医学心脏序列图像自动分析研究
|
摘要
随着人类生活水平的提高和预期寿命的延长，心血管疾病(cardiovascular disease，CVD)成为人类的头号死因。对心血管疾病的早期定量诊断和风险评估对延长人类预期寿命，提高人类的生活质量，起着非常关键的作用。
心脏由心电节律控制，房室按顺序收缩、舒展和瓣膜开闭作周期运动。很多现代医学影像设备都能对心脏进行动态成像。近年来，医学影像设备包括磁共振成像(magnetic resonance imaging，MRI)、计算机断层成像(x-ray computer tomography，CT)和超声成像(ultrasonic imaging，US)等，在成像速度、时间和空间分辨率方面快速提高，基本实现了对心脏的3D动态成像。
MR心脏成像的主要优点包括：较好的软组织对比度，能够清楚地区别心脏内各种组织、肿瘤和组织变性；进行任意平面成像的能力；无放射性，无需注射或服用示踪剂；对血流具有较高对比度，还能够评价血流的流速、流量，所以MRI心脏成像能准确地显示其解剖、形态、功能、血流、心肌活性等。近几年实时三维US开始进入临床，三维US不仅能显示解剖结构的二维断层图像，而且可观察与断面相垂直的前侧和后侧结构的立体形态，对了解各个结构空间非常有效，通过软件辅助在三维数据选择任意适当的剖切平面，能获取各种结构的全貌，如瓣膜形态、开口面积等；采用用三维体显示或面显示方法对图像数据做三维重建显示可以直观展示解剖结构，减少了对超声科医生专业经验的依籁。心脏影像设备的进步带来海量的图像数据，心脏成像通常是空间上的3D成像，在心动周期内随时间动态变化构成所谓4D数据。这使传统在观片灯上观察2D图像的工作方式出现问题。首先，4D数据很难以2D方式直观显示。过去观察静态投影或断层图像辅以空间想象的图像解读方法，面对高维动态心脏医学图像数据时比较困难；其次，只依靠放射医生的主观经验分析很难做到定量、可重复的提取具有临床诊断意义的信息，人际差别、可重复性、工作效率等都限制了现代影像设备在心血管检查临床实践中的充分应用。虽然部分新设备也带有简单的图像分析软件，但是它们一般是利用简单的几何模型，提供传统全局参数粗略估计。开发新的计算机辅助分析工具提取海量医学图像中客观、定量、有临床意义的诊断信息来辅助医生诊断成为必然趋势，而对心脏图像中各种解剖结构尤其是左心室的分割则是心脏医学图像分析在临床应用的重要瓶颈之一。
图像分割是图像处理中最重要、基础也是研究内容最为广泛的领域之一，研究者曾提出过基于不同理论框架和不同图像特征的图像分割方法。图像分割技术的成功应用与其处理对象和应用领域密切相关。心脏医学图像有其固有特点，必须结合图像分割理论、具体医学图像特点以及感兴趣的解剖结构来研究有效的心脏医学图像分割算法。
本文针对心脏MR和US图像，在计算机辅助心脏医学图像分析方面上做了以下工作：
一)提出了一种知识引导下的广义模糊几何动态轮廓线分割算法(generalized fuzzy active contour model，GFACM)，结合基于水平集框架的概率形状模型整合医生手动分割结果形成的训练集引入先验知识，实现了对心脏MR图像左心室内壁的鲁棒分割。
从MR心脏三维动态序列图像中快速精确分割左心室内边界是计算机辅助图像分析和心功能诊断的重要前提步骤。由于心脏快速非刚性运动、软组织低对比度和快速成像序列物理原理等各种原因，心脏MR图像的心室边界比较模糊，动态轮廓线算法算法不能很好的定位心室轮廓边界；一般的基于灰度概率和曲线演化的方法也很难保证分割结果的鲁棒和精确。
图像的梯度矢量流(gradient vector flow，GVF)扩大了曲线演化的动态范围，使曲线可以搜索到非凸边界。通过把边缘信息以梯度矢量的形式向外扩散，GVF为动态轮廓线提供更大的形变动态范围。考虑到提取正确地图像边缘信息是计算梯度矢量流的关键，通过对传统的GVF扩散方程通过引入广义模糊算子(generalized fuzzy operator，GFO)算子，改善了噪声环境下几何动态轮廓线的动态范围和准确捕捉目标边界的能力，将改进GVF场引入几何动态轮廓线模型(geometric active contour model，GACM)，改善了边界搜寻动态范围，并且具有较强的抗噪和模糊边界定位的能力。
另外，研究表明在分割模型中整合解剖结构和医生经验的先验知识，可以提高分割结果对噪声和模糊边界的鲁棒性，改进计算效率。我们利用人工分割训练集在水平集框架下构建了概率形状模型，将先验知识引导整合到上述曲线演化过程中，成功实现了对MR左心室内壁的鲁棒精确分割。对多套临床心脏MR图像数据的实验结果显示，分割结果和专家手动分割结果的距离在合理范围内。
二)提出一种小波多尺度框架下的水平集曲线演化算法，实现了对心脏超声图像左心室内壁的鲁棒分割。
由于成像物理特性的原因，US图像的信噪比较低，而且由于斑点噪声(speckle noise)的存在，超声图像的灰度分布被认为是非高斯的，所以传统的基于高斯模型的图像分割方法不能解决心脏超声图像分割问题，而经典动态轮廓线模型是基于图像梯度的，由于超声中弱边界和断裂边界的存在，单纯的基于梯度的曲线演化很容易发生边界泄漏，这是传统基于图像梯度水平集演化的固有缺陷之一。2001年Tony针对这一问题引入基于区域灰度一致性的无边界信息动态轮廓线模型(Active Contour Without Edge)，该模型具有分割结果鲁棒，对曲线初始位置不敏感的优点。但该模型成立的前提是图像区域灰度分布近似符合高斯分布，这个前提在原始超声图像中得不到满足。
小波多尺度分析可以同时在时(空)域和频域上进行局部分解，是信号分析发展史上里程碑式的进展，被广泛应用于信号处理、图像分析、模式识别、计算机视觉等研究领域。由于小波基对信号的平滑和降采样的作用，超声小波分解高层的相邻低频系数之间的相关性降低，近似于高斯分布。而且小波分解高层，构成图像主要能量的灰度信息大部分得到了保留，斑点噪声大部分被抑制。这些特点提示可以在小波分解后不同尺度的低频近似图像中采用不同的分割模型，而设计分割结果的尺度间传播，利用低分辨率尺度图像的分割结果来约束高分辨率尺度图像中的曲线演化，从而得到稳健而精确的结果。
