摘要
动脉粥样硬化（Atherosclerosis，AS），缺血性中风（Transient Ischemic Stroke，TIS）和突发性心脏病（Heart Attack），属于世界上致死的第一大疾病---心脑血管疾病（Cardiovascular and Cerebrovascular Diseases，CVDs），每年都造成了巨大的经济损失，也给无数家庭带来痛苦。改进检测和治疗技术、正确评估和确定病人中风的风险概率、提高风险因子的预测能力，对于降低该疾病的死亡率将产生巨大的影响。
颈动脉粥样硬化常常在主颈动脉（Common Carotid Artery，CCA）的分叉处（Bifurcation，BF）产生血栓栓塞，导致脑动脉的阻塞，形成中风。该疾病大多可以通过调节生活方式、改变饮食结构在早期加以防治；后期则可以通过药物治疗、颈动脉支架手术（Carotid Artery Stenting，CAS）、颈动脉内膜切除术（Carotid ArterialEndarterectomy，CAE）等加以缓解。目前，研究AS的发生与发展，特别是对颈动脉斑块治疗反应的对比及监控，是以“开发敏感的风险因子评价技术”、“识别高风险的病人”和“减少发生中风的概率”为主要发展战略。
在临床应用上，现阶段超声普查（Ultrasound screening）对晚期、高发的AS人群效果较好，统计学上具有显著意义；然而，对早期、无症状或症状不明显的病患容易产生漏检的情况。三维（Three-dimensional，3D）超声作为传统二维（Two-dimensional，2D）超声的一个重要发展，在“颈动脉粥样硬化诊断”和“易损斑块识别”中具有重要的临床价值。因此，基于三维超声图像的颈动脉血管的实时分割、药效的分析评价和斑块的准确识别与定性，是本论文的主要研究方向。
本论文的主要研究内容旨在：以颈动脉三维超声作为一种低成本、高敏感的测量工具，来确定加重颈动脉粥样硬化的风险因素，并评估颈动脉粥样硬化的治疗效果。所以，本论文的研究手段是：将颈动脉三维超声（Three-dimensional Ultrasound，3D US）成像技术，作为一种新的监测颈动脉粥样硬化变化的手段，通过对颈动脉粥样硬化的表型特征（phenotypic characteristics）量化与分析，验证这种无创、定量的三维颈动脉成像方法的临床适用性。其中颈动脉粥样硬化的表型是指：颈动脉和斑块的形态、功能等各方面的表现，如厚度、大小、形状、体积、回声性质、药物耐受力乃至其易损性等等。本论文的研究目标是：通过纵截面和横截面的血管分割，提取并确定易损斑块的重要特征，提供一种评估颈动脉斑块生长或消亡（progressionand regression）的低成本和高敏感方法，并提供反应斑块稳定性治疗的有用信息。
因此，本论文在建立灵敏、重复性好的三维超声成像系统上，具体地量化与分析以下四个颈动脉粥样硬化的表型特征：局部和整个血管壁内中膜厚度（Intima-media Thickness，IMT）；斑块总面积和总体积（Total PlaqueArea，TPA；TotalPlaque Volume，TPV）；血管体积（Vessel Wall Volume，VWV）；斑块形态与纹理特征，并能监测、比较这些特征的变化。
本论文按照上述研究方向、研究内容和研究目标，已完成的三个具体研究工作包括：
（1）提出了一种半自动的“基于主颈动脉分叉点和中轴切分的血管厚度测量方法”。为了能获得三维体数据中血管局部和整体平均厚度信息，该方法基于主颈动脉分叉点和中轴，对超声三维体数据按三视图方向切分，依次得到二维横断面、冠状面和矢状面序列图像；分别处理上述序列图像，统计得到最终的主颈动脉血管壁内外轮廓和血管壁厚度等信息。该方法克服现有计算机辅助诊断中血管分割方法计算复杂度大、主观因素易造成误差等缺点，能快速、准确、完整地获得颈部超声主颈动脉血管的局部和整体信息；与手动分割方法相比，操作便捷，所得的血管局部和整体平均厚度信息，可作为衡量颈部粥样硬化程度的指标，进而用于心脑血管疾病辅助诊断和防治。
（2）在实现“主动轮廓模型（Active Contour Model，ACM）和数学形态学的混合方法”分割血管内外轮廓后，进一步应用主动形状模型（Active Shape Models，ASM）方法及其改进（ImprovedActive Shape Models，I-ASM）方法、主动外观模型（ActiveAppearance Models，AAM）方法，应用于多种颈动脉外轮廓（Media–adventitiaBoundary，MAB）和内轮廓（Lumen–intima Boundary，LIB）分割，并在算法间进行横向比较，与金标准进行纵向比较，从而进行算法的量化分析。该算法能够在5分钟内完成分割，其产生的平均偏差小于人工手动分割偏差的一半；采用距离、面积等测度和体积误差，评价算法的鲁棒性，并用统计分析方法衡量两个专家用本算法分割结果的一致性。实验结果和数据分析均表明：该算法的分割效果接近金标准，可为今后的辅助诊疗系统提供指导意义。
（3）经仿真体模和超声体模验证模拟的血流介导扩张（Flow Mediated Dilation，FMD）功能后，开发和验证一种半自动软件工具，来量化斑块的特征并用于评估颈动脉粥样硬化的治疗效果。颈动脉斑块的病理生理学研究表明，颈动脉斑块的形态和纹理的特征，是识别易损斑块和监测疾病发展的关键。提取斑块的形态、纹理、弹性的多维多类特征，并分别采用反向传播神经网络（Back Propagation NeuralNetwork，BPNN）、支撑向量机（Support Vector Machine，SVM）作为分类器，对特征集合进行识别判决，准确度分别为84%和91%，随后采用ROC（Receiver OperatingCharacteristic）曲线和AUC（Area Under Curve）面积对分类器性能进行了分析、比较。
上述方法与软件均通过三维颈动脉超声病人图像初步验证。实验结果表明：本论文的血管壁内中膜厚度测量、血管内外轮廓分割方法、粥样硬化体模仿真的定量与定性分析及斑块多维多类特征的提取与分类，结合相关危险因素，可综合评价药效，进而判决斑块易损性，对心脑血管疾病的诊断与治疗有重要临床意义。
Atherosclerosis (AS) and its sequelae, transient ischemic stroke (TIS) and heartattacks are the leading causes of mortality and morbidity in the developed world, and areincreasing in the developing countries. Cardiovascular and Cerebrovascular Diseases(CVDs) represent a staggering mortality, morbidity, and economic cost in the worldwide.Therefore, improved methods to identify patients at increased risk of stroke, torecommend advanced techniques to detect and treat the disease, and monitor them willhave an enormous impact.
