,1979.
[74]M Kass, A Witkin, D Terzopoulos. Snakes:active contour models [J]. Computer Vision,1988, 1:321-331.
[75]S Osher, J Sethian. Fronts propagating with curvature-dependent speed:algorithms based on Hamilton-Jacobi formulations [J]. Computational Physics,1988,79(1):12-49.
[76]C Zimmer, JC Olivo-Marin. Coupled parametric active contours [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2005,27(11):1838-1842.
[77]T Chan, L Vese. Active contours without edges [J]. IEEE Trans. Image Processing,2001, 10(2):266-277.
[78]Y Deng, Y Wang, P Chen. Automated detection of polycystic ovary syndrome from ultrasound images [C]. Proceedings of IEEE EMBS Conference, Vancouver, Canada,2008, 4772-4775.
[79]D Kersten, P Mamassian, AL Yuille. Object perception as bayesian inference [J]. Annual Review of Psychology,2004,55:271-304.
[80]PF Felzenszwalb, RB Grishick, D McAllister, D Ramanan. Object detection with discriminatively trained part based models [J]. IEEE Trans,on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[81]GE Mailloux, F Langlois, PY Simard, M Bertrand. Restoration of the velocity field of the heart from two-dimensional echocardiograms [J]. IEEE Trans. Medical Imaging,1989,8(2): 143-153.
[82]C Lin, M Lin, Y Suna. Ultrasound motion estimation using a hierarchical feature weighting algorithm [J]. Computerized Medical Imaging and Graphics,2007,31(3):178-190.
[83]B Cohen, I Dinstein. New maximum likelihood motion estimation schemes for noisy ultrasound images [J]. Pattern Recognition,2002,35(2):455-463.
[84]K Nam, J Kim, R Park, Y Shim. A fast hierarchical motion vector estimation algorithm using mean pyramid [J]. IEEE Trans. Circuits and Systems for Video Technology,1995,5(4): 344-351.
[85]P Perona, J Malik. Scale space and edge detection using anisotropic diffusion [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[86]MJ Black, G Sapiro, DH Marimont, D Heeger. Robust anisotropic diffusion [J]. IEEE Trans. Image Processing,1998,7(3):421-432.
[87]MJ Wainwright, MI Jordan. Graphical models, exponential families, and variational inference [J]. Foundations and Trends(?) in Machine Learning,2008,1(1-2):1-305.
[88]Y Wu, Z Si, H Gong, S Zhu. Learning active basis model for object detection and recognition [J]. International Journal of Computer Vision,2010,90:198-235.
[89]J Daugman. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters [J]. Journal of Optical Society of America,1985,2:1160-1169.
[90]J Ling, AC Bovik. Smoothing low-SNR molecular images via anisotropic median-diffusion [J]. IEEE Trans. Medical Imaging,2002,21(4):377-384.
[91]F Zhang, YM Yoo, LM Koh, Y Kim. Nonlinear diffusion in Laplacian pyramid domain for ultrasonic speckle reduction [J]. IEEE Trans. Medical Imaging,2007,26(2):200-211.
[92]TF Cootes, GJ Edwards, CJ Taylor. Active appearance models [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2001,23:681-685.
[93]Y Deng, Y Wang, P Chen. Automated detection of fetal cardiac structure from first-trimester ultrasound sequences [C]. Proceedings of IEEE Biomedical Engineering and Informatics, Yantai, China,2010,127-131.
[94]RF Wagner, SW Smith, JM Sandrik, H Lopez. Statistics of speckle in ultrasound B-scans [J]. IEEE Trans. Sonicsand Ultrasonics,1983.30:156-163.
[95]L Zhu, Y Chen, A Torralba, A Yuille, W Freeman. Latent hierarchical structural learning for object detection [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, San Francisco, USA,2010.1062-1069.
[96]A Torralba, K Murphy, W Freeman. Contextual models for object detection using boosted random fields [C]. Proceedings of Neural Information Processing Systems, Vancouver, Canada,2004.