为了实现在心脏超声图像左心室的鲁棒分割，算法在小波分解最高层采用结合边界信息和区域灰度一致性的分割模型，综合利用区域灰度和边界图像梯度信息，在小波分解最高层的低频近似图像中可以得到比较稳健和精确的分割结果。在最高层得到粗尺度的大致左心室内壁轮廓曲线后，通过尺度间插值得到下一层低频近似图像的初始轮廓。为了继续细化左心室轮廓，必须继续利用当前尺度图像信息来推动曲线演化，但由于当前低频图像不再满足高斯分布，所以不能再用区域灰度的均一性来约束曲线的演化。但边界信息复杂，如果没有进一步的约束，曲线的演化又很容易发生边界泄漏而完全偏离初始轮廓。为了进一步细化和约束曲线的演化，引入不同分辨率下曲线形状的一致性约束，作为对精细尺度图像中曲线继续细化演化的约束，结合曲线尺度问形状约束和边界约束使分割结果在不断细化的同时，不致大幅度偏离粗尺度下得到的初始曲线。
基于水平集分割的一个重要的问题是各种演化力权重参数调整。本文算法包含有三种曲线演化力：分别是区域力，边界力和层间约束力，怎么确定一个合理的权重系数是非常难的问题。通过在演化过程中，动态调节这几种演化力的权重，在演化的初期，应该尽量忠实于图像信息，也就是让基于图像信息的边界和区域的力占较大权重；而随着演化的进行到末期，层问约束力要起重要的作用，防止边界泄漏和大变形，保持层间的形状相似性。
总结以上分析，心脏超声图像左心室分割算法的具体步骤如下：
a)首先对超声心脏图像做小波分解，得到各层的低频图像。从小波分解的最高层层低频图像开始，利用边界和区域复合约束动态轮廓线模型寻找左心室内边界；
b)通过插值将结果向下一尺度低频图像传递，并利用尺度间形状约束和边界约束复合动态轮廓线进一步细化曲线，使其符合局部图像特征，并随着曲线演化动态调整参数；
c)向上逐层重复直至原始图像。
由于采用了小波多尺度框架和尺度问形状约束，算法具有曲线演化结果稳健鲁棒，不易陷入局部极小和发生边界泄漏等优点，非常适合心脏超声图像噪声高、对比度低和边界灰度梯度不显著的特点。在实际临床三维超声图像上的实验表明，算法分割结果和人工分割结果的误差在合理范围内。
三)提出一种心脏MR图像内外壁联合分割和时序追踪算法
为了计算左心室质量(left ventricle mass，LVM)等重要心功能参数，在得到各层面左心室短轴像的内壁精确分割结果后，还需要对左心室的外壁做分割，外壁的边界和周围的组织在某些位置灰度分布非常接近，如果不加约束很容易发生边界泄漏，本文提出一种灰度和距离双重约束的方法，实现了左心室外壁的鲁棒分割。
a)初始化和内壁分割：
假设左心室是一个被切割椭球体，选择较小半径和轴长使切割椭球体位于图像中左心室的内部。选择其中某个时刻t_0的三维图像集I_(：，t_0)，初始化各层面Z_i中的水平集函数，使其所包含曲线为对应层面上的截面圆，用第四章中的改进几何动态轮廓线算法分别在各层图像中进行演化，得到I_(：，t_0)，各层面心室内壁的分割结果。
b)心室外壁分割
左心室外壁边界有特殊特点，某些方向灰度对比度很好，但某些方向就很微弱或几乎没有区别，不管是采用边界或区域灰度信息都很难区分。所以心室外壁的分割必须结合解剖结构先验信息如到心室内壁最近点的距离，来控制外壁分割曲线的演化。
外壁分割以心室内壁分割结果为初始轮廓，曲线演化外力场的设计以较强的向外扩张膨胀外力为主导，用区域均值和曲线到心室内壁最近点的距离作约束，得到合理的心室外壁轮廓。
具体方法是计算心室内壁向外邻近一个小环状区域的灰度均值m~e：如果演化曲线上的某点区域灰度不同于聊m~e，那么说明曲线演化达到或超出了心室外壁，应该停止或降低速度；如果外壁上的点离内壁上最近的点距离超过2.5cm，那么根据解剖知识曲线也应该超过了外壁区域，应该改变方向。由于内外壁之间的心肌组织区域灰度比较均一，而且心室内外壁距离一般小于2.5厘米，所以当曲线演化到最大距离之外，或者是局部区域的灰度均值不同于图像中心肌区域的灰度均值时，改变曲线演化方向或降低曲线演化速度。保证心外壁的分割结果满足先验知识的要求。
c)时序追踪算法
由于左心室内壁的运动在空间和时间上是一个连续的周期过程，所以在分割t_0时刻MR心脏图像各短轴层面上的心室内壁后，为了在时序上追踪内壁的连续运动，本节提出使用时序追踪算法来跟踪同一短轴层面上内壁运动过程。
以I_(Z_i△_0)图像心室内壁分割结果为初始轮廓，向同一层面Z_i在不同时刻的图像I_(Z，：)扩展演化，得到I_(Z，：)上所有时刻的心室内壁轮廓。因为同层面的心室壁随时间的变化过程是平滑和渐进的，提出利用时间上相邻的各帧的改进GVF场(的高斯加权平均来得到当前帧的改进GVF场，同时利用该场和图像数据演化曲线，得到时间上相邻各帧I_(Z，：)的心室内轮廓，遍历所有层面Z_i后，再以得到内壁轮廓为起点，得到对应的心室外壁轮廓。
四)根据心脏图像左心室内外壁分割结果，实现了心功能量化参数的计算
计算机辅助心脏图像分析最终需要表现为具有临床意义的定量心功能参数。结合本文MR心脏图像左心室内壁分割算法和灰度和距离约束下的左心室外壁分割算法，构造心脏的三维模型，实现了各种量化的心功能参数的计算。
With the improvement of living condition and prolonged life expectancy, cardiovascular diseases (CVD) have been the number one cause of death in modem society. The early quantitative diagnosis and accurate evaluation of CVD are critical to improving quality of life and prolong life expectancy.