Most TIS are due to the blockage of a cerebral artery by a thrombotic embolusgenerated at the bifurcation (BF) of the common carotid artery (CCA). Most of thesestrokes can be prevented by lifestyle/dietary changes, medical and surgical treatment, suchas drug therapy, carotid artery stenting (CAS) and Carotid Arterial Endarterectomy (CAE)surgeries. Nowadays, researches on new strategies for treating atherosclerosis, such asimproving identification of patients, who are at risk for stroke, and developing sensitivetechniques for monitoring of carotid plaque response to therapy, will be great helpful forthe management of these patients, and decrease the risk of stroke.
B-mode ultrasound (US) had been widely used for AS screen examination and onlysensitive for those late stage patients in clinic. Three-dimensional (3D) ultrasound not onlyhas the Two-dimensional (2D) US advantages, but also has special capabilities in earlystage AS diagnose and vulnerable plaque identification. Therefore, this thesis researchorientation was focused on real-time carotid artery segmentation, quantification ofatorvastatin effective evaluation and plaque characterize classification.
We propose that3D carotid US can provide cost-effective, sensitive and specificmeasurement tools. The tools are critically needed to define novel risk factors thataggravate atherosclerosis, and to assess efficacy of therapies for carotid atherosclerosis asthe research contents. The research means, therefore, of this study is to verify thenon-invasive, quantitative three-dimensional carotid ultrasound imaging technologyclinical capability, by applying it as one of the new means for monitoring carotidatherosclerosis change based on the carotid atherosclerotic phenotypic characteristicsquantification and analysis. And the carotid atherosclerosis phenotype are carotidmorphology, function and other aspects of its performance, such as thickness, size, shape,volume, echo features and drug tolerance, and so on. The objective of this paper is toprovide a both low cost, high sensitive method for assessment of carotid plaqueprogression and regression, and some useful information of plaque reaction to stabilizationtherapies treatment, by segmentation on longitudinal and transverse sections of the carotidartery, identification of the important risk factors that will distinguish patients who havevulnerable plaques.
Our purposes are to develop sensitive and reproducible3D US imaging softwaretools that will allow semi-automated measurement of the following4imaging carotidatherosclerosis phenotypes: local and global vessel wall intima-media thickness (IMT); total plaque thickness, area (TPA) and volume (TPV); and vessel wall volume (VWV);plaque surface morphology and composition, and to provide software imaging tools formonitoring changes in these measures.
In order to achieve that, we propose the following3specific technical objectives:
(1) In this paper, an integrated segmentation method for3D US carotid artery basedon bifurcation and medial axis was proposed.3D US image was sliced into transverse,coronal and sagittal2D images on the carotid bifurcation point. Then, the three imageswere processed respectively, and the carotid artery contours and thickness were obtainedfinally. This paper tries to overcome the disadvantages of current computer aideddiagnosis method, such as high computational complexity, easily introduced subjectiveerrors et al. The proposed method could get the carotid artery overall information rapidly,accurately and completely. It could be transplanted into clinical usage for atherosclerosisdiagnosis and prevention.
(2) The following method, Active Contour Model (ACM) with mathematicalmorphology, Active Shape Models (ASM), and its improved version (Improved ActiveShape Models, I-ASM) and Active Appearance Models (AAM), were proposed on carotidartery transverse view for media–adventitia boundary (MAB) and lumen–intima boundary(LIB) segmentations. Different algorithms were compared between and with the manualsegmentation results which was the golden standard. The proposed semi-automatedsegmentation method could outline the carotid wall and lumen boundaries in5minutes,with a variance a factor of2compared with manual segmentation.
(3) The computer simulation phantom and agar phantom were used for the carotidvessel Flow Mediated Dilation (FMD) function measurement validation. And featuresextraction software tool was developed based on those phantom experiments forquantification drug therapy evaluation. The pathophysiology of carotid plaques indicatesthat morphological and compositional characterization is necessary for identification ofvulnerable plaques and monitoring disease progression and regression. Optimizationfeatures, extracted from all the morphology, texture and elastic features, were sent toclassifier such as: Back Propagation Neural Network (BPNN) and Support VectorMachine (SVM) for classification, as of84%and91%accuracy respectively. Then,Receiver Operating Characteristic (ROC) and Area Under Curve (AUC) were used for thevalidation and evaluation.
All the proposed methods, including IMT measurement, MAB/LIB segmentation,phantom simulations and features extraction and classification, were testified by the realpatient data on3D US images. And the experiments results indicate that the proposedmethods can promote the carotid3D US usage for a fast, safe and economical monitoringof the atherosclerotic disease progression and regression during therapy. The proposedmethod would accelerate the translation of3D US to clinical application and be asignificant role for CVDs diagnose and treatment.
引文
[1] Celermajer, D. S.,Chow, C. K.,Marijon, E., et al. Cardiovascular Disease in theDeveloping World: Prevalences, Patterns, and the Potential of Early DiseaseDetection. Journal of the American College of Cardiology,2012,60(14):1207-1216.
[2]邹春鹏,吴笑英,黄品同,等.2型糖尿病合并高脂血症患者颈动脉内膜-中层厚度与动脉弹性的相关性研究.中华超声影像学杂志,2010,(3):212-215.
[3]吴长君,张璐,张春梅,等.应用内中膜厚度及动脉僵硬度定量检测技术评价高血压患者颈动脉弹性.中华超声影像学杂志,2011,20(5):386-389.
[4] Guin, A.,Chatterjee Adhikari, M.,Chakraborty, S., et al. Effects of diseasemodifying anti-rheumatic drugs on subclinical atherosclerosis and endothelialdysfunction which has been detected in early rheumatoid arthritis:1-year follow-upstudy. In Seminars in arthritis and rheumatism,2013.
[5] Go, A. S.,Mozaffarian, D.,Roger, V. L., et al. Heart Disease and StrokeStatistics—2013Update A Report From the American Heart Association.Circulation,2013,127(1): e6-e245.
[6]贺顺龙,朱兆洪,陈宝国,等.超声检测脑血管病高危人群颈动脉内皮舒张功能.中国动脉硬化杂志,2004,12(2):206-208.
[7] Lloyd-Jones, D.,Adams, R. J.,Brown, T. M., et al. Heart disease and strokestatistics—2010update. Circulation,2010,121(7): e46-e215.
[8]李秋萍,华扬.颈动脉粥样硬化的超声检测与临床相关性研究进展.中国脑血管病杂志,2009,6(6):317-321.
[9]胡大一,向小平.动脉粥样硬化早期检测的临床应用.中国心血管病研究杂志,2007,5(2):82-82.
[10] Gillard, J.,Graves, M.,Hatsukami, T., et al. Carotid disease: the role of imaging indiagnosis and management. Cambridge University Press,2006.
[11] Ge, J.,Chirillo, F.,Schwedtmann, J., et al. Screening of ruptured plaques in patientswith coronary artery disease by intravascular ultrasound. Heart,1999,81(6):621-627.