[97]BJ Whitlow, IK Chatzipapas, DL Economides. The effect of fetal neck position on nuchal translucency measurement [J]. British Journal of Obstetrics and Gynaecology,1998,105: 872-876.
[98]B Scholkopf, A Smola, R Williamson, PL Bartlett. New support vector algorithms [J]. Neural Computation,2000,12:1207-1245.
[99]DG Lowe. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision,2004,60(2):91-110.
[100]N Dalal, B Triggs. Histograms of oriented gradients for human detection [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, San Diego, USA,2005,886-893.
[101]EH Adelson, CH Anderson, JR Bergen, PJ Burt, JM Ogdeh. Pyramid methods in image processing [J]. RCA Engineer,1984,29(6):33-41.
[102]P Felzenszwalb, D Huttenlocher. Distance transforms of sampled functions [R]. Cornell University Computing and Information Science, Technical Report 2004-1963,2004.
[2]陈欣林,许杨青,杨小红.妇产科超声造影的应用现状及研究进展[J].现代实用医学,2009,21(4)：300-301.
[3]郎景和.中国妇产科学的现状与发展.国际妇产科学杂志[J].2008,35(1)：3-5.
[4]周启昌,彭清海,章鸣,张静,孙巍,曹丹鸣,马丽萍,肖永志,谭宜.产前超声筛选胎儿早期心脏病的方法学研究[J].中华超声影像学杂志,2007,16(1)：43-46.
[5]Medifocus guidebook:polycystic ovary syndrome [EB]. www.medifocus.com.
[6]S Franks. Polycystic ovary syndrome [J]. Medicine,2005,33(11):38-40.
[7]CB Burckhardt. Speckle in ultrasound B-mode scans [J]. IEEE Trans. Sonics and Ultrasonics, 1978,25(1):1-6.
[8]CP Loizou, CS Pattichis, CI Christodoulou, RSH Istepanian, M Pantziaris, A Nicolaides. Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,2005,52(10):1653-1669.
[9]R Muzzolini, YH Yang, R Pierson. Multiresolution texture segmentation with application to diagnostic ultrasound images [J]. IEEE Trans. Medical Imaging,1993,12(1):108-123.
[10]RA Pierson, GP Adams. Computer-assisted image analysis, diagnostic ultrasonography and ovulation induction:Strange bedfellows [J]. Theriogenology,1995,43(1):105-112.
[11]GE Sarty, W Liang, M Sonka, RA Pierson. Semiautomated segmentation of ovarian follicular ultrasound images using a knowledge based algorithm [J]. Ultrasound in Medicine and Biology,1998,24(1):27-42.
[12]A Krivanek, M Sonka. Ovarian ultrasound image analysis:follicle segmentation [J]. IEEE Trans. Medical Imaging,1998,17(6):935-944.
[13]B Potocnik, D Zazula. Automated ovarian follicle segmentation using region growing [C]. Proceedings of First Int'l Workshop on Image and Signal Processing and Analysis, Pula, Croatia,2000,157-162.
[14]B Potocnik, D Zazula. Automated analysis of a sequence of ovarian ultrasound images. Part Ⅰ: segmentation of single 2D images [J]. Image and Vision Computing,2002,20(3):217-225.
[15]B Potocnik, D Zazula. Automated analysis of a sequence of ovarian ultrasound images. Part Ⅱ:prediction-based object recognition from a sequence of images [J]. Image and Vision Computing,2002,20(3):227-235.
[16]B Cigale, D Zazula. Segmentation of ovarian ultrasound images using cellular neural networks [J]. International Journal of Pattern Recognition and Artificial Intelligence,2004, 18(4):563-581.
[17]Z Tao, HD Tagare. Tunneling descent for m.a.p. active contours in ultrasound segmentation [J]. Medical Image Analysis,2007,11(3):266-281.
[18]KW Sum, PYS Cheung. Boundary vector field for parametric active contours [J]. Pattern Recognition,2007,40(6):1635-1645.
[19]杨晓霜,汪源源,王涌,王怡.基于改进变分水平集法提取超声图像乳腺肿瘤边缘[J].航天医学与医学工程,2008,21(6)：500-504.