Human heart is a chambered, muscular organ controlled by electrical rhythm that pumps blood into body. Many types of modem medical imaging equipment are capable of cardiovascular imaging. Recently the rapid development of imaging equipments such as magnetic resonance imaging (MRI), computer tomography (CT), ultrasonic (US) and nuclear medicine (NM), has led to dramatically shortening of imaging time and higher spatial and temporal resolution. These make it possible for dynamic 3D cardiovascular imaging.
The merits of MRI include good soft tissue contrast, arbitrary imaging plane etc. MRI has natural high contrast between blood and other tissue because of the physical principle of imaging. It is capable of evaluating the anatomy, morphology, quantitative heart function indices, blood flow and viability of regional heart muscle at the same time. In recent years, 3D ultrasonic comes into use for clinical cardiac function evaluation. It is not only able to show the 2D cross section like traditional US, but also make real time volume imaging of heart structure. With the aid of post processing software, it can select arbitrary plane for diagnosis, which enable physician to see as many anatomy structures as possible and measure their properties quantitatively. After volume rending or surface rending, it is more intuitive to observe the structures than traditional 2D US and to some extent release the relying on medical expertise.
The development of cardiac imaging equipments leads to enormous image data. Typically, cardiac imaging acquires 3D volume data which change with time during the cardiac cycle, so called 4D data. Traditional method of 2D diagnosis by clinical experts' subjective observation is problematic. Firstly, it is hard to show 4D data in 2D form, the traditional way of observing projection image or tomography imaging can hardly pick up any clinical significant information from 4D data. Secondly, it is hardly to get quantitative information merely by subjective analysis because manual delineation of chamber boundaries is time-consuming and prone to intra observer and inter observer variability. These facts limit the full exploitation of the imaging ability. Although some of the imaging equipments provide some simple computer aided image analysis software. They only take use of some simple geometric models and calculate some global cardiac function indices. Therefore, new computer aided medical image analysis software for objective quantitative analysis and getting clinical significant information for diagnosis is indispensable. For cardiac image analysis the segmentation of anatomy structure such as left ventricle is the bottle-neck in clinical application.
Image segmentation is one of the most fundamental and important research topics in the area of image processing and analysis. The researchers have proposed various segmentation methods based on different theory frameworks and image features. The successful implementation of image segmentation technique in medical images is closely related to the anatomy structure it deals with and the clinical environmental itbeing applied. The cardiac images have its unique properties. To achieve successfully segmentation of cardiac images, we must combine segmentation techniques, the specified image features and anatomy structure of interesting together.
In this thesis, we propose several algorithms for cardiac MR and US image left ventricle segmentation, respectively. The main contribution of this thesis is list as following.
1. A novel generalized fuzzy active contour model is proposed in this thesis. Combined with prior statistic shape model based on level set framework from expert manual outlines, the algorithm is capable of robust segmentation of endocardium borders in cardiac short axis MR images.
Segmentation of left ventricle borders from MR dynamic 3D sequential images is the most important prerequisite for computer aided cardiac image analysis and quantitative measurement of heart function. It is because of complicate and non-rigid periodic motion of heart, respiratory motion and limit time resolution of MR that thecardiac MR images typically have low SNR and are full of weak edges. Further more, segmentation is an ill-posed problem, or say, the pose and reflection properties of the object and the noise from the acquisition devices are some of the factors that can interfere with it, there by, the traditional methods based on active contour model(ACM), regional growing often lead to failure in cardiac image segmentation.
The introduction of gradient vector flow(GVF) greatly improves the dynamic capture range of curve and enabled the convergence to concave borders. The GVF is estimated from the continuous gradient space. The diffusion process of GVF leads to a measurement that is contextual. This is due to the fact that multiple boundary information contributes to the estimation of the GVF.
The accurate image edge information is the key to calculate GVF. Considering the fuzzy and weak edges is common in cardiac MR images, the generalized fuzzy operator (GFO) is incorporated into the diffusion process of GVF in order to handle the weak edge detection. The resulting vector field is incorporating into the evolution equation of ACM. By designing the new external force based on general fuzzy gradient vector flow, the algorithm improves both dynamic capture range and robustness to fuzz3, object borders, and achieves successful application to the segmentation and tracking of LV borders in cardiac MR images. The advantages are the capability of locating the fuzzy object border in strong noisy image like cardiac MR and little human intervention.
Further, past research indicated the incorporation of anatomy and human expertise as prior knowledge can improve the efficiency of computation and the robustness to noise and fuzzy edge. We construct a statistic shape model based on level set framework from human expert manual outlines of MR left ventricle. The prior shape model is used to guide the evolution of curve. Experiments on clinical ECG gated 4-D cardiac MR images show that the results are close to the manual outlines of medical experts.
2. A wavelet multi-scale curve evolution algorithm based on level set framework is proposed and robust segmentation of cardiac ultrasonic left ventricle is achieved.
Due to the existence of attenuation, shadows and speckle noises in ultrasonic images, the segmentation of ultrasonic images is a very difficult task. Traditional image segmentation methods based on Gaussian model often fail in echocardiographic images. Classic methods such as ACM are apt to leak due to the existence of weakand broken edges. In 2001, Tony proposed the model named Active Contour Without Edge (ACWE), which is based on regional homogeneity. ACWE has the merit of robustness and insensitivity to initial position. But the prerequisite of ACWE is the regional gray level distribution of image is Gaussian.
Wavelets are a powerful mathematical tool for hierarchically decomposing functions and signals both in frequency and spatial domain. Using wavelets, a signal can be described in terms of a coarse approximation, plus details that range from broad to narrow. Regardless of whether the function of interest is an image, a curve, or a surface, wavelets provide an elegant technique for representing the levels of detail present. Wavelet theory uses a two-dimensional expansion set to characterize and give a time-frequency localization of a one-dimensional signal. Since this is a linear system, the signal can be reconstructed by a weighted sum of the basis functions. In contrast to the one-dimensional Fourier basis localized in only frequency, the wavelet basis is two-dimensional - localized in both frequency and time. A signal's energy, therefore, is usually well represented by just a few wavelet expansion coefficients.
Generally speaking, a typical echocardiographic image contains regular region with little change, texture region with similar intensity distribution pattern and sharp edges. Wavelet is successfully applied to model and remove noise in ultrasonic images. After wavelet decomposition, the different kind of information is divided into different scales. For example, the regular regions mainly exist in coarse scale and sharp edge in fine scale. In echocardiographic images, region inside the LV has the similar texture and intensity distribution which can be easily outlined by region based level set algorithm. Sharpe edge in fine scale can be better used by edge based level set evolution. These characteristics have motivated us to combine the region based and edge based level set based active contour model through the coarse to fine scale and use iner-scale constrain to improve the robustness of segmentation.
