基于无重初始化的HGVF-测地线模型的颈动脉超声图像分割算法
|
摘要
心脑血管疾病是危害人类健康的主要疾病之一。根据世界卫生组织统计的数据,每年心血管疾病导致的死亡人数约占全世界死亡人数的三分之一。相关研究表明,颈动脉粥样硬化与心脑血管疾病密切相关,颈动脉壁状况的评价在提前判断无症状病人的危险状况的过程中起着非常重要的作用。
超声成像作为最常用的颈动脉斑块检测的影像学方法之一,具有方便、无创等优点。且随着高频超声的发展,超声图像的分辨率越来越高,超声成像的临床应用变得更为广泛。这带来另一个问题:导致读片医师的工作负荷加重,最终影响疾病的漏诊率。于是学者们提出了计算机辅助诊断技术。一个完整的基于灰阶超声图像的计算机辅助诊断系统将依次由边缘提取、特征提取、分类判断三个部分组成,本文主要的研究内容是颈动脉斑块的边缘提取,以期提出一种性能更好的能用于临床诊断的颈动脉斑块超声图像分割算法。所完成的主要研究工作和创新点描述如下:
(1)针对GVF-Snake主动轮廓模型在进行颈动脉超声图像分割时存在的网络拓扑结构问题以及轮廓可能沿着错误方向演化问题,Paragios等提出了GVF-测地线模型。该模型利用了测地线主动轮廓模型具有的优势:与水平集方法结合的GVF-测地线模型能够解决网络拓扑结构问题;由于测地线模型的轮廓沿着法线方向演化,因此GVF-测地线模型不存在轮廓可能沿着错误方向演化问题。但该模型可移植性不好,因此本文修改了该模型的边缘图矩阵以使其严格满足与边缘检测函数之间的线性反比关系,并且改进了该模型的部分算子,得到更接近测地线主动轮廓模型的改进的GVF-测地线模型。
(2)由于改进的GVF-测地线模型不能解决深度凹陷区域问题,Wang.Y等提出的HGVF- Snake主动轮廓模型能够有效解决该问题,因此本文在HGVF-Snake模型的基础上增加弱边缘检测算子,并将改进的HGVF-Snake模型与改进的GVF-测地线模型相结合,提出改进的HGVF-测地线模型。实验已论证改进的HGVF-测地线模型能够有效解决深度凹陷区域问题以及弱边缘检测问题,其性能相对于改进的GVF-测地线模型有所提升。
(3)针对改进的HGVF-测地线模型存在的耗时过长、效率测度不好问题,文章在模型处理对象以及水平集函数的重初始化两方面进行改进,提出无需重初始化的改进的HGVF-测地线模型。该模型在曲线演化过程中节省了重复初始化时间;另外本文进一步提出了一种改进的子图作为模型分割对象,实验表明,该方法能进一步缩减程序运行时间,且能解决通用子图中存在的效率测度不稳定以及给FPF和TNF的计算结果带来额外误差等问题。
综上所述,无需重初始化的改进的HGVF-测地线模型原理简单、易于实现,不仅解决GVF-Snake主动轮廓模型中存在的拓扑结构和深度凹陷区域问题,而且进一步解决了弱边缘检测问题等。实验结果表明,无需重初始化的改进的HGVF-测地线分割算法分割精度很高,能够在颈动脉斑块提取中取得非常好的效果,其性能远优于GVF-Snake分割算法。
Cardiovascular and cerebrovascular disease(CCD) is one of principal diseases to do harm to human health.According to the World Health Organization, the deaths caused by cardiovascular diseases (CVD) is one-third of total global deaths each year. Correlational study shows that atherosclerosis (AS) is closely related to CCD and assessment of the status of carotid artery wall plays a very important role on judging in advance risk situation of the symptomless.
Ultrasonography, which is one of the most frequently used medical imaging methods for the detection of carotid plaque, is convenient and noninvasive. With the development of high frequency ultrasound, resolution ratio of the ultrasonic image becomes higher and higher, and clinical application of ultrasonography also becomes wider. But this brings another problem: it makes workload of the doctors heavier, finally affects rate of missed disease diagnosis.So scholars bring forward Computer Aided Diagnosis (CAD). A complete CAD system based on grayscale ultrasound image consists of edge extracting, feature extraction and classification.The content of this paper is edge extracting of carotid plaque,in the hope of putting forward a carotid plaque ultrasonic image segmentation algorithm that has the better performance and can used for clinical diagnosis. Main finished research work and contributions of this dissertation are as follows:
(1) In view of the problems of net topology and the contour evolving in a wrong direction exist in GVF-Snake active contour model when segmenting carotid ultrasonic images, Paragios puts forward GVF-GAC model. This model takes advantage of geodesic active contour (GAC) model: GVF-GAC model combined with level set method can solve the problem of net topology; the contour of GAC model evolves in the direction of the normal, so the problem of contour evolving in a wrong direction doesn’t exist in the GVF-GAC model.But this model has bad transportability, so this paper modifies edge map of this model to make it strictly satisfy the inverse linear relation with edge detection function, and improves some operator of this model, raises improved GVF- GAC model which is more close to GAC model.
(2) Improved GVF-GAC model cann’t solve the problem of deep concavities, and HGVF- Snake active contour model put forwad by Wang.Y can solve this problem, so this paper adds weak edge detector to HGVF-Snake model, combines it with improved GVF-GAC model and puts forwad improved HGVF-GAC model.The experiment has demonstrated that improved HGVF- GAC model could solve the problems of deep concavities and weak edge detection, and its performance is better than improved GVF-GAC model.
(3) In view of the problem of long time consuming and bad efficiency exists in improved HGVF-GAC model, this paper makes some improvements in re-initialization of level set function and model-processing object, and puts forward the improved HGVF-GAC model without re-initialization. This new model saves time of re-initialization in process of curve evolution; moreover, this dissertation furtherly puts forward an improved subimage to be model-processing object, the experiment shows that this method could furthurly decrease program running time, and solve the problems of unstable efficiency and additional error of FPF and TNF’result exists general subimage.