[12] Stensland-Bugge, E.,Bonaa, K. H.,Joakimsen, O. Reproducibility ofultrasonographically determined intima-media thickness is dependent on arterialwall thickness. The Tromso Study. Stroke, Oct,1997,28(10):1972-80.
[13] Egger, M.,Krasinski, A.,Rutt, B. K., et al. Comparison of B-mode ultrasound,3-dimensional ultrasound, and magnetic resonance imaging measurements ofcarotid atherosclerosis. Journal of Ultrasound in Medicine,2008,27(9):1321-1334.
[14] Nakamura, T.,Obata, J.-e.,Hirano, M., et al. Endothelial vasomotor dysfunction inthe brachial artery predicts the short-term development of early stage renaldysfunction in patients with coronary artery disease. International journal ofcardiology,2011,148(2):183-188.
[15]滕长青,沈玲,文剑,等.动脉粥样硬化诊疗技术在老年医学领域的运用管理.中华现代医院管理杂志,2012,9(6):31-34.
[16] Spence, J. D. Technology insight: ultrasound measurement of carotidplaque—patient management, genetic research, and therapy evaluation. NatureClinical Practice Neurology,2006,2(11):611-619.
[17]张娜,刘新,张元亭. MRI检测易损斑块的优势与不足.磁共振成像,2010,1(006):415-421.
[18]张梅.超声技术对动脉血管弹性和血液流场检测的研究进展.中华医学超声杂志(电子版),2009,(02):231-233.
[19] Johannsen, W. The Genotype Conception of Heredity. The American Naturalist,1911,45(531):129-159.
[20] Churchill, F. William Johannsen and the genotype concept. J Hist Biol,1974/03/01,1974,7(1):5-30.
[21] Yang, X.,He, W.,Li, K., et al. A review an artery wall segmentation techniques andintima-media thickness measurement for carotid ultrasound images. Journal ofInnovative Optical Health Sciences,2012,5(1):1230001-1230011.
[22] Ukwatta, E.,Awad, J.,Ward, A. D., et al. Three-dimensional ultrasound of carotidatherosclerosis: Semiautomated segmentation using a level set-based method.Medical Physics,2011,38(5):2479-2493.
[23] Molinari, F.,Zeng, G.,Suri, J. S. Review: A state of the art review on intima-mediathickness (IMT) measurement and wall segmentation techniques for carotidultrasound. Comput. Methods Prog. Biomed.,2010,100(3):201-221.
[24] Bots, M. L.,Hoes, A. W.,Koudstaal, P. J., et al. Common Carotid Intima-MediaThickness and Risk of Stroke and Myocardial Infarction: The Rotterdam Study.Circulation, September2,1997,1997,96(5):1432-1437.
[25] Spence, J. D.,Eliasziw, M.,DiCicco, M., et al. Carotid Plaque Area. Stroke,2002,33(12):2916-2922.
[26] Landry, A.,Spence, J. D.,Fenster, A. Measurement of carotid plaque volume by3-dimensional ultrasound. Stroke,2004,35(4):864-869.
[27] Ainsworth, C. D.,Blake, C. C.,Tamayo, A., et al.3D ultrasound measurement ofchange in carotid plaque volume: a tool for rapid evaluation of new therapies.Stroke, Sep,2005,36(9):1904-1909.
[28] Krasinski, A.,Chiu, B.,Spence, J. D., et al. Three-dimensional ultrasoundquantification of intensive statin treatment of carotid atherosclerosis. Ultrasound inmedicine&biology,2009,35(11):1763-1772.
[29] Egger, M.,Spence, J. D.,Fenster, A., et al. Validation of3D ultrasound vessel wallvolume: an imaging phenotype of carotid atherosclerosis. Ultrasound in medicine&biology,2007,33(6):905-914.
[30] Pignoli, P. Ultrasound B-mode imaging for arterial wall thickness measurement.Atherosclerosis Reviews1984,12177-184.
[31] Pignoli, P.,Tremoli, E.,Poli, A., et al. Intimal plus medial thickness of the arterialwall: a direct measurement with ultrasound imaging. Circulation,1986,74(6):1399-1406.
[32]许先进,董旭.颈动脉内膜中膜厚度的临床研究进展.中国动脉硬化杂志,2008,16(8):665-668.
[33] Helfand, M.,Buckley, D. I.,Freeman, M., et al. Emerging risk factors for coronaryheart disease: a summary of systematic reviews conducted for the U.S. PreventiveServices Task Force. Annals of internal medicine, Oct6,2009,151(7):496-507.
[34] O'Leary, D. H.,Polak, J. F.,Kronmal, R. A., et al. Carotid-artery intima and mediathickness as a risk factor for myocardial infarction and stroke in older adults. NewEngland Journal of Medicine,1999,340(1):14-22.
[35] Spence, J. D. Measurement of intima‐media thickness vs. carotid plaque: uses inpatient care, genetic research and evaluation of new therapies. International Journalof Stroke,2006,1(4):216-221.
[36] Spence, J. D. Ultrasound measurement of carotid plaque as a surrogate outcome forcoronary artery disease. The American journal of cardiology,2002,89(4):10-15.
[37] Fenster, A.,Blake, C.,Gyacskov, I., et al.3D ultrasound analysis of carotid plaquevolume and surface morphology. Ultrasonics,2006,44e153-e157.
[38] Schminke, U.,Hilker, L.,Motsch, L., et al. Volumetric Assessment of PlaqueProgression With3‐Dimensional Ultrasonography Under Statin Therapy. Journalof Neuroimaging,2002,12(3):245-251.
[39] Landry, A.,Spence, J. D.,Fenster, A. Quantification of carotid plaque volumemeasurements using3D ultrasound imaging. Ultrasound in medicine&biology,2005,31(6):751-762.
[40] Buchanan, D. N.,Lindenmaier, T.,McKay, S., et al. The Relationship of CarotidThree-Dimensional Ultrasound Vessel Wall Volume with Age and Sex: Comparisonto Carotid Intima-Media Thickness. Ultrasound in medicine&biology, Jul,2012,38(7):1145-53.
[41] Yang, X.,Wang, R.,Li, L., et al. Classification of atorvastatin effect based on shapeand texture features in ultrasound images. In Proc. SPIE8669, Medical Imaging2013: Image Processing, Lake Buena Vista (Orlando Area), Florida, USA, February09,2013;86690S-86696S.
[42]王亚斌,王慎旭,曹丰.动脉粥样硬化易损斑块的分子影像研究进展.生物物理学报,2011,27(4).
[43] Buchanan, D.,Gyacskov, I.,Ukwatta, E., et al. Semi-automated segmentation ofcarotid artery total plaque volume from three dimensional ultrasound carotidimaging. In Molthen, R. C.,Weaver, J. B., SPIE Medical Imaging, San Diego,California, USA,2012;83170I-83170I-7.