After wavelet decomposition of ultrasonic images, the wavelet coefficient in high level low frequency sub-band is approximately Gaussian. Based on this characteristic, this paper proposes a novel wavelet multi-scale level set algorithm. Firstly, the echocardiographic image is wavelet transformed to get coarse scale approximation images. Then the algorithm begins with the highest level approximation image and outlines the left ventricle endocardium border with regional and edge constrained ACM. Then the result is interpolated into the next finer level of approximation image as a initial contour, and evolved with edge based and inter scales shape constrained ACM. The weighting parameter between inter scale constrain and image force is tuning during the intra-scale curve evolution.
One of the important problems in curve evolution based on level set frame is the tuning of weighting parameters of different force. There exist three kinds of fore: regional force, edge force and inter-scale constrain force in our algorithm. How to choose the proper weighting parameters is difficult. We propose a dynamic adjusting scheme for these parameters. In the beginning, the curve should be faith to image information, but at end of evolution, inter-scale constrain should become more important to avoid the edge leakage and maintain the inte4-scale similarity.
In sum, the algorithm can be descried by following procedures:
a, Wavelet decomposition the original echocardiography images into multi-scale pyramid, use the edge and region compound model to get the initial endocardium contour in the coarsest level;
b. Use the segmentation results in A_jf to interpolate the initial contour in finer level A_(j-1)f then evolve the contour and get the endocardium contour in A_(j-1)f;
c. If reach the finest level (original image), stop the algorithm, elseifjump to step
(b);
Because of the inter-scale constrain and compound force, our algorithm is robust to local minimums and weak edges and suitable for the US image with high noise, poor contrast and small edge gradient. Comparison is made between the traditional ACM with edges and GACM methods. Experiments on clinical 3D echocardiographic images also show the algorithm's result is very close to the expert manual outlines.
3. A new associate scheme for enpi- and endocardium segmentation and temporal tracking in cardiac MR image is proposed
Accurate segmentation of endocardium and epicardium is the most important prerequisite for computer aid diagnosis of cardiac function. In this study, we use ~(I_(z,t)(x,y)) to donate the cardiac image in time t and slice position z. especially, ~(I_(z,1)) stand for all cardiac images in slice position z of entire cardiac cycle and ~(I(1-t)) stand for images of all slice position in time frame t. The segmentation and tracking of endo- and epicardium steps is as follows:
a. Segmentation of endocardium
LV is approximately the shape of truncated ellipse as illustrated by Fig. 5. In time~t_0, proper D and L are selected to get a rough initial shape of LV. Then the level set functions in all slices are initialized to embed the curves of truncated ellipse. The adapted geometric active contour model proposed in section 2 is then applied to evolve the curve to get the endocardium border in~I_(:,to.)
b. Segmentation of epicardium
Segmentation of epicardium begins with the results of endocardium segmentation. In cardiac MR images, the cardiac muscles appear to have gray levels of Gaussian distribution. By an ad hoc designed regional balloon force controlled by local mean gray level and distance from endocardium, the curves evolve outward to get sensible epicardium borders. At each evolving steps, the local mean gray level ~m_p in a outward neighborhood is calculated and compare to the initial ~(m~e_0) calculated in endocardium neighborhoods. If the ~(m_p) is different from ~(m_e_0), then the curve could have evolved out of the epicardium and the evolving speed should become slow. Further more, cording to the anatomy of human heart, the maximum distance of epicardium for endocardium should be around 2.5 cm, once the evolving curves are out of the this distance, the evolution should be stopped and pulled back. According to equation 7, when the curves are out of the cardiac muscle area (mean gray level changes), or the distance is bigger than 2.5 cm, the curves are slowed down or pulled back to ensure the results are robust and compliant with anatomy prior knowledge.
c. Temporal propagations
Endocardium segmentation results in ~(I_(zi, eo) are used as initial curve and propagated to the images in the same slice position z in other time frame and get the endocardium borders of~(I_(=,:)) in all time. Because the motion of ventricle border is regular and progressive (Fig.7), the time neighborhood GFGVF fields are weighted summed to get current frame GFGVF. After get the endocardium border in all slice position ~(Z_i), the step b is executed to get the epicardium borders.
4. Implement the quantitative cardiac function calculation according to the endoand epicardium segmentation from cardiac images.
The ultimate goal of computer aided medical image analysis is some clinical significant quantitative cardiac indices. After segmentation of endo- and epicardium from cardiac MR image, 3D model is construct and various quantitative cardiac indices was calculated based on it.