[20]XF Jiang, Z Yi, JC Lv. Fuzzy SVM with a new membership function [J]. Neural Computing and Applications,2006,15(3):268-276.
[21]ZH Man, HR Wu, S Liu, XH Yu. A new adaptive backpropagation algorithm based on Lyapunov stability theory for Neural Networks [J]. IEEE Trans. Neural Networks,2006, 17(6):1580-1591.
[22]MN Do, M Vetterli. The contourlet transform:an efficient directional multiresolution image representation [J]. IEEE Trans. Image Processing,2005,14(12):2091-2106.
[23]H Szu,张立明.智能视觉图象处理[M].上海：上海科技教育出版社,2002.
[24]JIE Hoffman, S Kaplan. The incidence of congenital heart disease [J]. Journal of the American College of Cardiology,2002,39(12):1890-1900.
[25]R Becher, RD Wegner. Detailed screening for fetal anomalies and cardiac defects at the 11-13-week scan [J]. Ultrasound in Obstetrics and Gynecology,2006,27(6):613-618.
[26]TA Lassige, PJ Benkeser, D Fyfe, S Sharma. Comparison of septal defects in 2D and 3D echocardiography using active contour models [J]. Computerized Medical Imaging and Graphics,2000,24(6):377-388.
[27]ML Siqueira, J Scharcanski, POA Navaux. Echocardiographic image sequence segmentation and analysis using self-organizing maps [J]. Journal of VLSI Signal Processing,2002,32(1): 135-145.
[28]I Dindoyal, T Lambrou, J Deng, A Todd-Pokropek. Level set snake algorithms on the fetal heart [C]. Proceedings of IEEE International Symposium on Biomedical Imaging, Washington DC, USA,2007,864-867.
[29]SV Rasiah, M Publicover, AK Ewer, KS Khan, MD Kilby, J Zamora. A systematic review of the accuracy of first-trimester ultrasound examination for detecting major congenital heart disease [J]. Ultrasound in Obstetrics and Gynecology,2006,28(1):110-116.
[30]KW Fong, A Toi, S Salem, LK Hornberger, D Chitayat, SJ Keating, F McAuliffe, J Johnson. Detection of fetal structural abnormalities with US during early pregnancy [J]. RadioGraphics,2004,24:157-174.
[31]A Machlitt, KS Heling, R Chaoui. Increased cardiac atrial-to-ventricular length ratio in the fetal four-chamber view:a new marker for atrioventricular septal defects [J]. Ultrasound in Obstetrics and Gynecology,2004,24:618-622.
[32]MA Zoppi, RM Ibba, M Floris, F Manca, C Axiana, G Monni. Changes in nuchal translucency thickness in normal and abnormal karyotype fetuses [J]. BJOG:an International Journal of Obstetrics and Gynaecology,2003,110(6):584-588.
[33]N Montenegro, A Matias, JC Areas, S Castedo, H Barros. Increased fetal nuchal translucency: possible involvement of early cardiac failure [J]. Ultrasound in Obstetrics and Gynecology, 1997,10(4):265-268.
[34]AP Souka, E Krampl, S Bakalis, V Heath, KH Nicolaides. Outcome of pregnancy in chromosomally normal fetuses with increased nuchal translucency in the first trimester [J]. Ultrasound in Obstetrics and Gynecology,2001,18(1):9-17.
[35]RJ Snijders, P Noble, N Sebire, A Souka, KH Nicolaides. UK multicentre project on assessment of risk of trisomy 21 by maternal age and fetal nuchal translucency thickness at 10-14 weeks of gestation [J]. The Lancet,1998,352(9125):343-346.
[36]F Bernadino, R Cardoso, N Montenegro, J Bernardes, J Marques de Sa. Semiautomated ultrasonographic measurement of fetal nuchal translucency using a computer software tool [J]. Ultrasound in Medicine and Biology,1998,24(1):51-54.
[37]Y Lee, M Kim, M Kim. Robust border enhancement and detection for measurement of fetal nuchal translucency in ultrasound images [J]. Medical and Biological Engineering and Computing,2007,45(11):1143-1152.