[44] Macskassy, S. A. Using graph-based metrics with empirical risk minimization tospeed up active learning on networked data. In Proceedings of the15th ACMSIGKDD international conference on Knowledge discovery and data mining,2009;597-606.
[45] Pignoli, P.,Longo, T. Evaluation of atherosclerosis with B-mode ultrasound imaging.The Journal of nuclear medicine and allied sciences,1988,32(3):166-173.
[46] Touboul, P. J.,Prati, P.,Scarabin, P. Y., et al. Use of monitoring software to improvethe measurement of carotid wall thickness by B-mode imaging. Journal ofhypertension,1992,10S37-S42.
[47] Touboul, P. J.,Hennerici, M. G.,Meairs, S., et al. Mannheim intima-media thicknessconsensus. Cerebrovascular Diseases,2004,18(4):346-349.
[48] Touboul, P. J.,Hennerici, M. G.,Meairs, S., et al. Mannheim carotid intima mediathickness consensus (2004-2006). Cerebrovascular Diseases,2006,23(1):75-80.
[49] Touboul, P. J.,Hernandez Hernandez, R.,Kucukoglu, S., et al. Carotid artery intimamedia thickness, plaque and framingham cardiovascular score in Asia,Africa/Middle East and Latin America: the PARC-AALA Study. The InternationalJournal of Cardiovascular Imaging (formerly Cardiac Imaging),2007,23(5):557-567.
[50] Wendelhag, I.,Liang, Q.,Gustavsson, T., et al. A new automated computerizedanalyzing system simplifies readings and reduces the variability in ultrasoundmeasurement of intima-media thickness. Stroke,1997,28(11):2195-2200.
[51] Liang, Q.,Wendelhag, I.,Wikstrand, J., et al. A multiscale dynamic programmingprocedure for boundary detection in ultrasonic artery images. Medical Imaging,IEEE Transactions on,2000,19(2):127-142.
[52] Santhiyakumari, N.,Madheswaran, M. Non-invasive evaluation of carotid arterywall thickness using improved dynamic programming technique. Signal, Image andVideo Processing,2008,2(2):183-193.
[53] Santhiyakumari, N.,Rajendran, P.,et al. Detection of the intima and media layerthickness of ultrasound common carotid artery image using efficient active contoursegmentation technique. Medical and Biological Engineering and Computing,2011,49(11):1299-1310.
[54] Cheng, D.,Schmidt-Trucksass, A.,Cheng, K., et al. Using snakes to detect theintimal and adventitial layers of the common carotid artery wall in sonographicimages. Computer Methods and Programs in Biomedicine,2002,67(1):27-37.
[55] Stein, J. H.,Korcarz, C. E.,Mays, M. E., et al. A semiautomated ultrasound borderdetection program that facilitates clinical measurement of ultrasound carotidintima-media thickness. Journal of the American Society of Echocardiography,2005,18(3):244-251.
[56] Loizou, C. P.,Pattichis, C. S.,Pantziaris, M., et al. Snakes based segmentation of thecommon carotid artery intima media. Medical and Biological Engineering andComputing,2007,45(1):35-49.
[57] Golemati, S.,Stoitsis, J.,Sifakis, E. G., et al. Using the Hough transform to segmentultrasound images of longitudinal and transverse sections of the carotid artery.Ultrasound in medicine and biology,2007,33(12):1918-1932.
[58] Xu, X.,Zhou, Y.,Cheng, X., et al. Ultrasound intima–media segmentation usingHough transform and dual snake model. Computerized Medical Imaging andGraphics,2012,36(3):248-258.
[59] Destrempes, F.,Meunier, J.,Giroux, M. F., et al. Segmentation in ultrasonic B-modeimages of healthy carotid arteries using mixtures of Nakagami distributions andstochastic optimization. Medical Imaging, IEEE Transactions on,2009,28(2):215-229.
[60] Delsanto, S.,Molinari, F.,Giustetto, P., et al. CULEX-completely user-independentlayers extraction: ultrasonic carotid artery images segmentation. In Engineering inMedicine and Biology Society,2005. IEEE-EMBS2005.27th Annual InternationalConference of the,2006;6468-6471.
[61] Delsanto, S.,Molinari, F.,Giustetto, P., et al. Characterization of a completelyuser-independent algorithm for carotid artery segmentation in2-D ultrasoundimages. Instrumentation and Measurement, IEEE Transactions on,2007,56(4):1265-1274.
[62] Molinari, F.,Zeng, G.,Suri, J. S. Intima-media thickness: setting a standard for acompletely automated method of ultrasound measurement. Ultrasonics,Ferroelectrics and Frequency Control, IEEE Transactions on,2010,57(5):1112-1124.
[63] Molinari, F.,Meiburger, K.,Zeng, G., et al. CAUDLES-EF: Carotid AutomatedUltrasound Double Line Extraction System Using Edge Flow. Journal of DigitalImaging,2011/12/01,2011,24(6):1059-1077.
[64] Molinari, F.,Pattichis, C. S.,Zeng, G., et al. Completely Automated MultiresolutionEdge Snapper—A New Technique for an Accurate Carotid Ultrasound IMTMeasurement: Clinical Validation and Benchmarking on a Multi-InstitutionalDatabase. Image Processing, IEEE Transactions on,2012,21(3):1211-1222.
[65]李国宽,程新耀,周渊,等.超声图像中颈动脉血管内外膜分割.华中科技大学学报:自然科学版,2010,38(6):75-79.
[66] Cheng, X.,Zhou, Y.,Jin, Y., et al. Intima-medial thickness homogeneity in thecommon carotid artery: Measurement method and preliminary clinical study.Journal of Clinical Ultrasound,2012,40(9):559-565.
[67] Chiu, B.,Egger, M.,Spence, D. J., et al. Area-preserving flattening maps of3Dultrasound carotid arteries images. Medical Image Analysis,2008,12(6):676.
[68] Chiu, B.,Egger, M.,Spence, J. D., et al. Quantification of carotid vessel wall andplaque thickness change using3D ultrasound images. Medical Physics,2008,353691-3710.
[69] Chiu, B.,Ukwatta, E.,Shavakh, S., et al. Quantification and Visualization of CarotidSegmentation Accuracy and Precision Using A2D Standardized Carotid Map.Physics in Medicine and Biology,2013,1-45.
[70] Mao, F.,Gill, J.,Downey, D., et al. Segmentation of carotid artery in ultrasoundimages: Method development and evaluation technique. Medical Physics, Aug,2000,27(8):1961-1970.
[71] Abolmaesumi, P.,Sirouspour, M.,Salcudean, S. Real-time extraction of carotidartery contours from ultrasound images. In Proceedings of13th IEEE Symposiumon Computer-Based Medical Systems2000(CBMS),2000;181-186.