To sum up, improved HGVF-GAC model without re-initialization has simple principle and can implement easily, this method not only solves problems of net topology and deep concavities but also furthurly solves problem of weak edge detection. Result of experiment shows that improved HGVF-GAC segmentation algorithm without re-initialization have high segmentation precision, could bring a good result in edge extracting of carotid plaque and its performance is much better than GVF-Snake active contour model.
超声成像作为最常用的颈动脉斑块检测的影像学方法之一,具有方便、无创等优点。且随着高频超声的发展,超声图像的分辨率越来越高,超声成像的临床应用变得更为广泛。这带来另一个问题:导致读片医师的工作负荷加重,最终影响疾病的漏诊率。于是学者们提出了计算机辅助诊断技术。一个完整的基于灰阶超声图像的计算机辅助诊断系统将依次由边缘提取、特征提取、分类判断三个部分组成,本文主要的研究内容是颈动脉斑块的边缘提取,以期提出一种性能更好的能用于临床诊断的颈动脉斑块超声图像分割算法。所完成的主要研究工作和创新点描述如下:
(1)针对GVF-Snake主动轮廓模型在进行颈动脉超声图像分割时存在的网络拓扑结构问题以及轮廓可能沿着错误方向演化问题,Paragios等提出了GVF-测地线模型。该模型利用了测地线主动轮廓模型具有的优势:与水平集方法结合的GVF-测地线模型能够解决网络拓扑结构问题;由于测地线模型的轮廓沿着法线方向演化,因此GVF-测地线模型不存在轮廓可能沿着错误方向演化问题。但该模型可移植性不好,因此本文修改了该模型的边缘图矩阵以使其严格满足与边缘检测函数之间的线性反比关系,并且改进了该模型的部分算子,得到更接近测地线主动轮廓模型的改进的GVF-测地线模型。
(2)由于改进的GVF-测地线模型不能解决深度凹陷区域问题,Wang.Y等提出的HGVF- Snake主动轮廓模型能够有效解决该问题,因此本文在HGVF-Snake模型的基础上增加弱边缘检测算子,并将改进的HGVF-Snake模型与改进的GVF-测地线模型相结合,提出改进的HGVF-测地线模型。实验已论证改进的HGVF-测地线模型能够有效解决深度凹陷区域问题以及弱边缘检测问题,其性能相对于改进的GVF-测地线模型有所提升。
(3)针对改进的HGVF-测地线模型存在的耗时过长、效率测度不好问题,文章在模型处理对象以及水平集函数的重初始化两方面进行改进,提出无需重初始化的改进的HGVF-测地线模型。该模型在曲线演化过程中节省了重复初始化时间;另外本文进一步提出了一种改进的子图作为模型分割对象,实验表明,该方法能进一步缩减程序运行时间,且能解决通用子图中存在的效率测度不稳定以及给FPF和TNF的计算结果带来额外误差等问题。
综上所述,无需重初始化的改进的HGVF-测地线模型原理简单、易于实现,不仅解决GVF-Snake主动轮廓模型中存在的拓扑结构和深度凹陷区域问题,而且进一步解决了弱边缘检测问题等。实验结果表明,无需重初始化的改进的HGVF-测地线分割算法分割精度很高,能够在颈动脉斑块提取中取得非常好的效果,其性能远优于GVF-Snake分割算法。
Cardiovascular and cerebrovascular disease(CCD) is one of principal diseases to do harm to human health.According to the World Health Organization, the deaths caused by cardiovascular diseases (CVD) is one-third of total global deaths each year. Correlational study shows that atherosclerosis (AS) is closely related to CCD and assessment of the status of carotid artery wall plays a very important role on judging in advance risk situation of the symptomless.
Ultrasonography, which is one of the most frequently used medical imaging methods for the detection of carotid plaque, is convenient and noninvasive. With the development of high frequency ultrasound, resolution ratio of the ultrasonic image becomes higher and higher, and clinical application of ultrasonography also becomes wider. But this brings another problem: it makes workload of the doctors heavier, finally affects rate of missed disease diagnosis.So scholars bring forward Computer Aided Diagnosis (CAD). A complete CAD system based on grayscale ultrasound image consists of edge extracting, feature extraction and classification.The content of this paper is edge extracting of carotid plaque,in the hope of putting forward a carotid plaque ultrasonic image segmentation algorithm that has the better performance and can used for clinical diagnosis. Main finished research work and contributions of this dissertation are as follows:
(1) In view of the problems of net topology and the contour evolving in a wrong direction exist in GVF-Snake active contour model when segmenting carotid ultrasonic images, Paragios puts forward GVF-GAC model. This model takes advantage of geodesic active contour (GAC) model: GVF-GAC model combined with level set method can solve the problem of net topology; the contour of GAC model evolves in the direction of the normal, so the problem of contour evolving in a wrong direction doesn’t exist in the GVF-GAC model.But this model has bad transportability, so this paper modifies edge map of this model to make it strictly satisfy the inverse linear relation with edge detection function, and improves some operator of this model, raises improved GVF- GAC model which is more close to GAC model.
(2) Improved GVF-GAC model cann’t solve the problem of deep concavities, and HGVF- Snake active contour model put forwad by Wang.Y can solve this problem, so this paper adds weak edge detector to HGVF-Snake model, combines it with improved GVF-GAC model and puts forwad improved HGVF-GAC model.The experiment has demonstrated that improved HGVF- GAC model could solve the problems of deep concavities and weak edge detection, and its performance is better than improved GVF-GAC model.