[38]Y Lee, Y Choi, M Kim. Boundary detection in carotid ultrasound images using dynamic programming and a directional Haar-like filter [J]. Computers in Biology and Medicine,2010, 40(8):687-697.
[39]E Catanzariti, G Fusco, F Isgro, S Masecchia, R Prevete, M Santoro. A semi-automated method for the measurement of the fetal nuchal translucency in ultrasound images [J]. Lecture Notes in Computer Science,2009,5716:613-622
[40]JU Quistqaard. Signal acquisition and processing in medical diagnostic ultrasound [J]. IEEE Signal Processing Magazine,1997,14(1):67-74.
[41]N Gupta, MNS Swamy, E Plotkin. Despeckling of medical ultrasound images using data and rate adaptive lossy compression [J]. IEEE Trans. Medical Imaging,2005,24(6):743-754.
[42]DL Donoho. De-noising by soft-thresholding [J]. IEEE Trans. Information Theory,1995, 41(3):613-627.
[43]Y Yu, ST Acton. Speckle reducing anisotropic diffusion [J]. IEEE Trans. Image Processing, 2002,11(11):1260-1270.
[44]KZ Abd-Elmoniem, ABM Youssef, YM Kadah. Real-time speckle reduction and coherence enhancement in ultrasound imaging via nonlinear anisotropic diffusion [J]. IEEE Trans. Biomedical Engineering,2002,49(9):997-1014.
[45]P Perona, J Malik. Scale-space and edge detection using anisotropic diffusion [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[46]Y Yue, MM Croitoru, A Bidani, JB Zwishchenberger, JW Clark. Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images [J]. IEEE Trans. Medical Imaging,2006,25(3):297-311.
[47]M Karaman, AM Kutay, G Bozdagi. An adaptive speckle suppression filter for medical ultrasonic imaging [J]. IEEE Trans. Medical Image,1995,14(2):283-292.
[48]CP Loizou, CS Pattichis, CI Christodoulou, RSH Istepanian, M Pantziaris, A Nicolaides. Comparative evaluation of despeckle filtering in ultrasound imaging of the carotid artery [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,2005,52(10):1653-1669.
[49]TC Aysal, K.E Barner. Rayleigh-maximum-likelihood filtering for speckle reduction of ultrasound images [J]. IEEE Trans. Medical Imaging,2007,26(5):712-727.
[50]TR Crimmins. Geometric filter for speckle reduction [J]. Applied Optics,1985,24(10): 1438-1443.
[51]J Busse, TR Crimmins, JR Fienup. A model based approach to improve the performance of the geometric filtering speckle reduction algorithm [C]. Proceedings of IEEE Ultrasonics Symposium, Seattle, USA,1995,2:1353-1356.
[52]J Montagnat, M Sermesant, H Delingette, G Malandain, N Ayache. Anisotropic filtering for model-based segmentation of 4D cylindrical echocardiographic images [J]. Pattern Recognition Letters,2003,24(4):815-828.
[53]V Grau, JA Noble. Motion-guided anisotropic filtering of ultrasound sequences [C]. Proceedings of the 3rd IEEE International Symposium on Biomedical Imaging, Arlington, USA,2006,209-212.
[54]Y Yu, ST Acton. Edge detection in ultrasound imagery using the instantaneous coefficient of variation [J]. IEEE Trans. Image Processing,2004,13(12):1640-1655.
[55]SH Okazawa, R Ebrahimi, J Chuang, RN Rohing, SE Salcudean. Methods for segmenting curved needles in ultrasound images [J]. Medical Image Analysis,2006,10(3):330-342.
[56]D Shi, L Zheng, J Liu. Advanced hough transform using a multilayer fractional fourier method [J]. IEEE Trans. Image Processing,2010,19(6):1558-1566.
[57]M Moradi, P Abolmaesumi, DR Siemens, EE Sauerbrei, AH Boag, P Mousavi. Augmenting detection of prostate cancer in transrectal ultrasound images using SVM and RF time series [J]. IEEE Trans. Biomedical Engineering,2009,56(9):2214-2224.