[72] Zahalka, A.,Fenster, A. An automated segmentation method for three-dimensionalcarotid ultrasound images. Physics in medicine and biology,2001,46(4):1321-1342.
[73] Li, X.,Wang, Z.,Lu, H., et al. Automated segmentation method for the3Dultrasound carotid image based on geometrically deformable model with automaticmerge function. In Sonka, M.,Fitzpatrick, J. M., Proc. of SPIE Medical Imaging,May15,2002,2002;1458-1463.
[74] Kass, M.,Witkin, A.,Terzopoulos, D. Snakes: Active contour models. Internationaljournal of computer vision,1988,1(4):321-331.
[75]吴慧慧,杨鑫,吴琼,等.基于主动轮廓模型的颈动脉超声图像分割方法研究.华中科技大学学报:自然科学版,2013, xx (xx): xx-xx.[Under Review].
[76] Shah, D.,Mumford, J. Boundary detection by minimizing functionals. In Proc.IEEE Conf. on Computer Vision and Pattern Recognition, San Francisco, CA, USA,1985;22-26.
[77] Chan, T. F.,Vese, L. A. Active contours without edges. Image Processing, IEEETransactions on,2001,10(2):266-277.
[78]曾雅洁,杨鑫,徐红卫,等.基于局部Chan-Vese模型的超声颈动脉图像水平集分割方法研究.计算机科学,2013, xx (xx): xx-xx.[Under Review].
[79] Cootes, T. F.,Taylor, C. J.,Cooper, D. H., et al. Active shape models-their trainingand application. Computer vision and image understanding,1995,61(1):38-59.
[80] Cootes, T. F.,Edwards, G. J.,Taylor, C. J. Active appearance models. PatternAnalysis and Machine Intelligence, IEEE Transactions on,2001,23(6):681-685.
[81] Sethian, J. A. Level set methods and fast marching methods: evolving interfaces incomputational geometry, fluid mechanics, computer vision, and materials science.Cambridge university press,1999.
[82]李鹤.三维超声图像中颈动脉血管壁的分割方法.华中科技大学2013.
[83] Loizou, C. P.,Pattichis, C. S.,Pantziaris, M., et al. An integrated system for thesegmentation of atherosclerotic carotid plaque. Information Technology inBiomedicine, IEEE Transactions on,2007,11(6):661-667.
[84] Destrempes, F.,Meunier, J.,Giroux, M.-F., et al. Segmentation of plaques insequences of ultrasonic B-mode images of carotid arteries based on motionestimation and a bayesian model. Biomedical Engineering, IEEE Transactions on,2011,58(8):2202-2211.
[85] Seabra, J. C.,Pedro, L. M.,Fernandes e Fernandes, J., et al. A3-D ultrasound-basedframework to characterize the echo morphology of carotid plaques. BiomedicalEngineering, IEEE Transactions on,2009,56(5):1442-1453.
[86]程洁玉.基于水平集方法的三维超声颈动脉斑块分割.华中科技大学2013.
[87]熊莉,邓又斌.超声造影评价颈动脉易损斑块内新生血管.中华超声影像学杂志,2008,17(4):361-362.
[88]杨万勇,谭泽锋,徐安定.动脉粥样硬化易损斑块的识别与干预.中国卒中杂志,2007,2(4):318-321.
[89]赵雅萍,邹春鹏,孙晶,等.超声造影三维成像评价颈动脉软斑块内新生血管的初步研究.中华超声影像学杂志,2010,19(11):937-939.
[90] Fenster, A.,Downey, D. B.,Cardinal, H. N. Three-dimensional ultrasound imaging.Physics in Medicine and Biology,2001,46(5): R67-R99.
[91] Landry, A.,Fenster, A. Theoretical and experimental quantification of carotid plaquevolume measurements made by three-dimensional ultrasound using test phantoms.Medical physics,2002,292319-2327.
[92] Krasinski, A.,Chiu, B.,Fenster, A., et al. Magnetic resonance imaging and three‐dimensional ultrasound of carotid atherosclerosis: Mapping regional differences.Journal of Magnetic Resonance Imaging,2009,29(4):901-908.
[93] Chalana, V.,Kim, Y. A methodology for evaluation of boundary detectionalgorithms on medical images. Medical Imaging, IEEE Transactions on,1997,16(5):642-652.
[94] Papademetris, X.,Sinusas, A. J.,Dione, D. P., et al. Estimation of3D left ventriculardeformation from echocardiography. Medical Image Analysis,2001,5(1):17-28.
[95] Endo, A. The origin of the statins. In International Congress Series,2004;3-8.
[96] Shai, I.,Spence, J. D.,Schwarzfuchs, D., et al. Dietary intervention to reverse carotidatherosclerosis. Circulation, Mar16,2010,121(10):1200-1208.
[97] Awad, J.,Krasinski, A.,Parraga, G., et al. Texture analysis of carotid arteryatherosclerosis from three-dimensional ultrasound images. Medical Physics, Apr,2010,37(4):1382-1391.
[98] Ukwatta, E.,Awad, J.,Buchanan, D., et al. Three-dimensional semi-automatedsegmentation of carotid atherosclerosis from three-dimensional ultrasound images.In van Ginneken, B.,Novak, C. L., SPIE Medical Imaging, San Diego, California,USA,2012;83150O-6.
[99] Schulz, U. G. R.,Rothwell, P. M. Major Variation in Carotid Bifurcation Anatomy APossible Risk Factor for Plaque Development? Stroke, Nov,2001,32(11):2522-2529.
[100]张麒.动脉粥样硬化研究中的医学图像处理.复旦大学2010.
[101] Zakeri, F.,Behnam, H.,Ahmadinejad, N. Classification of Benign and MalignantBreast Masses Based on Shape and Texture Features in Sonography Images. J MedSyst,2012/06/01,2012,36(3):1621-1627.
[102] Bao, P.,Zhang, L.,Wu, X. Canny edge detection enhancement by scalemultiplication. Pattern Analysis and Machine Intelligence, IEEE Transactions on,2005,27(9):1485-1490.
[103] Cumming, G.,Fidler, F.,Vaux, D. L. Error bars in experimental biology. The Journalof cell biology, Apr9,2007,177(1):7-11.
[104] Altman, D. G.,Bland, J. M. Measurement in Medicine: The Analysis of MethodComparison Studies. Journal of the Royal Statistical Society. Series D (TheStatistician),1983,32(3):307-317.
[105] Martin Bland, J.,Altman, D. Statistical methods for assessing agreement betweentwo methods of clinical measurement. The Lancet,1986,327(8476):307-310.
[106] Rodgers, J. L.,Nicewander, W. A. Thirteen ways to look at the correlationcoefficient. The American Statistician,1988,42(1):59-66.