(3) In view of the problem of long time consuming and bad efficiency exists in improved HGVF-GAC model, this paper makes some improvements in re-initialization of level set function and model-processing object, and puts forward the improved HGVF-GAC model without re-initialization. This new model saves time of re-initialization in process of curve evolution; moreover, this dissertation furtherly puts forward an improved subimage to be model-processing object, the experiment shows that this method could furthurly decrease program running time, and solve the problems of unstable efficiency and additional error of FPF and TNF’result exists general subimage.
To sum up, improved HGVF-GAC model without re-initialization has simple principle and can implement easily, this method not only solves problems of net topology and deep concavities but also furthurly solves problem of weak edge detection. Result of experiment shows that improved HGVF-GAC segmentation algorithm without re-initialization have high segmentation precision, could bring a good result in edge extracting of carotid plaque and its performance is much better than GVF-Snake active contour model.
引文
A. Kelemen, G. Szekely, G. Gerig. 1999. Elastic model-based segmentation of 3-D neuro- radiological data sets. IEEE Trans. Med. Image, 18(10): 828-839.
Alexandrow AV, Bladin CF, Murphy J, et al. 1994. Clinical applicability of method to measure carotid stenosis. J Strok Cerebrovas Dis, 4: 256-258.
Amirbekian V, Lipinski M J, et a1. 2007. Detecting and assessing macrophages in vivo to evaluate atherosclerosis non-invasively using molecular MRI. PNAS, 104(3): 961-966.
Arnold JA, Modaresi KB, Thomas N, et a1. 1999. Carotid plaque characterization by duplex scanning: observer error may undermine current clinical trials. Strobe, 30: 6l-65.
A. Yezzi, A. Tsai, A. Willsky. 1999. A statistical approach to snakes for bimodal and tri-modal imagery. Proc. IEEE Int’l Conf. Computer Vision, pp. 898-903.
Belohlavek M, Foley DA, Gerber TC, et al. 1993. Three- and four-dimensional cardiovascular ultrasound imaging: a new era for echocardiography. Mayo Clin Proc, 68(3): 221-249.
Bomithon KP, Vaviver J, Anne T, et al. 1993. Early carotid atherosclerosis in healthy middle-aged women: a follow-up study [J]. Stroke, 24: 1837-1842.
Bradley JE, Brian B. 2002. Computer-aided detection and diagnosis at the start of the third millennium [J]. J Digit Imaging, 15(2): 59-68.
Byun JH, Kim TK, Lee SS, et a1. 2003. Evaluation of the hepatic artery in potential donors for living donor liver transplantation by computed tomography angiography using multi-detector row computed tomography: comparison of volume rendering and maximum intensity projection techniques. J Comput Assist Tomngr, 27(2): 125-131.
Cai J, Hatsukami TS, Ferguson MS, et a1. 2005. In vivo quantitative measurement of intact fibr- ous cap and lipid rich necrotic core size in atherosclerotie carotid plaque: a comparison of high resolution contrast enhanced MRI and histology.Circulation, 12(22): 3437-3444.
Canny J. 1986. A computational approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6): 679-698.
Caselles V, Catte F, Coll T, et al. 1993. A geometric model for active contours in image processing [J]. Numerische Mathematik, 66(1): 1-31.
Chalana V, Kim Y. 1997. A methodology for evaluation of boundary detection algorithms on medical images [J]. IEEE Transactions on medical imaging, 16(5): 642-652.
CHEN DR, CHANG RF, et a1. 2002. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks [J]. Ultrasound in Med. Biol, 28(10):1301-1310.
CHOU YH, TIU CM, HUNG GS, et a1. 2001. Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis [J]. Ultrasound in Med. Biol, 27(11): 1493-1498.
Christos P. Loizou, Constantinos S. Pattichis, et al. 2005. Comparative Evaluation of Despeckle Filtering In Ultrasound Imaging of the Carotid Artery. IEEE Trans. Ultrasonics, Ferroelectrics, and Frequency Control, 52(10): 1653-1669.
C. I. Christodoulou, C. Loizou, C. S. Pattichis, et al. 2002. Despeckle filtering in ultrasound imaging of the carotid artery.in Proc. Second Joint Eng. Med. Biol./Biomed. Eng.Soc: 1027–1028.
C. I. Christodoulou, C. S. Pattichis, et al. 2003. Texture-Based Classification of Atherosclerotic Carotid Plaques. IEEE Trans. Medical Imaging, 22(7): 902-912.
C. Metz. 1978. Basic principles of ROC analysis. Semin. Nucl. Medic, 8: 283-298.
Coli S, Magnoni M, Sangiorgi, et a1. 2008. Contrast enhanced ultrasound imaging of intra-plaque neovascularization in carotid arteries. J Am Col1 Cardio1, 52(3):223-230.
C. Xu, J. Prince. 1998. Snakes, Shapes, and Gradient Vector Flow.IEEETrans.Image Processing, 7: 359-369.
C. Xu, J. L. Prince. 1998. Generalized gradient vector flow external forces for active contours. Signal Process. 71: 131-139
De Weert TT, Ouhlous M, Meijering E, et a1. 2006. In vivo characterization and quantification of atherosclerotic carotid plaque components with multi-detector computed tomography and histopa-thological correlation Arterioscler Thromb Vase Bio1, 26(10): 2366- 2372.
De Weert TT, de Monye C, et a1. 2008. Assessment of atherosclerotic carotid plaque volume with multi-detector computed tomography angiography. Int J Cardiovasc Imaging, 24(7): 751-759.
Doi K. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential [J].Comput Med Imaging Graph, 31(4-5): 198-211.
D. T. Kuan, A. A. Sawchuk. 1985. Adaptive noise smoothing filter for images with signal dependent noise. IEEE Trans. Pattern Anal. Machine Intell. 7(2): 165–177.
D. T. Kuan, A. A. Sawchuk, T. C. Strand, P.Chavel. 1987. Adaptive restoration of images with speckle. IEEE Trans. Acoust. Speech Signal Processing, ASSP-35: 373-383.