心脏由心电节律控制，房室按顺序收缩、舒展和瓣膜开闭作周期运动。很多现代医学影像设备都能对心脏进行动态成像。近年来，医学影像设备包括磁共振成像(magnetic resonance imaging，MRI)、计算机断层成像(x-ray computer tomography，CT)和超声成像(ultrasonic imaging，US)等，在成像速度、时间和空间分辨率方面快速提高，基本实现了对心脏的3D动态成像。
MR心脏成像的主要优点包括：较好的软组织对比度，能够清楚地区别心脏内各种组织、肿瘤和组织变性；进行任意平面成像的能力；无放射性，无需注射或服用示踪剂；对血流具有较高对比度，还能够评价血流的流速、流量，所以MRI心脏成像能准确地显示其解剖、形态、功能、血流、心肌活性等。近几年实时三维US开始进入临床，三维US不仅能显示解剖结构的二维断层图像，而且可观察与断面相垂直的前侧和后侧结构的立体形态，对了解各个结构空间非常有效，通过软件辅助在三维数据选择任意适当的剖切平面，能获取各种结构的全貌，如瓣膜形态、开口面积等；采用用三维体显示或面显示方法对图像数据做三维重建显示可以直观展示解剖结构，减少了对超声科医生专业经验的依籁。心脏影像设备的进步带来海量的图像数据，心脏成像通常是空间上的3D成像，在心动周期内随时间动态变化构成所谓4D数据。这使传统在观片灯上观察2D图像的工作方式出现问题。首先，4D数据很难以2D方式直观显示。过去观察静态投影或断层图像辅以空间想象的图像解读方法，面对高维动态心脏医学图像数据时比较困难；其次，只依靠放射医生的主观经验分析很难做到定量、可重复的提取具有临床诊断意义的信息，人际差别、可重复性、工作效率等都限制了现代影像设备在心血管检查临床实践中的充分应用。虽然部分新设备也带有简单的图像分析软件，但是它们一般是利用简单的几何模型，提供传统全局参数粗略估计。开发新的计算机辅助分析工具提取海量医学图像中客观、定量、有临床意义的诊断信息来辅助医生诊断成为必然趋势，而对心脏图像中各种解剖结构尤其是左心室的分割则是心脏医学图像分析在临床应用的重要瓶颈之一。
图像分割是图像处理中最重要、基础也是研究内容最为广泛的领域之一，研究者曾提出过基于不同理论框架和不同图像特征的图像分割方法。图像分割技术的成功应用与其处理对象和应用领域密切相关。心脏医学图像有其固有特点，必须结合图像分割理论、具体医学图像特点以及感兴趣的解剖结构来研究有效的心脏医学图像分割算法。
本文针对心脏MR和US图像，在计算机辅助心脏医学图像分析方面上做了以下工作：
一)提出了一种知识引导下的广义模糊几何动态轮廓线分割算法(generalized fuzzy active contour model，GFACM)，结合基于水平集框架的概率形状模型整合医生手动分割结果形成的训练集引入先验知识，实现了对心脏MR图像左心室内壁的鲁棒分割。
从MR心脏三维动态序列图像中快速精确分割左心室内边界是计算机辅助图像分析和心功能诊断的重要前提步骤。由于心脏快速非刚性运动、软组织低对比度和快速成像序列物理原理等各种原因，心脏MR图像的心室边界比较模糊，动态轮廓线算法算法不能很好的定位心室轮廓边界；一般的基于灰度概率和曲线演化的方法也很难保证分割结果的鲁棒和精确。
图像的梯度矢量流(gradient vector flow，GVF)扩大了曲线演化的动态范围，使曲线可以搜索到非凸边界。通过把边缘信息以梯度矢量的形式向外扩散，GVF为动态轮廓线提供更大的形变动态范围。考虑到提取正确地图像边缘信息是计算梯度矢量流的关键，通过对传统的GVF扩散方程通过引入广义模糊算子(generalized fuzzy operator，GFO)算子，改善了噪声环境下几何动态轮廓线的动态范围和准确捕捉目标边界的能力，将改进GVF场引入几何动态轮廓线模型(geometric active contour model，GACM)，改善了边界搜寻动态范围，并且具有较强的抗噪和模糊边界定位的能力。
另外，研究表明在分割模型中整合解剖结构和医生经验的先验知识，可以提高分割结果对噪声和模糊边界的鲁棒性，改进计算效率。我们利用人工分割训练集在水平集框架下构建了概率形状模型，将先验知识引导整合到上述曲线演化过程中，成功实现了对MR左心室内壁的鲁棒精确分割。对多套临床心脏MR图像数据的实验结果显示，分割结果和专家手动分割结果的距离在合理范围内。
二)提出一种小波多尺度框架下的水平集曲线演化算法，实现了对心脏超声图像左心室内壁的鲁棒分割。
由于成像物理特性的原因，US图像的信噪比较低，而且由于斑点噪声(speckle noise)的存在，超声图像的灰度分布被认为是非高斯的，所以传统的基于高斯模型的图像分割方法不能解决心脏超声图像分割问题，而经典动态轮廓线模型是基于图像梯度的，由于超声中弱边界和断裂边界的存在，单纯的基于梯度的曲线演化很容易发生边界泄漏，这是传统基于图像梯度水平集演化的固有缺陷之一。2001年Tony针对这一问题引入基于区域灰度一致性的无边界信息动态轮廓线模型(Active Contour Without Edge)，该模型具有分割结果鲁棒，对曲线初始位置不敏感的优点。但该模型成立的前提是图像区域灰度分布近似符合高斯分布，这个前提在原始超声图像中得不到满足。
小波多尺度分析可以同时在时(空)域和频域上进行局部分解，是信号分析发展史上里程碑式的进展，被广泛应用于信号处理、图像分析、模式识别、计算机视觉等研究领域。由于小波基对信号的平滑和降采样的作用，超声小波分解高层的相邻低频系数之间的相关性降低，近似于高斯分布。而且小波分解高层，构成图像主要能量的灰度信息大部分得到了保留，斑点噪声大部分被抑制。这些特点提示可以在小波分解后不同尺度的低频近似图像中采用不同的分割模型，而设计分割结果的尺度间传播，利用低分辨率尺度图像的分割结果来约束高分辨率尺度图像中的曲线演化，从而得到稳健而精确的结果。
为了实现在心脏超声图像左心室的鲁棒分割，算法在小波分解最高层采用结合边界信息和区域灰度一致性的分割模型，综合利用区域灰度和边界图像梯度信息，在小波分解最高层的低频近似图像中可以得到比较稳健和精确的分割结果。在最高层得到粗尺度的大致左心室内壁轮廓曲线后，通过尺度间插值得到下一层低频近似图像的初始轮廓。为了继续细化左心室轮廓，必须继续利用当前尺度图像信息来推动曲线演化，但由于当前低频图像不再满足高斯分布，所以不能再用区域灰度的均一性来约束曲线的演化。但边界信息复杂，如果没有进一步的约束，曲线的演化又很容易发生边界泄漏而完全偏离初始轮廓。为了进一步细化和约束曲线的演化，引入不同分辨率下曲线形状的一致性约束，作为对精细尺度图像中曲线继续细化演化的约束，结合曲线尺度问形状约束和边界约束使分割结果在不断细化的同时，不致大幅度偏离粗尺度下得到的初始曲线。
基于水平集分割的一个重要的问题是各种演化力权重参数调整。本文算法包含有三种曲线演化力：分别是区域力，边界力和层间约束力，怎么确定一个合理的权重系数是非常难的问题。通过在演化过程中，动态调节这几种演化力的权重，在演化的初期，应该尽量忠实于图像信息，也就是让基于图像信息的边界和区域的力占较大权重；而随着演化的进行到末期，层问约束力要起重要的作用，防止边界泄漏和大变形，保持层间的形状相似性。
总结以上分析，心脏超声图像左心室分割算法的具体步骤如下：
a)首先对超声心脏图像做小波分解，得到各层的低频图像。从小波分解的最高层层低频图像开始，利用边界和区域复合约束动态轮廓线模型寻找左心室内边界；
b)通过插值将结果向下一尺度低频图像传递，并利用尺度间形状约束和边界约束复合动态轮廓线进一步细化曲线，使其符合局部图像特征，并随着曲线演化动态调整参数；
c)向上逐层重复直至原始图像。
由于采用了小波多尺度框架和尺度问形状约束，算法具有曲线演化结果稳健鲁棒，不易陷入局部极小和发生边界泄漏等优点，非常适合心脏超声图像噪声高、对比度低和边界灰度梯度不显著的特点。在实际临床三维超声图像上的实验表明，算法分割结果和人工分割结果的误差在合理范围内。
三)提出一种心脏MR图像内外壁联合分割和时序追踪算法
为了计算左心室质量(left ventricle mass，LVM)等重要心功能参数，在得到各层面左心室短轴像的内壁精确分割结果后，还需要对左心室的外壁做分割，外壁的边界和周围的组织在某些位置灰度分布非常接近，如果不加约束很容易发生边界泄漏，本文提出一种灰度和距离双重约束的方法，实现了左心室外壁的鲁棒分割。
a)初始化和内壁分割：
假设左心室是一个被切割椭球体，选择较小半径和轴长使切割椭球体位于图像中左心室的内部。选择其中某个时刻t_0的三维图像集I_(：，t_0)，初始化各层面Z_i中的水平集函数，使其所包含曲线为对应层面上的截面圆，用第四章中的改进几何动态轮廓线算法分别在各层图像中进行演化，得到I_(：，t_0)，各层面心室内壁的分割结果。
b)心室外壁分割
左心室外壁边界有特殊特点，某些方向灰度对比度很好，但某些方向就很微弱或几乎没有区别，不管是采用边界或区域灰度信息都很难区分。所以心室外壁的分割必须结合解剖结构先验信息如到心室内壁最近点的距离，来控制外壁分割曲线的演化。