[107] Stigler, S. M. Francis Galton's account of the invention of correlation. StatisticalScience,1989,4(2):73-79.
[108] Goh, K.-I.,Cusick, M. E.,Valle, D., et al. The human disease network. Proceedingsof the National Academy of Sciences, May22,2007,2007,104(21):8685-8690.
[109] Frommert, M.,Durrer, R.,Michaud, J. The Kolmogorov-Smirnov test for the CMB.Journal of Cosmology and Astroparticle Physics,2012,2012(01):009.
[110] Schepis, T.,Marwan, M.,Pflederer, T., et al. Quantification of non-calcified coronaryatherosclerotic plaques with dual-source computed tomography: comparison withintravascular ultrasound. Heart,2010,96(8):610-615.
[111] Awad, J.,Krasinski, A.,Spence, D., et al. Three-dimensional ultrasound-basedtexture analysis of the effect of atorvastatin on carotid atherosclerosis. In SPIEmedical Imaging,2010;762621-762621-10.
[112] Salonen, J. T.,Salonen, R. Ultrasound B-mode imaging in observational studies ofatherosclerotic progression. Circulation,1993,87(3Suppl): II56-II65.
[113] de Groot, E.,van Leuven, S. I.,Duivenvoorden, R., et al. Measurement of carotidintima-media thickness to assess progression and regression of atherosclerosis.Nature clinical practice. Cardiovascular medicine, May,2008,5(5):280-8.
[114] Touboul, P.-J.,Grobbee, D. E.,den Ruijter, H. Assessment of subclinicalatherosclerosis by carotid intima media thickness: technical issues. EuropeanJournal of Preventive Cardiology,2012,19(2suppl):18-24.
[115] Saba, L.,Sanfilippo, R.,Montisci, R., et al. Carotid artery wall thickness:comparison between sonography and multi-detector row CT angiography.Neuroradiology,2010,52(2):75-82.
[116] Coll, B.,Feinstein, S. B. Carotid intima-media thickness measurements: techniquesand clinical relevance. Current atherosclerosis reports, Oct,2008,10(5):444-50.
[117] Yang, X.,Jin, J.,He, W., et al. Artery Wall Segmentation Techniques for CarotidUltrasound Images. In Chinese Bio-Medical Engineering Annual Conference(CBME2011) Wuhan, China Oct.,30-Nov.,12011;33-40.
[118]蔡文娟,曾雅洁,杨鑫,等.基于二维超声的颈动脉血管壁测量方法. In2012年湖北省生物医学工程学会生物医学仪器专业委员会学术年会[优秀论文一等奖],襄樊,湖北,2012.
[119] Jin, J.,Ding, M.,Yang, X. Automatic Detection of the Intima-Media Layer inUltrasound Common Carotid Artery Image Based on Active Contour Model. InIEEE Intelligent Computation and Bio-Medical Instrumentation (ICBMI2011),International Conference on14-17Dec.,2011;105-108.
[120] Molinari, F.,Zeng, G.,Suri, J. S. Automatic recognition and validation of thecommon carotid artery wall segmentation in100longitudinal ultrasound images: anintegrated approach using feature selection, fitting and classification. In SPIEMedical Imaging,2010;76233W-76233W-10.
[121] Molinari, F.,Zeng, G.,Suri, J. S. An Integrated Approach to Computer-BasedAutomated Tracing and Its Validation for200Common Carotid Arterial WallUltrasound Images. Journal of Ultrasound in Medicine,2010,29(3):399-418.
[122] Polak, J. F.,Pencina, M. J.,Meisner, A., et al. Associations of Carotid ArteryIntima-Media Thickness (IMT) With Risk Factors and Prevalent CardiovascularDisease Comparison of Mean Common Carotid Artery IMT With MaximumInternal Carotid Artery IMT. Journal of Ultrasound in Medicine,2010,29(12):1759-1768.
[123]孙正,杨宇.基于snake模型的IVUS图像序列三维分割方法.工程图学学报,2012,32(6):25-32.
[124] Yang, X.,Jin, J.,Yuchi, M., et al. Ultrasound Carotid Artery Intima-Media Thickness(IMT) Segmentation Review. In IEEE Intelligent Computation and Bio-MedicalInstrumentation (ICBMI2011), International Conference on14-17Dec.,2011;97-100.
[125]杨鑫,吴慧慧,刘洋,等.基于三维超声图像的主颈动脉血管分割方法.中国医疗器械杂志,2013, xx (xx): xx-xx.[已录用，待发表].
[126]杨颖,勇强,梁立荣,等.超声检测颈动脉内-中膜厚度的重复性评价.中华超声影像学杂志,2010,19(2):120-123.
[127]唐力,程艳彬,任卫东,等.实时三维超声测定颈动脉斑块体积的临床价值.中华超声影像学杂志,2010,(2):116-119.
[128] Spangler, E. L.,Brown, C.,Roberts, J. A., et al. Evaluation of internal carotid arterysegmentation by InsightSNAP. In Proc. SPIE Medical Imaging,2007;65123F-65123F-8.
[129] Gill, J. D.,Ladak, H. M.,Steinman, D. A., et al. Accuracy and variability assessmentof a semiautomatic technique for segmentation of the carotid arteries fromthree-dimensional ultrasound images. Medical Physics,2000,27(6):1333-1342.
[130] Ukwatta, E.,Yuan, J.,Rajchl, M., et al.3-D Carotid Multi-Region MRISegmentation by Globally Optimal Evolution of Coupled Surfaces. MedicalImaging, IEEE Transactions on,2013,32(4):770-785.
[131] Ukwatta, E.,Yuan, J.,Buchanan, D., et al. Three-dimensional segmentation ofthree-dimensional ultrasound carotid atherosclerosis using sparse field level sets.Medical physics, May2013,2013,40(5):052903.
[132]金娇英,杨鑫,邱武,等. Snake法和GVF snake法进行颈动脉超声图像分割的比较[OL].中国科技论文在线,[2011-03-01],http://www.paper.edu.cn/releasepaper/content/201103-14.
[133] Noble, J. A.,Boukerroui, D. Ultrasound image segmentation: A survey. MedicalImaging, IEEE Transactions on,2006,25(8):987-1010.
[134] Noble, J. Ultrasound image segmentation and tissue characterization. Proceedingsof the Institution of Mechanical Engineers, Part H: Journal of Engineering inMedicine,2010,224(2):307-316.
[135] Jacob, G.,Noble, J. A.,Behrenbruch, C., et al. A shape-space-based approach totracking myocardial borders and quantifying regional left-ventricular functionapplied in echocardiography. Medical Imaging, IEEE Transactions on,2002,21(3):226-238.