Guo Q, Mandal. M, Li M. 2005. Efficient Hodge-Helmholtz decomposition of motion fields. Pattern Recognit. Lett. 26: 493-501.
Guo Z, Moreau M, Rickey DW, et al. 1995. Quantitative investigation of in vitro flow using three-dimensional color Doppler ultrasound. Ultra-sound Med Biol, 21(6): 807-816.
Hennerici M, Meairs S. 2000. Imaging arterial wall disease. Cerebrovascular Dis. 10(5): 9-20.
H. Tek, B. B. Kimia. 1995. Image segmentation by reaction-diffusion bubbles. in Proc. 5th Int. Conf. Computer Vision, pp. 156–162.
HUBER S, DANES J, ZUNA I, et a1. 2000. Relevance of sonographic B-mode criteria and computer-aided ultrasonic tissue characterization in differential/diagnosis of solid breast masses[J]. Ultras- ound in Med.Biol, 26(8): l243-1252.
Hyafil F, Cornily JC, Feig J, et a1. 2008. Noninvasive detection of macrophages using a nanopar- ticulate contrast agent for computed tomography. Nature Med, 13(5): 636-641.
I. Wendelhag, et al. 1997. A new automated computerized analyzing system simplifies readings and reduces the variability in ultrasound measurement of intima-media thickness. Stroke, 28: 2195-2200.
Jalba A, Wilkinson M, Roerdink J. 2004. CPM: A defommble model for shape recovery andsegmentation based Oil charged particles[J].IEEE Trans. Pattern Analysis and Machine Intelligence, 26(10):1320-1335.
Jierong Cheng, Say Wei Foo. 2006. Dynamic Directional Gradient Vector Flow for Snakes. IEEE Trans. Image Processing. 15(6):1563-1571.
JOO S, YANG Y S, MOON W K, et a1. 2004. Computer-aided diagnosis of solid breast nodules:use of an artificial neural network based on multiple sonographic features[J].Medical Imaging, 23(10):1292-1300.
J. P. Touboul, J. Labreuche, E. Vicaut, et al. 2005. Carotid intima-media thickness, plaques, and Framingham risk score as independent determinants of stroke risk. Stroke, 36(8):1741-1745.
J. S. Lee. 1980. Digital image enhancement and noise filtering by using local statistics. IEEE Trans. Pattern Anal. Machine Intell. 2(2): 165-168.
J. S. Lee. 1981a. Speckle analysis and smoothing of synthetic aperture radar images,Comput. Graph. Image Processing, 17: 24-32.
J. S. Lee. 1981b. Refined filtering of image noise using local statistics. Comput. Graph, Image Processing, 15:380–389.
J. T. Tou, R. C. Gonzalez. 1974. Pattern Recognition Principles. Reading, MA: Addison-Wesley. Kerwin WS, Hooker A, Spilker M, et a1. 2003. Quantitative Magnetic Resonance Imaging Analysis of Neovasculature Volume in Carotid Atherosclerotic Plaque.Circulation, 107(6): 851-856.
Kietselaer BL, Reutelingsperger CP, Heidendal GA, et a1. 2004. Noninvasive detection of plaque instability with use of radio-labeled annexin A5 in patients with carotid-artery atherosclerosis. J Med, 350(14):1472-1473.
Kono Y, Pinnell SP, Sirlin CB, et a1. 2004. Carotid arteries: contrast enhanced US angiography preliminary clinical experience.Radiology, 230(2):561-568.
L. Busse, T. R Crimmins, and J. R. Fienup. 1995. A model based approach to improve the performance of the geometric filtering speckle reduction algorithm, in Proc. IEEE Ultrason. Symp, pp. 1353-1356.
L. D. Cohen. 1991. On active contour models and balloons.CVGIP: Image Understanding, 53(2): 211–218.
Li CM, Xu CY, Gui CF, et al. 2005. Level set evolution without re-initialization: a new Variational formulation [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR). 1: 430-436.
Li Y, Gerbod-Giannone MC, Seitz H, et a1. 2006. Cholesterol-induced apoptotie macrophages elicit an inflammatory response in phagocytes, which is partially attenuated by the Mer receptor. J Bid Chem, 281(10):6707-6717.
Li ZY, Howarth S, Trivedi RA, et a1. 2006. Stress analysis of carotid plaque rupture based on in vivo high resolution MRI. J Biomech, 39(14):2611-2622.
Malladi R, Sethian JA, Vemuri BC. 1995. Shape modeling with front propagation - A level set approach [J]. IEEE Trans Pattern Anal Machine Intell, 17(2): 158-175.
Meairs S, Hennerici M. 1999. Four dimensional ultrasonographic characterization of plaque surface motion m patients with symptomatic and asymptomatic carotid artery stenosis. Stroke, 30(9): 1807-1813.
M. Kass, A. Witkin, D. Terzopoulos. 1987. Snakes: Active contour models. Int.J.Comput Vis, 1: 321–331.
Nandalur KR, Hardie AD, Raghavan P, et a1. 2007. Composition of the stable carotid plaque insights from a multi-detector computed tomography study of plaque volume.Stoke, 38(3):935-940.
Nikos Paragios, Olivier Mellina Gottardo, Visvanathan Ramesh. 2004. Gradient Vector Flow Fast Geometric Active Contours. IEEE Trans. pattern analysis and machine intelligence, 26(3): 402-407.
Nonent M, Serfaty JM, Nighoghossian N, et a1. 2004. Concordance rate differences of 3 noninvasive imaging techniques to measure carotid stenosis in clinical routine practice: results of the CARMEDAS multi-center study. Stroke, 35: 682-686.