外壁分割以心室内壁分割结果为初始轮廓，曲线演化外力场的设计以较强的向外扩张膨胀外力为主导，用区域均值和曲线到心室内壁最近点的距离作约束，得到合理的心室外壁轮廓。
具体方法是计算心室内壁向外邻近一个小环状区域的灰度均值m~e：如果演化曲线上的某点区域灰度不同于聊m~e，那么说明曲线演化达到或超出了心室外壁，应该停止或降低速度；如果外壁上的点离内壁上最近的点距离超过2.5cm，那么根据解剖知识曲线也应该超过了外壁区域，应该改变方向。由于内外壁之间的心肌组织区域灰度比较均一，而且心室内外壁距离一般小于2.5厘米，所以当曲线演化到最大距离之外，或者是局部区域的灰度均值不同于图像中心肌区域的灰度均值时，改变曲线演化方向或降低曲线演化速度。保证心外壁的分割结果满足先验知识的要求。
c)时序追踪算法
由于左心室内壁的运动在空间和时间上是一个连续的周期过程，所以在分割t_0时刻MR心脏图像各短轴层面上的心室内壁后，为了在时序上追踪内壁的连续运动，本节提出使用时序追踪算法来跟踪同一短轴层面上内壁运动过程。
以I_(Z_i△_0)图像心室内壁分割结果为初始轮廓，向同一层面Z_i在不同时刻的图像I_(Z，：)扩展演化，得到I_(Z，：)上所有时刻的心室内壁轮廓。因为同层面的心室壁随时间的变化过程是平滑和渐进的，提出利用时间上相邻的各帧的改进GVF场(的高斯加权平均来得到当前帧的改进GVF场，同时利用该场和图像数据演化曲线，得到时间上相邻各帧I_(Z，：)的心室内轮廓，遍历所有层面Z_i后，再以得到内壁轮廓为起点，得到对应的心室外壁轮廓。
四)根据心脏图像左心室内外壁分割结果，实现了心功能量化参数的计算
计算机辅助心脏图像分析最终需要表现为具有临床意义的定量心功能参数。结合本文MR心脏图像左心室内壁分割算法和灰度和距离约束下的左心室外壁分割算法，构造心脏的三维模型，实现了各种量化的心功能参数的计算。
With the improvement of living condition and prolonged life expectancy, cardiovascular diseases (CVD) have been the number one cause of death in modem society. The early quantitative diagnosis and accurate evaluation of CVD are critical to improving quality of life and prolong life expectancy.
Human heart is a chambered, muscular organ controlled by electrical rhythm that pumps blood into body. Many types of modem medical imaging equipment are capable of cardiovascular imaging. Recently the rapid development of imaging equipments such as magnetic resonance imaging (MRI), computer tomography (CT), ultrasonic (US) and nuclear medicine (NM), has led to dramatically shortening of imaging time and higher spatial and temporal resolution. These make it possible for dynamic 3D cardiovascular imaging.
The merits of MRI include good soft tissue contrast, arbitrary imaging plane etc. MRI has natural high contrast between blood and other tissue because of the physical principle of imaging. It is capable of evaluating the anatomy, morphology, quantitative heart function indices, blood flow and viability of regional heart muscle at the same time. In recent years, 3D ultrasonic comes into use for clinical cardiac function evaluation. It is not only able to show the 2D cross section like traditional US, but also make real time volume imaging of heart structure. With the aid of post processing software, it can select arbitrary plane for diagnosis, which enable physician to see as many anatomy structures as possible and measure their properties quantitatively. After volume rending or surface rending, it is more intuitive to observe the structures than traditional 2D US and to some extent release the relying on medical expertise.
The development of cardiac imaging equipments leads to enormous image data. Typically, cardiac imaging acquires 3D volume data which change with time during the cardiac cycle, so called 4D data. Traditional method of 2D diagnosis by clinical experts' subjective observation is problematic. Firstly, it is hard to show 4D data in 2D form, the traditional way of observing projection image or tomography imaging can hardly pick up any clinical significant information from 4D data. Secondly, it is hardly to get quantitative information merely by subjective analysis because manual delineation of chamber boundaries is time-consuming and prone to intra observer and inter observer variability. These facts limit the full exploitation of the imaging ability. Although some of the imaging equipments provide some simple computer aided image analysis software. They only take use of some simple geometric models and calculate some global cardiac function indices. Therefore, new computer aided medical image analysis software for objective quantitative analysis and getting clinical significant information for diagnosis is indispensable. For cardiac image analysis the segmentation of anatomy structure such as left ventricle is the bottle-neck in clinical application.