[136] Yang, X.,Eranga, U.,Aaron, F., et al. Common Carotid Artery Lumen Segmentationof Ultrasound Images on Transverse Views Based on Morphology Method. In the6th Canadian Student Conference on Biomedical Computing and Engineering(CSCBCE2011), London, ON, Canada, May26-28,2011,2011;135-136.
[137] Yang, X.,Ding, M.,Lou, L., et al. Common Carotid Artery Lumen Segmentation inB-mode Ultrasound Transverse View Images. International Journal of Image,Graphics and Signal Processing (IJIGSP),2011,3(5):15-21.
[138] Yang, X.,He, W.,Jin, J., et al. A hybrid method to segment common carotid arteriesfrom3D ultrasound images. In Biomedical and Health Informatics (BHI2012),IEEE-EMBS International Conference on,2012;241-244.
[139]金娇英.基于3D超声图像的颈动脉血管斑块分割方法研究.华中科技大学2011.
[140]贺婉佶.基于主动外观模型（AAM）的超声颈动脉血管分割方法研究.华中科技大学2012.
[141]董硕,罗述谦.活动形状模型在医学图像分割中的应用.国际生物医学工程杂志,2007,30(3):1-5.
[142]张墨逸.基于表观的二维手势识别方法研究.兰州理工大学2010.
[143]董硕,罗述谦.基于活动形状模型的人脸识别.中国生物医学工程学报,2008,27(2).
[144] Cootes, T.,Twining, C.,Babalola, K., et al. Diffeomorphic statistical shape models.Image and Vision Computing,2008,26(3):326-332.
[145] Caunce, A.,Cristinacce, D.,Taylor, C., et al. Locating facial features and poseestimation using a3D shape model. In Advances in Visual Computing, Springer:2009;750-761.
[146] Cootes, T. F.,Taylor, C. J. Statistical models of appearance for computer vision.World Wide Web Publication, February,2001.
[147] Cootes, T. An introduction to active shape models. In Image Processing andAnalysis,1st ed.;2000;223-248.
[148] Yang, X.,Jin, J.,He, W., et al. Segmentation of the common carotid artery withactive shape models from3D ultrasound images. In van Ginneken, B.,Novak, C. L.,Proc. SPIE8315, Medical Imaging2012: Computer-Aided Diagnosis, San Diego,California, USA,2012;83152H-831528.
[149] Yang, X.,Jin, J.,Xu, M., et al. Ultrasound Common Carotid Artery SegmentationBased on Active Shape Model. Computational and Mathematical Methods inMedicine,2013,20131-11.
[150]金娇英,王龙会,丁明跃.两种超声颈动脉血管斑块图像分割方法比较与改进.计算机科学,2012,39(B06):485-488.
[151] Cootes, T.,Edwards, G.,Taylor, C. Active appearance models. ComputerVision—ECCV’98,1998,484-498.
[152]黄琛,丁晓青,方驰.一种鲁棒高效的人脸特征点跟踪方法.自动化学报,2012,38(005):788-796.
[153] Stegmann, M. B. Active appearance models: Theory, extensions and cases.Informatics and Mathematical Modelling,2000,262.
[154] Yang, X.,He, W.,Fenster, A., et al. Segmentation of common carotid artery withactive appearance models from ultrasound images. In Novak, C. L., Proc. SPIE8670, Medical Imaging2013: Computer-Aided Diagnosis, Lake Buena Vista(Orlando Area), Florida, USA, February09,2013;86703H-86703H.
[155] Bamber, J.,Dickinson, R. Ultrasonic B-scanning: a computer simulation. Physics inmedicine and biology,1980,25(3):463.
[156] Jensen, J. A. Field: A program for simulating ultrasound systems. In10THNORDICBALTIC CONFERENCE ON BIOMEDICAL IMAGING, VOL.4,SUPPLEMENT1, PART1:351--353,1996.
[157] Jensen, J. A. Simulation of advanced ultrasound systems using Field II. InBiomedical Imaging: Nano to Macro,2004. IEEE International Symposium on,2004;636-639.
[158] Stoitsis, J.,Golemati, S.,Koropouli, V., et al. Simulating dynamic B-modeultrasound image data of the common carotid artery. In Imaging Systems andTechniques,2008. IST2008. IEEE International Workshop on,2008;144-148.
[159] Golemati, S.,Stoitsis, J. S.,Perakis, D. A., et al. Carotid artery motion estimationfrom sequences of B-mode ultrasound images: effect of scanner settings and imagenormalization. Instrumentation and Measurement, IEEE Transactions on,2009,58(7):2102-2112.
[160] Stoitsis, J.,Golemati, S.,Perakis, D., et al. Carotid artery motion estimation fromsequences of B-mode ultrasound images: Effect of dynamic range and persistence.In2006IEEE Int. Workshop on Imaging Systems and Techniques,2006.
[161] Golemati, S.,Konstantina, J.,Nikita, S. On the use of block matching for theestimation of arterial wall motion. In BioInformatics and BioEngineering,2008.BIBE2008.8th IEEE International Conference on,2008;1-5.
[162] Lin, Y.,Yang, X.,Xu, M., et al. Carotid Artery Phantom Design and Simulationusing Field II. In Faxiong Zhang, E., Proc. SPIE, MIPPR2013: Medical ImageProcessing, Wuhan, Hubei,26~27, October,2013; xx-xx [Under Review].
[163] Meunier, J.,Bertrand, M. Ultrasonic texture motion analysis: theory and simulation.Medical Imaging, IEEE Transactions on,1995,14(2):293-300.
[164] Jensen, J. A. Users’ guide for the Field II program. Dept. of Information Technology,Technical University of Denmark May6,2011, Technical report (Current version:3.20).
[165] Jensen, J. A.,Munk, P. Computer phantoms for simulating ultrasound B-mode andcfm images. In Acoustical Imaging, Springer:1997;75-80.
[166] Jensen, J. A. Linear description of ultrasound imaging systems. Notes for theInternational Summer School on Advanced Ultrasound Imaging, TechnicalUniversity of Denmark (July5to9,1999), June29,2001,(Release1.01):1-71.
[167]杜春宁.超声成像数字波束形成算法研究.[硕士论文],中国科学技术大学2007.
[168]彭虎.超声成像算法导论.中国科学技术大学出版社,2008.
[169]王平,许琴,范文政,等.超声成像中基于特征空间的前后向最小方差波束形成.声学学报,2013,38(1):65-70.
[170] Mehidzadeh, S.,Austeng, A.,Johansen, T., et al. Eigenspace Based MinimumVariance Beamforming Applied to Ultrasound Imaging of Acoustically HardTissues.2012.
[171] Shin, J.,Yen, J. Effects of dual apodization with cross-correlation on tissueharmonic and pulse inversion harmonic imaging in the presence of phase aberration.Ultrasonics, Ferroelectrics and Frequency Control, IEEE Transactions on,2013,60(3):643-649.