Nosir YF, Lequin MH, Kasprzak JD, et al. 1998. Measurements and day-day variabilities of left ventricular volume and ejection fraction by tree-dimensional echocardiography and comparison with magnetic resonance imaging. Am J Cardiology, 82(2):209-214.
Pignoli P, Tremoli E, Poll A, et al. 1986. Intimal plus medial thickness of the arterial wall: a direct measurement with ultrasound imaging.Circulation, 7: 1399.
Prisant LM, Zemel PC, Nichols FT, et al. 1993. Carotid plaque associations among hypertensive patients [J]. Arch Intern Med, 153(4):501-508.
Sahiner B, Petrick N, Chan HP, et al. 2001. Computer-aided characterization of mammo- graphic masses: accuracy of mass segmentation and its effects on characterization [J]. IEEE Trans Med Imaging, 20(12): 1275-1284.
Salonen J T, Salonen R. 1993. Ultrasound B-mode in observational studies of atherosclerotic progression. Circulation, 87:53-56.
SAPIRO G. 2001. Geometric partial differential equations and image analysis[M]. New York:Cambridge University Press.
Shah PK. 1997. New insights into the pathogenesis and prevention of acute coronary syndromes. Am J Cardiology, 79(12):17-23. S. Osher, J. Sethian. 1988. Fronts Propagating with Curvature-Dependent Speed: Algorithms Based on the Hamilton-Jacobi Formulation. J.Computational Phys- ics, 79: 12-49.
Steinke W, Ries S, Artemis N, et a1. 1997. Power Doppler imaging of carotid artery stenosis: Comparison with color Doppler flow imaging and angiography.Stroke, 28: 198l-1987.
Talelli P, Terzis G, et al. 2007. Recurrent stroke: the role of common carotid artery intima-media thickness [J]. J Clin Neurosci, 14 (11):1067-1072.
T. Kohonen. 1990. The self-organizing map. Proc. IEEE. 78(9):1464–1480.
Tueeryan M, Jain AK. 1993. Texture Analysis, Handbook Pattern Recognition and Computer Vision [M].World Scientific, 235-276.
T. Watanabe, S. Koba, M. Kawamura, et al. 2004. Small dense low-density lipoprotein and carotid atherosclerosis in relation to vascular dementia. Metabolism, 53(4): 476-482.
V. S. Frost, J. A. Stiles, K. S. Shanmuggam, J. C. Holtzman. 1982. A model for radar images and its application for adaptive digital filtering of multiplicative noise. IEEE Trans.Pattern Anal. Machine Intell. 4(2): 157-165.
Wang Rui, Zhang Zhaoqi. 2009. Progress on non-invasive imaging evaluation on carotid plaque. Chin J Med Imaging Technol, 25(4):705-707.
Wang. Y, Jia. Y, Liu. L. 2008. Harmonic gradient vector flow external force for snake model. Electronics Letters, 44(2):105-107.
Wikstand J, Wiklund O. 1992. Frontiers in cardiovascular science: Quantitative measurement of Atherosclerotic manifestation in human[J].Arterioscler Thromb, 12(1):114-119.
Wong M, Edelstein J, Wollman J, et al. 1993. Ultrasonic-pathological comparison of the humanarterial Wall: verification of intima-medial thickness. Arterioscler Thromb, 13:482.
Yasnoff W A, Mui J K, Bacus J W. 1977. Error measure for scene segmentation [J]. Pattern Recognition,9(4):217-231.
Yuan C, Kerwin WS, Ferguson MS, et a1. 2002. Contrast enhanced High Resolution MRI for Atherosclerotic Carotid Artery Tissue Characterization [J].J Magn Reson Imaging, 15(1):62-67.
Zhang YJ. 1996a. A survey on evaluation methods for image segmentation [J]. Pattern Recognition, 29(8): 1335-l346.
Zhang YJ. l996b. A classification and comparison of evaluation techniques for image segmentation [J].Joumal of Image and Graphics, l(2):151-l58.
曹之江,郝矿荣,丁永生. 2008.基于GVF-Snake人体轮廓提取的优化算法.计算机工程, 34(22): 204-206.
陈允杰,张建伟. 2004.遗传算法在Snake模型中的应用[J].计算机应用, 24(5): 80-81.
崔华,高立群. 2009.辅以区域力量的梯度矢量流测地线活动轮廓模型.中国图像图形学报, 14(5): 938-943.
侯格贤,毕笃彦,吴成柯. 2000.图象分割质量评价方法研究[J].中国图象图形学报, 5(1): 39-43.
刘丽,匡纲要. 2009.图像纹理特征提取方法综述.中国图像图形学报,14: 622-635.
罗惠韬,章毓晋. 1997.一个图象分割评价实例及讨论[J].数据采集与处理, 12(1): 18-22.
孙阳光,蔡超等. 2009. R.Snake:一种基于边缘与区域信息的图像主动轮廓提取模型.电子学报, 37 (8):1810-1815.
王小东,葛云,李宝生. 2008.一种新的基于GVF-Snake的B超图像分割方法.生物医学工程研究, 27(3): 170-174.
王元全,汤敏,王平安,等. 2005. Snake模型与深度凹陷区域的分割.计算机研究与发展, 42(7): 1179-1184.
汪源源,沈嘉琳,王涌,等. 2006.基于形态特征判别超声图像中乳腺肿瘤的良恶性[J].光学精密工程, 14(2): 333-340.
卫娜,杨继庆,罗建等. 2004.超声技术在医学领域的应用与发展[J].医疗卫生装备, 8: 30-31.
杨丽秀,周长钰. 2008.颈动脉超声在心血管疾病中的应用.Medical Recapitulate, 14(6): 947-949.
姚斌. 2009.一种改进的GVF-Snake模型轮廓检测方法.科技信息, 12: 77-79.
张博,苏永利,张书玲. 2008.一种测地线活动轮廓模型的快速算法.计算机应用研究, 25(6):1765-1767.