[58]G Carneiro, B Georgescu, S Good, D Comaniciu. Detection and measurement of fetal anatomies from ultrasound images using a constrained probabilistic boosting tree [J]. IEEE Trans. Medical Imaging,2008,27(9):1342-1355.
[59]J Yu, Y Wang, P Chen, Y Shen. Fetal abdominal contour extraction and measurement in ultrasound images [J]. Ultrasound in Medicine and Biology,2008,34(2):169-182.
[60]C Xu, JL Prince. Snake, shapes, and gradient vector flow [J]. IEEE Trans. Image Processing, 1998,7(3):359-369.
[61]MA Savelonas, DK. lakovidis, I Legakis, D Maroulis. Active contours guided by echogenicity and texture for delineation of thyroid nodules in ultrasound images [J]. IEEE Trans. Information technology in Biomedicine,2009,13(4):519-527.
[62]JJ Corso, A Yuille. NL Sicotte, A Toga. Detection and segmentation of pathological structures by the extended graph-shifts algorithm [C]. Proceedings of Medical Image Computing and Computer Aided Intervention, Brisbane, Australia,2007,985-993.
[63]JJ Corso, E Sharon, S Dube, S El-Saden, U Sinha, A Yuille. Efficient multilevel brain tumor segmentation with integrated Bayesian model classification [J]. IEEE Trans. Medical Imaging,2008,27(5):629-640.
[64]JJ Corso, Z Tu, A Yuille, A Toga. Segmentation of Sub-Cortical Structures by the Graph-Shifts Algorithm [C]. Proceedings of Information Processing in Medical Imaging, Roiduc Abbey, Netherlands.2007,20(1):183-197.
[65]J Pearl. Causality:models, reasoning, and inference (second edition) [M]. New York: Cambridge University Press,2009.
[66]RC Gonzalez, RE Woods. Digital image processing (second edition) [M], Upper Saddle River, NJ:Prentice Hall,2002.
[67]X Hou, L Zhang. Saliency detection:a spectral residual approach [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, Minneapolis,2007,1-8.
[68]L Itti, C Koch. A saliency-based search mechanism for overt and covert shifts of visual attention [J]. Vision Research,2000,40(10):1489-1506.
[69]J Wolfe, A Oliva, T Horowitz, S Butcher, A Bompas. Segmentation of objects from backgrounds in visual search tasks [J]. Vision Research,2002,42(28):2985-3004.
[70]CB Barber, DP Dobkin, HT Huhdanpaa. The quickhull algorithm for convex hulls [J]. ACM Trans. Mathematical Software,1996,22:469-483.
[71]Y Chen, SB Broschat, PJ Flynn. Phase insensitive homomorphic image processing for speckle reduction [J]. Ultrasonic Imaging,1996,18(2):122-139.
[72]JA Jensen, NB Svendsen. Calculation of pressure fields from arbitrarily shaped, apodized, and excited ultrasound transducers [J]. IEEE Trans. Ultrasonics, Ferroelectrics and Frequency Control,1992,39(2):262-267.
[73]CJV Rijsbergen. Information Retrieval [M]. Newton, MA:Butterworth-Heinemann,1979.
[74]M Kass, A Witkin, D Terzopoulos. Snakes:active contour models [J]. Computer Vision,1988, 1:321-331.
[75]S Osher, J Sethian. Fronts propagating with curvature-dependent speed:algorithms based on Hamilton-Jacobi formulations [J]. Computational Physics,1988,79(1):12-49.
[76]C Zimmer, JC Olivo-Marin. Coupled parametric active contours [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2005,27(11):1838-1842.
[77]T Chan, L Vese. Active contours without edges [J]. IEEE Trans. Image Processing,2001, 10(2):266-277.
[78]Y Deng, Y Wang, P Chen. Automated detection of polycystic ovary syndrome from ultrasound images [C]. Proceedings of IEEE EMBS Conference, Vancouver, Canada,2008, 4772-4775.
[79]D Kersten, P Mamassian, AL Yuille. Object perception as bayesian inference [J]. Annual Review of Psychology,2004,55:271-304.