Image segmentation is one of the most fundamental and important research topics in the area of image processing and analysis. The researchers have proposed various segmentation methods based on different theory frameworks and image features. The successful implementation of image segmentation technique in medical images is closely related to the anatomy structure it deals with and the clinical environmental itbeing applied. The cardiac images have its unique properties. To achieve successfully segmentation of cardiac images, we must combine segmentation techniques, the specified image features and anatomy structure of interesting together.
In this thesis, we propose several algorithms for cardiac MR and US image left ventricle segmentation, respectively. The main contribution of this thesis is list as following.
1. A novel generalized fuzzy active contour model is proposed in this thesis. Combined with prior statistic shape model based on level set framework from expert manual outlines, the algorithm is capable of robust segmentation of endocardium borders in cardiac short axis MR images.
Segmentation of left ventricle borders from MR dynamic 3D sequential images is the most important prerequisite for computer aided cardiac image analysis and quantitative measurement of heart function. It is because of complicate and non-rigid periodic motion of heart, respiratory motion and limit time resolution of MR that thecardiac MR images typically have low SNR and are full of weak edges. Further more, segmentation is an ill-posed problem, or say, the pose and reflection properties of the object and the noise from the acquisition devices are some of the factors that can interfere with it, there by, the traditional methods based on active contour model(ACM), regional growing often lead to failure in cardiac image segmentation.
The introduction of gradient vector flow(GVF) greatly improves the dynamic capture range of curve and enabled the convergence to concave borders. The GVF is estimated from the continuous gradient space. The diffusion process of GVF leads to a measurement that is contextual. This is due to the fact that multiple boundary information contributes to the estimation of the GVF.
The accurate image edge information is the key to calculate GVF. Considering the fuzzy and weak edges is common in cardiac MR images, the generalized fuzzy operator (GFO) is incorporated into the diffusion process of GVF in order to handle the weak edge detection. The resulting vector field is incorporating into the evolution equation of ACM. By designing the new external force based on general fuzzy gradient vector flow, the algorithm improves both dynamic capture range and robustness to fuzz3, object borders, and achieves successful application to the segmentation and tracking of LV borders in cardiac MR images. The advantages are the capability of locating the fuzzy object border in strong noisy image like cardiac MR and little human intervention.
Further, past research indicated the incorporation of anatomy and human expertise as prior knowledge can improve the efficiency of computation and the robustness to noise and fuzzy edge. We construct a statistic shape model based on level set framework from human expert manual outlines of MR left ventricle. The prior shape model is used to guide the evolution of curve. Experiments on clinical ECG gated 4-D cardiac MR images show that the results are close to the manual outlines of medical experts.
2. A wavelet multi-scale curve evolution algorithm based on level set framework is proposed and robust segmentation of cardiac ultrasonic left ventricle is achieved.
Due to the existence of attenuation, shadows and speckle noises in ultrasonic images, the segmentation of ultrasonic images is a very difficult task. Traditional image segmentation methods based on Gaussian model often fail in echocardiographic images. Classic methods such as ACM are apt to leak due to the existence of weakand broken edges. In 2001, Tony proposed the model named Active Contour Without Edge (ACWE), which is based on regional homogeneity. ACWE has the merit of robustness and insensitivity to initial position. But the prerequisite of ACWE is the regional gray level distribution of image is Gaussian.
Wavelets are a powerful mathematical tool for hierarchically decomposing functions and signals both in frequency and spatial domain. Using wavelets, a signal can be described in terms of a coarse approximation, plus details that range from broad to narrow. Regardless of whether the function of interest is an image, a curve, or a surface, wavelets provide an elegant technique for representing the levels of detail present. Wavelet theory uses a two-dimensional expansion set to characterize and give a time-frequency localization of a one-dimensional signal. Since this is a linear system, the signal can be reconstructed by a weighted sum of the basis functions. In contrast to the one-dimensional Fourier basis localized in only frequency, the wavelet basis is two-dimensional - localized in both frequency and time. A signal's energy, therefore, is usually well represented by just a few wavelet expansion coefficients.
Generally speaking, a typical echocardiographic image contains regular region with little change, texture region with similar intensity distribution pattern and sharp edges. Wavelet is successfully applied to model and remove noise in ultrasonic images. After wavelet decomposition, the different kind of information is divided into different scales. For example, the regular regions mainly exist in coarse scale and sharp edge in fine scale. In echocardiographic images, region inside the LV has the similar texture and intensity distribution which can be easily outlined by region based level set algorithm. Sharpe edge in fine scale can be better used by edge based level set evolution. These characteristics have motivated us to combine the region based and edge based level set based active contour model through the coarse to fine scale and use iner-scale constrain to improve the robustness of segmentation.
After wavelet decomposition of ultrasonic images, the wavelet coefficient in high level low frequency sub-band is approximately Gaussian. Based on this characteristic, this paper proposes a novel wavelet multi-scale level set algorithm. Firstly, the echocardiographic image is wavelet transformed to get coarse scale approximation images. Then the algorithm begins with the highest level approximation image and outlines the left ventricle endocardium border with regional and edge constrained ACM. Then the result is interpolated into the next finer level of approximation image as a initial contour, and evolved with edge based and inter scales shape constrained ACM. The weighting parameter between inter scale constrain and image force is tuning during the intra-scale curve evolution.
One of the important problems in curve evolution based on level set frame is the tuning of weighting parameters of different force. There exist three kinds of fore: regional force, edge force and inter-scale constrain force in our algorithm. How to choose the proper weighting parameters is difficult. We propose a dynamic adjusting scheme for these parameters. In the beginning, the curve should be faith to image information, but at end of evolution, inter-scale constrain should become more important to avoid the edge leakage and maintain the inte4-scale similarity.
In sum, the algorithm can be descried by following procedures:
a, Wavelet decomposition the original echocardiography images into multi-scale pyramid, use the edge and region compound model to get the initial endocardium contour in the coarsest level;
b. Use the segmentation results in A_jf to interpolate the initial contour in finer level A_(j-1)f then evolve the contour and get the endocardium contour in A_(j-1)f;
c. If reach the finest level (original image), stop the algorithm, elseifjump to step
(b);
Because of the inter-scale constrain and compound force, our algorithm is robust to local minimums and weak edges and suitable for the US image with high noise, poor contrast and small edge gradient. Comparison is made between the traditional ACM with edges and GACM methods. Experiments on clinical 3D echocardiographic images also show the algorithm's result is very close to the expert manual outlines.