张石,董建威,佘黎煌. 2009.医学图像分割算法的评价方法.中国图像图形学报, 14(9):1872-1880.
张玲艳,闫丽,陈颖,张欢. 2009.实现测地线活动轮廓模型的改进变分水平集方法.计算机工程与应用. 45(16): 188-189.
赵辉林,许建荣. 2007.颈动脉粥样硬化斑块MRI研究进展,Radiol Practice, 22(6): 634- 635.
Alexandrow AV, Bladin CF, Murphy J, et al. 1994. Clinical applicability of method to measure carotid stenosis. J Strok Cerebrovas Dis, 4: 256-258.
Amirbekian V, Lipinski M J, et a1. 2007. Detecting and assessing macrophages in vivo to evaluate atherosclerosis non-invasively using molecular MRI. PNAS, 104(3): 961-966.
Arnold JA, Modaresi KB, Thomas N, et a1. 1999. Carotid plaque characterization by duplex scanning: observer error may undermine current clinical trials. Strobe, 30: 6l-65.
A. Yezzi, A. Tsai, A. Willsky. 1999. A statistical approach to snakes for bimodal and tri-modal imagery. Proc. IEEE Int’l Conf. Computer Vision, pp. 898-903.
Belohlavek M, Foley DA, Gerber TC, et al. 1993. Three- and four-dimensional cardiovascular ultrasound imaging: a new era for echocardiography. Mayo Clin Proc, 68(3): 221-249.
Bomithon KP, Vaviver J, Anne T, et al. 1993. Early carotid atherosclerosis in healthy middle-aged women: a follow-up study [J]. Stroke, 24: 1837-1842.
Bradley JE, Brian B. 2002. Computer-aided detection and diagnosis at the start of the third millennium [J]. J Digit Imaging, 15(2): 59-68.
Byun JH, Kim TK, Lee SS, et a1. 2003. Evaluation of the hepatic artery in potential donors for living donor liver transplantation by computed tomography angiography using multi-detector row computed tomography: comparison of volume rendering and maximum intensity projection techniques. J Comput Assist Tomngr, 27(2): 125-131.
Cai J, Hatsukami TS, Ferguson MS, et a1. 2005. In vivo quantitative measurement of intact fibr- ous cap and lipid rich necrotic core size in atherosclerotie carotid plaque: a comparison of high resolution contrast enhanced MRI and histology.Circulation, 12(22): 3437-3444.
Canny J. 1986. A computational approach to edge detection [J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6): 679-698.
Caselles V, Catte F, Coll T, et al. 1993. A geometric model for active contours in image processing [J]. Numerische Mathematik, 66(1): 1-31.
Chalana V, Kim Y. 1997. A methodology for evaluation of boundary detection algorithms on medical images [J]. IEEE Transactions on medical imaging, 16(5): 642-652.
CHEN DR, CHANG RF, et a1. 2002. Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks [J]. Ultrasound in Med. Biol, 28(10):1301-1310.
CHOU YH, TIU CM, HUNG GS, et a1. 2001. Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis [J]. Ultrasound in Med. Biol, 27(11): 1493-1498.
Christos P. Loizou, Constantinos S. Pattichis, et al. 2005. Comparative Evaluation of Despeckle Filtering In Ultrasound Imaging of the Carotid Artery. IEEE Trans. Ultrasonics, Ferroelectrics, and Frequency Control, 52(10): 1653-1669.
C. I. Christodoulou, C. Loizou, C. S. Pattichis, et al. 2002. Despeckle filtering in ultrasound imaging of the carotid artery.in Proc. Second Joint Eng. Med. Biol./Biomed. Eng.Soc: 1027–1028.
C. I. Christodoulou, C. S. Pattichis, et al. 2003. Texture-Based Classification of Atherosclerotic Carotid Plaques. IEEE Trans. Medical Imaging, 22(7): 902-912.
C. Metz. 1978. Basic principles of ROC analysis. Semin. Nucl. Medic, 8: 283-298.
Coli S, Magnoni M, Sangiorgi, et a1. 2008. Contrast enhanced ultrasound imaging of intra-plaque neovascularization in carotid arteries. J Am Col1 Cardio1, 52(3):223-230.
C. Xu, J. Prince. 1998. Snakes, Shapes, and Gradient Vector Flow.IEEETrans.Image Processing, 7: 359-369.
C. Xu, J. L. Prince. 1998. Generalized gradient vector flow external forces for active contours. Signal Process. 71: 131-139
De Weert TT, Ouhlous M, Meijering E, et a1. 2006. In vivo characterization and quantification of atherosclerotic carotid plaque components with multi-detector computed tomography and histopa-thological correlation Arterioscler Thromb Vase Bio1, 26(10): 2366- 2372.
De Weert TT, de Monye C, et a1. 2008. Assessment of atherosclerotic carotid plaque volume with multi-detector computed tomography angiography. Int J Cardiovasc Imaging, 24(7): 751-759.
Doi K. 2007. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential [J].Comput Med Imaging Graph, 31(4-5): 198-211.
D. T. Kuan, A. A. Sawchuk. 1985. Adaptive noise smoothing filter for images with signal dependent noise. IEEE Trans. Pattern Anal. Machine Intell. 7(2): 165–177.
D. T. Kuan, A. A. Sawchuk, T. C. Strand, P.Chavel. 1987. Adaptive restoration of images with speckle. IEEE Trans. Acoust. Speech Signal Processing, ASSP-35: 373-383.
Guo Q, Mandal. M, Li M. 2005. Efficient Hodge-Helmholtz decomposition of motion fields. Pattern Recognit. Lett. 26: 493-501.
Guo Z, Moreau M, Rickey DW, et al. 1995. Quantitative investigation of in vitro flow using three-dimensional color Doppler ultrasound. Ultra-sound Med Biol, 21(6): 807-816.