[172] Seo, C.,Yen, J. Sidelobe suppression in ultrasound imaging using dual apodizationwith cross-correlation. Ultrasonics, Ferroelectrics and Frequency Control, IEEETransactions on,2008,55(10):2198-2210.
[173] Celermajer, D. S.,Sorensen, K. E.,Gooch, V. M., et al. Non-invasive detection ofendothelial dysfunction in children and adults at risk of atherosclerosis. Lancet,Nov7,1992,340(8828):1111-5.
[174] Corretti, M. C.,Anderson, T. J.,Benjamin, E. J., et al. Guidelines for the ultrasoundassessment of endothelial-dependent flow-mediated vasodilation of the brachialartery: a report of the International Brachial Artery Reactivity Task Force. J AmColl Cardiol, Jan16,2002,39(2):257-65.
[175] Stroz, M. J.,Fenster, A. Measuring flow-mediated dilation through transverse andlongitudinal imaging: comparison and validation of methods. Physics in Medicineand Biology,2010,55(21):6501.
[176] Korkmaz, H.,Onalan, O. Evaluation of endothelial dysfunction: flow-mediateddilation. Endothelium,2008,15(4):157-163.
[177] Vogel, R. A. Coronary risk factors, endothelial function, and atherosclerosis: areview. Clinical cardiology,1997,20(5):426-432.
[178]宋佳,郭涛,俞梦孙.含肱动脉分支的心血管系统简化模型研究.中国生物医学工程学报,2011,30(6):842-846.
[179] Thijssen, D. H.,Black, M. A.,Pyke, K. E., et al. Assessment of flow-mediateddilation in humans: a methodological and physiological guideline. AmericanJournal of Physiology-Heart and Circulatory Physiology,2011,300(1): H2-H12.
[180] Chaudhry, F. A.,Bangalore, S.,Upadya, S., et al. Cross-sectional imaging identifiesflow-mediated vasodilatation more accurately compared with longitudinal imaging.Journal of the American Society of Echocardiography,2007,20(12):1380-1385.
[181]石清.三维超声系统参数测定及分析.华中科技大学2009.
[182] Mallett, C.,House, A. A.,Spence, J. D., et al. Longitudinal ultrasound evaluation ofcarotid atherosclerosis in one, two and three dimensions. Ultrasound in medicine&biology,2009,35(3):367-75.
[183]蔡文娟,杨鑫,徐红卫,等.基于超声体模的颈动脉血管扩张(FMD)测量与比较.中国生物医学工程学报,2013, xx (xx): xx-xx.[大修中].
[184] Naghavi, M.,Falk, E.,Hecht, H. S., et al. From Vulnerable Plaque to VulnerablePatient–Part III. Asymptomatic Atherosclerosis,2010,517-535.
[185]王钰洁,吴慧慧,杨鑫,等.基于灰度统计特征的三维超声纹理特征提取. In2012年湖北省生物医学工程学会生物医学仪器专业委员会学术年会,襄樊,湖北,2012.
[186]汪源源,沈嘉琳,王涌,等.基于形态特征判别超声图像中乳腺肿瘤的良恶性.光学精密工程,2006,14(2):333.
[187] Mougiakakou, S. G.,Golemati, S.,Gousias, I., et al. Computer-aided diagnosis ofcarotid atherosclerosis based on ultrasound image statistics, laws’ texture and neuralnetworks. Ultrasound in medicine&biology,2007,33(1):26-36.
[188] Laws, K. I. Rapid Texture Identification. In Wiener, T. F., Proc. SPIE, ImageProcessing for Missile Guidance, San Diego, July29,1980;376-381.
[189] Weszka, J. S.,Dyer, C. R.,Rosenfeld, A. A comparative study of texture measuresfor terrain classification. Systems, Man and Cybernetics, IEEE Transactions on,1976,(4):269-285.
[190] Haggerty, J.,Young, M. Spatial light modulator for texture classification. Appliedoptics,1989,28(23):4992-4995.
[191] Chung-Ming, W.,Yung-Chang, C.,Kai-Sheng, H. Texture features for classificationof ultrasonic liver images. Medical Imaging, IEEE Transactions on,1992,11(2):141-152.
[192] Greenleaf, J. F.,Fatemi, M.,Insana, M. Selected methods for imaging elasticproperties of biological tissues. Annual review of biomedical engineering,2003,5(1):57-78.
[193]张麒,汪源源,马剑英,等.基于血管内超声图像自动识别易损斑块.光学精密工程,2011,19(10):2507-2519.
[194] Zhang, P. F.,Su, H. J.,Yao, G. H., et al. Plaque volume compression ratio, a novelbiomechanical index, is independently associated with ischemic cerebrovascularevents. Journal of hypertension,2009,27(2):348-356.
[195] Van den Berkmortel, F.,Wollersheim, H.,Van Langen, H., et al. Dynamic vessel wallproperties and their reproducibility in subjects with increased cardiovascular risk.Commentary. Journal of human hypertension,1998,12(6):343-350.
[196] Den Berkmortel, V.,Langen, V. The effect of cholesterol lowering on carotid andfemoral artery wall stiffness and thickness in patients with familialhypercholesterolaemia. European journal of clinical investigation,2000,30(6):473-480.
[197] Wada, T.,Fukumoto, T. Biomechanical diagnosis of atherosclerosis by ultrasound.Methods of Information in Medicine-Methodik der Information in der Medizin,2000,39(3):246-248.
[198] Fang, M.,Yang, X.,Ding, M. BP network for atorvastatin effect evaluation fromultrasound images features classification. In Faxiong Zhang, E., Proc. SPIE, MIPPR2013: Pattern Recognition and Computer Vision, Wuhan, Hubei,26~27, October,2013; xx-xx [Under Review].
[199] Fawcett, T. An introduction to ROC analysis. Pattern recognition letters,2006,27(8):861-874.
[200] Obuchowski, N. A. ROC analysis. American Journal of Roentgenology,2005,184(2):364-372.
[201] Brugaletta, S.,Garcia-Garcia, H. M.,Serruys, P. W., et al. Relationship betweenpalpography and virtual histology in patients with acute coronary syndromes. JACC:Cardiovascular Imaging,2012,5(3s1): S19-S27.
[202] Xi, P.,Xu, T.,Zhao, Z. Knowledge-based active appearance model applied inmedical image localization. In Mechatronics and Automation,2005IEEEInternational Conference,2005;637-642.
[203] Tresadern, P.,Sauer, P.,Cootes, T. F. Additive update predictors in active appearancemodels. In British Machine Vision Conference,2010;4.
[204] Nichols, W. W.,O'Rourke, M. F.,Vlachopoulos, C. McDonald's blood flow inarteries: theoretical, experimental and clinical principles. CRC Press,2011.