[80]PF Felzenszwalb, RB Grishick, D McAllister, D Ramanan. Object detection with discriminatively trained part based models [J]. IEEE Trans,on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.
[81]GE Mailloux, F Langlois, PY Simard, M Bertrand. Restoration of the velocity field of the heart from two-dimensional echocardiograms [J]. IEEE Trans. Medical Imaging,1989,8(2): 143-153.
[82]C Lin, M Lin, Y Suna. Ultrasound motion estimation using a hierarchical feature weighting algorithm [J]. Computerized Medical Imaging and Graphics,2007,31(3):178-190.
[83]B Cohen, I Dinstein. New maximum likelihood motion estimation schemes for noisy ultrasound images [J]. Pattern Recognition,2002,35(2):455-463.
[84]K Nam, J Kim, R Park, Y Shim. A fast hierarchical motion vector estimation algorithm using mean pyramid [J]. IEEE Trans. Circuits and Systems for Video Technology,1995,5(4): 344-351.
[85]P Perona, J Malik. Scale space and edge detection using anisotropic diffusion [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,1990,12(7):629-639.
[86]MJ Black, G Sapiro, DH Marimont, D Heeger. Robust anisotropic diffusion [J]. IEEE Trans. Image Processing,1998,7(3):421-432.
[87]MJ Wainwright, MI Jordan. Graphical models, exponential families, and variational inference [J]. Foundations and Trends(?) in Machine Learning,2008,1(1-2):1-305.
[88]Y Wu, Z Si, H Gong, S Zhu. Learning active basis model for object detection and recognition [J]. International Journal of Computer Vision,2010,90:198-235.
[89]J Daugman. Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters [J]. Journal of Optical Society of America,1985,2:1160-1169.
[90]J Ling, AC Bovik. Smoothing low-SNR molecular images via anisotropic median-diffusion [J]. IEEE Trans. Medical Imaging,2002,21(4):377-384.
[91]F Zhang, YM Yoo, LM Koh, Y Kim. Nonlinear diffusion in Laplacian pyramid domain for ultrasonic speckle reduction [J]. IEEE Trans. Medical Imaging,2007,26(2):200-211.
[92]TF Cootes, GJ Edwards, CJ Taylor. Active appearance models [J]. IEEE Trans. Pattern Analysis and Machine Intelligence,2001,23:681-685.
[93]Y Deng, Y Wang, P Chen. Automated detection of fetal cardiac structure from first-trimester ultrasound sequences [C]. Proceedings of IEEE Biomedical Engineering and Informatics, Yantai, China,2010,127-131.
[94]RF Wagner, SW Smith, JM Sandrik, H Lopez. Statistics of speckle in ultrasound B-scans [J]. IEEE Trans. Sonicsand Ultrasonics,1983.30:156-163.
[95]L Zhu, Y Chen, A Torralba, A Yuille, W Freeman. Latent hierarchical structural learning for object detection [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, San Francisco, USA,2010.1062-1069.
[96]A Torralba, K Murphy, W Freeman. Contextual models for object detection using boosted random fields [C]. Proceedings of Neural Information Processing Systems, Vancouver, Canada,2004.
[97]BJ Whitlow, IK Chatzipapas, DL Economides. The effect of fetal neck position on nuchal translucency measurement [J]. British Journal of Obstetrics and Gynaecology,1998,105: 872-876.
[98]B Scholkopf, A Smola, R Williamson, PL Bartlett. New support vector algorithms [J]. Neural Computation,2000,12:1207-1245.
[99]DG Lowe. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision,2004,60(2):91-110.
[100]N Dalal, B Triggs. Histograms of oriented gradients for human detection [C]. Proceedings of IEEE Computer Vision and Pattern Recognition, San Diego, USA,2005,886-893.
[101]EH Adelson, CH Anderson, JR Bergen, PJ Burt, JM Ogdeh. Pyramid methods in image processing [J]. RCA Engineer,1984,29(6):33-41.
[102]P Felzenszwalb, D Huttenlocher. Distance transforms of sampled functions [R]. Cornell University Computing and Information Science, Technical Report 2004-1963,2004.