Hennerici M, Meairs S. 2000. Imaging arterial wall disease. Cerebrovascular Dis. 10(5): 9-20.
H. Tek, B. B. Kimia. 1995. Image segmentation by reaction-diffusion bubbles. in Proc. 5th Int. Conf. Computer Vision, pp. 156–162.
HUBER S, DANES J, ZUNA I, et a1. 2000. Relevance of sonographic B-mode criteria and computer-aided ultrasonic tissue characterization in differential/diagnosis of solid breast masses[J]. Ultras- ound in Med.Biol, 26(8): l243-1252.
Hyafil F, Cornily JC, Feig J, et a1. 2008. Noninvasive detection of macrophages using a nanopar- ticulate contrast agent for computed tomography. Nature Med, 13(5): 636-641.
I. Wendelhag, et al. 1997. A new automated computerized analyzing system simplifies readings and reduces the variability in ultrasound measurement of intima-media thickness. Stroke, 28: 2195-2200.
Jalba A, Wilkinson M, Roerdink J. 2004. CPM: A defommble model for shape recovery andsegmentation based Oil charged particles[J].IEEE Trans. Pattern Analysis and Machine Intelligence, 26(10):1320-1335.
Jierong Cheng, Say Wei Foo. 2006. Dynamic Directional Gradient Vector Flow for Snakes. IEEE Trans. Image Processing. 15(6):1563-1571.
JOO S, YANG Y S, MOON W K, et a1. 2004. Computer-aided diagnosis of solid breast nodules:use of an artificial neural network based on multiple sonographic features[J].Medical Imaging, 23(10):1292-1300.
J. P. Touboul, J. Labreuche, E. Vicaut, et al. 2005. Carotid intima-media thickness, plaques, and Framingham risk score as independent determinants of stroke risk. Stroke, 36(8):1741-1745.
J. S. Lee. 1980. Digital image enhancement and noise filtering by using local statistics. IEEE Trans. Pattern Anal. Machine Intell. 2(2): 165-168.
J. S. Lee. 1981a. Speckle analysis and smoothing of synthetic aperture radar images,Comput. Graph. Image Processing, 17: 24-32.
J. S. Lee. 1981b. Refined filtering of image noise using local statistics. Comput. Graph, Image Processing, 15:380–389.
J. T. Tou, R. C. Gonzalez. 1974. Pattern Recognition Principles. Reading, MA: Addison-Wesley. Kerwin WS, Hooker A, Spilker M, et a1. 2003. Quantitative Magnetic Resonance Imaging Analysis of Neovasculature Volume in Carotid Atherosclerotic Plaque.Circulation, 107(6): 851-856.
Kietselaer BL, Reutelingsperger CP, Heidendal GA, et a1. 2004. Noninvasive detection of plaque instability with use of radio-labeled annexin A5 in patients with carotid-artery atherosclerosis. J Med, 350(14):1472-1473.
Kono Y, Pinnell SP, Sirlin CB, et a1. 2004. Carotid arteries: contrast enhanced US angiography preliminary clinical experience.Radiology, 230(2):561-568.
L. Busse, T. R Crimmins, and J. R. Fienup. 1995. A model based approach to improve the performance of the geometric filtering speckle reduction algorithm, in Proc. IEEE Ultrason. Symp, pp. 1353-1356.
L. D. Cohen. 1991. On active contour models and balloons.CVGIP: Image Understanding, 53(2): 211–218.
Li CM, Xu CY, Gui CF, et al. 2005. Level set evolution without re-initialization: a new Variational formulation [C]. IEEE Conf Computer Vision Pattern Recognition (CVPR). 1: 430-436.
Li Y, Gerbod-Giannone MC, Seitz H, et a1. 2006. Cholesterol-induced apoptotie macrophages elicit an inflammatory response in phagocytes, which is partially attenuated by the Mer receptor. J Bid Chem, 281(10):6707-6717.
Li ZY, Howarth S, Trivedi RA, et a1. 2006. Stress analysis of carotid plaque rupture based on in vivo high resolution MRI. J Biomech, 39(14):2611-2622.
Malladi R, Sethian JA, Vemuri BC. 1995. Shape modeling with front propagation - A level set approach [J]. IEEE Trans Pattern Anal Machine Intell, 17(2): 158-175.
Meairs S, Hennerici M. 1999. Four dimensional ultrasonographic characterization of plaque surface motion m patients with symptomatic and asymptomatic carotid artery stenosis. Stroke, 30(9): 1807-1813.
M. Kass, A. Witkin, D. Terzopoulos. 1987. Snakes: Active contour models. Int.J.Comput Vis, 1: 321–331.
Nandalur KR, Hardie AD, Raghavan P, et a1. 2007. Composition of the stable carotid plaque insights from a multi-detector computed tomography study of plaque volume.Stoke, 38(3):935-940.
Nikos Paragios, Olivier Mellina Gottardo, Visvanathan Ramesh. 2004. Gradient Vector Flow Fast Geometric Active Contours. IEEE Trans. pattern analysis and machine intelligence, 26(3): 402-407.
Nonent M, Serfaty JM, Nighoghossian N, et a1. 2004. Concordance rate differences of 3 noninvasive imaging techniques to measure carotid stenosis in clinical routine practice: results of the CARMEDAS multi-center study. Stroke, 35: 682-686.
Nosir YF, Lequin MH, Kasprzak JD, et al. 1998. Measurements and day-day variabilities of left ventricular volume and ejection fraction by tree-dimensional echocardiography and comparison with magnetic resonance imaging. Am J Cardiology, 82(2):209-214.
Pignoli P, Tremoli E, Poll A, et al. 1986. Intimal plus medial thickness of the arterial wall: a direct measurement with ultrasound imaging.Circulation, 7: 1399.
Prisant LM, Zemel PC, Nichols FT, et al. 1993. Carotid plaque associations among hypertensive patients [J]. Arch Intern Med, 153(4):501-508.
Sahiner B, Petrick N, Chan HP, et al. 2001. Computer-aided characterization of mammo- graphic masses: accuracy of mass segmentation and its effects on characterization [J]. IEEE Trans Med Imaging, 20(12): 1275-1284.
Salonen J T, Salonen R. 1993. Ultrasound B-mode in observational studies of atherosclerotic progression. Circulation, 87:53-56.
SAPIRO G. 2001. Geometric partial differential equations and image analysis[M]. New York:Cambridge University Press.
Shah PK. 1997. New insights into the pathogenesis and prevention of acute coronary syndromes. Am J Cardiology, 79(12):17-23. S. Osher, J. Sethian. 1988. Fronts Propagating with Curvature-Dependent Speed: Algorithms Based on the Hamilton-Jacobi Formulation. J.Computational Phys- ics, 79: 12-49.
Steinke W, Ries S, Artemis N, et a1. 1997. Power Doppler imaging of carotid artery stenosis: Comparison with color Doppler flow imaging and angiography.Stroke, 28: 198l-1987.
Talelli P, Terzis G, et al. 2007. Recurrent stroke: the role of common carotid artery intima-media thickness [J]. J Clin Neurosci, 14 (11):1067-1072.
T. Kohonen. 1990. The self-organizing map. Proc. IEEE. 78(9):1464–1480.
Tueeryan M, Jain AK. 1993. Texture Analysis, Handbook Pattern Recognition and Computer Vision [M].World Scientific, 235-276.
T. Watanabe, S. Koba, M. Kawamura, et al. 2004. Small dense low-density lipoprotein and carotid atherosclerosis in relation to vascular dementia. Metabolism, 53(4): 476-482.
V. S. Frost, J. A. Stiles, K. S. Shanmuggam, J. C. Holtzman. 1982. A model for radar images and its application for adaptive digital filtering of multiplicative noise. IEEE Trans.Pattern Anal. Machine Intell. 4(2): 157-165.
Wang Rui, Zhang Zhaoqi. 2009. Progress on non-invasive imaging evaluation on carotid plaque. Chin J Med Imaging Technol, 25(4):705-707.
Wang. Y, Jia. Y, Liu. L. 2008. Harmonic gradient vector flow external force for snake model. Electronics Letters, 44(2):105-107.
Wikstand J, Wiklund O. 1992. Frontiers in cardiovascular science: Quantitative measurement of Atherosclerotic manifestation in human[J].Arterioscler Thromb, 12(1):114-119.
Wong M, Edelstein J, Wollman J, et al. 1993. Ultrasonic-pathological comparison of the humanarterial Wall: verification of intima-medial thickness. Arterioscler Thromb, 13:482.
Yasnoff W A, Mui J K, Bacus J W. 1977. Error measure for scene segmentation [J]. Pattern Recognition,9(4):217-231.
Yuan C, Kerwin WS, Ferguson MS, et a1. 2002. Contrast enhanced High Resolution MRI for Atherosclerotic Carotid Artery Tissue Characterization [J].J Magn Reson Imaging, 15(1):62-67.
Zhang YJ. 1996a. A survey on evaluation methods for image segmentation [J]. Pattern Recognition, 29(8): 1335-l346.
Zhang YJ. l996b. A classification and comparison of evaluation techniques for image segmentation [J].Joumal of Image and Graphics, l(2):151-l58.
曹之江,郝矿荣,丁永生. 2008.基于GVF-Snake人体轮廓提取的优化算法.计算机工程, 34(22): 204-206.
陈允杰,张建伟. 2004.遗传算法在Snake模型中的应用[J].计算机应用, 24(5): 80-81.
崔华,高立群. 2009.辅以区域力量的梯度矢量流测地线活动轮廓模型.中国图像图形学报, 14(5): 938-943.
侯格贤,毕笃彦,吴成柯. 2000.图象分割质量评价方法研究[J].中国图象图形学报, 5(1): 39-43.
刘丽,匡纲要. 2009.图像纹理特征提取方法综述.中国图像图形学报,14: 622-635.
罗惠韬,章毓晋. 1997.一个图象分割评价实例及讨论[J].数据采集与处理, 12(1): 18-22.
孙阳光,蔡超等. 2009. R.Snake:一种基于边缘与区域信息的图像主动轮廓提取模型.电子学报, 37 (8):1810-1815.
王小东,葛云,李宝生. 2008.一种新的基于GVF-Snake的B超图像分割方法.生物医学工程研究, 27(3): 170-174.
王元全,汤敏,王平安,等. 2005. Snake模型与深度凹陷区域的分割.计算机研究与发展, 42(7): 1179-1184.
汪源源,沈嘉琳,王涌,等. 2006.基于形态特征判别超声图像中乳腺肿瘤的良恶性[J].光学精密工程, 14(2): 333-340.
卫娜,杨继庆,罗建等. 2004.超声技术在医学领域的应用与发展[J].医疗卫生装备, 8: 30-31.
杨丽秀,周长钰. 2008.颈动脉超声在心血管疾病中的应用.Medical Recapitulate, 14(6): 947-949.
姚斌. 2009.一种改进的GVF-Snake模型轮廓检测方法.科技信息, 12: 77-79.
张博,苏永利,张书玲. 2008.一种测地线活动轮廓模型的快速算法.计算机应用研究, 25(6):1765-1767.
张石,董建威,佘黎煌. 2009.医学图像分割算法的评价方法.中国图像图形学报, 14(9):1872-1880.
张玲艳,闫丽,陈颖,张欢. 2009.实现测地线活动轮廓模型的改进变分水平集方法.计算机工程与应用. 45(16): 188-189.
赵辉林,许建荣. 2007.颈动脉粥样硬化斑块MRI研究进展,Radiol Practice, 22(6): 634- 635.