3. A new associate scheme for enpi- and endocardium segmentation and temporal tracking in cardiac MR image is proposed
Accurate segmentation of endocardium and epicardium is the most important prerequisite for computer aid diagnosis of cardiac function. In this study, we use ~(I_(z,t)(x,y)) to donate the cardiac image in time t and slice position z. especially, ~(I_(z,1)) stand for all cardiac images in slice position z of entire cardiac cycle and ~(I(1-t)) stand for images of all slice position in time frame t. The segmentation and tracking of endo- and epicardium steps is as follows:
a. Segmentation of endocardium
LV is approximately the shape of truncated ellipse as illustrated by Fig. 5. In time~t_0, proper D and L are selected to get a rough initial shape of LV. Then the level set functions in all slices are initialized to embed the curves of truncated ellipse. The adapted geometric active contour model proposed in section 2 is then applied to evolve the curve to get the endocardium border in~I_(:,to.)
b. Segmentation of epicardium
Segmentation of epicardium begins with the results of endocardium segmentation. In cardiac MR images, the cardiac muscles appear to have gray levels of Gaussian distribution. By an ad hoc designed regional balloon force controlled by local mean gray level and distance from endocardium, the curves evolve outward to get sensible epicardium borders. At each evolving steps, the local mean gray level ~m_p in a outward neighborhood is calculated and compare to the initial ~(m~e_0) calculated in endocardium neighborhoods. If the ~(m_p) is different from ~(m_e_0), then the curve could have evolved out of the epicardium and the evolving speed should become slow. Further more, cording to the anatomy of human heart, the maximum distance of epicardium for endocardium should be around 2.5 cm, once the evolving curves are out of the this distance, the evolution should be stopped and pulled back. According to equation 7, when the curves are out of the cardiac muscle area (mean gray level changes), or the distance is bigger than 2.5 cm, the curves are slowed down or pulled back to ensure the results are robust and compliant with anatomy prior knowledge.
c. Temporal propagations
Endocardium segmentation results in ~(I_(zi, eo) are used as initial curve and propagated to the images in the same slice position z in other time frame and get the endocardium borders of~(I_(=,:)) in all time. Because the motion of ventricle border is regular and progressive (Fig.7), the time neighborhood GFGVF fields are weighted summed to get current frame GFGVF. After get the endocardium border in all slice position ~(Z_i), the step b is executed to get the epicardium borders.
4. Implement the quantitative cardiac function calculation according to the endoand epicardium segmentation from cardiac images.
The ultimate goal of computer aided medical image analysis is some clinical significant quantitative cardiac indices. After segmentation of endo- and epicardium from cardiac MR image, 3D model is construct and various quantitative cardiac indices was calculated based on it.
引文
[1] 世界卫生统计年报：World Health Statistical Annual，2002，世界卫生组织
[2] 中华人民共和国卫生部 中国卫生统计年鉴2005，北京：人民卫生出版社 2005．
[3] Sating, D., et al., Computer-assisted analysis of 4D cardiac MR image sequences alter myocardial infarction. Methods Inf Med, 2006.45(4): p. 377-83.
[4] Dawson, D., et al., Quantitative 3-dimensional echocardiography for accurate and rapid cardiac phenotype characterization in mice. Circulation, 2004. 110(12): p. 1632-7.
[5] van der Geest, R.J., et al., Evaluation of a new method for automated detection of left ventricular boundaries in time series of magnetic resonance images using an Active Appearance Motion Model. J Cardiovasc Magn Reson, 2004. 6(3): p. 609-17.
[6] Sugioka, K., et al., Rapid and accurate noninvasive assessment of global left ventricular systolic function using biplane advanced automated contour tracking method. J Am Soc Echocardiogr, 2003. 16(12): p. 1237-43.
[7] Podgoreanu, M.V., et al., Quantitative echocardiographic assessment of regional wall motion and left ventricular asynchrony with color kinesis in cardiac surgery patients. Anesth Analg, 2003. 96(5): p. 1294-300, table of contents.
[8] Wolf, I., et al., ROPES: a semiautomated segmentation method for accelerated analysis of three-dimensional echocardiographic data. IEEE Trans Med Imaging, 2002. 21(9): p. 1091-104.
[9] van der Geest, R.J. and J.H. Reiber, Quantification in cardiac MRI. J Magn Reson Imaging, 1999.10(5): p. 602-8.
[10] Wise, R.G., et al., Geometrical models of left ventricular contraction from MRI of the normal and spontaneously hypertensive rat heart. Phys Med Biol, 1999.44(10): p. 2657-76.
[11]Rademakers, F.E. and J. Bogaert, Left ventricular myocardial tagging. Int J Card Imaging, 1997. 13(3): p. 233-45.
[1] 柏树令，应大君，王海杰等．系统解剖学．北京：人民卫生出版社，2002
[2] 李坤成，孙泽民，赵世华，D．Revel．心血管磁共振成像诊断学．北京：人民卫生出版社，1997
[3] Santarelli, M.F., et al., Automated cardiac MR image segmentation: theory and measurement evaluation. Med Eng Phys, 2003.25(2): p. 149-59.
[4] Krug, R., J.M. Boese, and L.R. Schad, Determination of aortic compliance from magnetic resonance images using an automatic active contour model. Phys Med Biol, 2003.48(15): p. 2391-404.
[5] Mitchell, S.C., et al., 3-D active appearance models: segmentation of cardiac MR. and ultrasound images. IEEE Trans Med Imaging, 2002.21(9): p. 1167-78.
[6] Oost, C.R., et al., Multi-View Active Appearance Models: application to X-ray LV angiography and cardiac MRI. InfProcess Med Imaging, 2003.18: p. 234-45.
[7] Makowski, P., et al., Two-phase active contour method for semiautomatic segmentation of the heart and blood vessels from MRI images for 3D visualization. Comput Med Imaging Graph, 2002. 26(1): p. 9-17.2
[8] Miller, S., et al., Conventional high resolution versus fast T(2)-weighted MR imaging of the heart: assessment of reperfusion induced myocardial injury in an animal model. Magn Reson Imaging, 2000.18(9): p. 1069-77.
[9] Aladl, U.E., et al., Automated image registration of gated cardiac single-photon emission computed tomography and magnetic resonance imaging. J Magn Reson Imaging, 2004. 19(3): p. 283-90.
[10]Makela, T., et al., A 3-D model-based registration approach for the PET, MR and MCG cardiac data fusion. Med Image Anal, 2003. 7(3): p. 377-89.
[11] Sturm, B., et al., Registration of 3D CT angiography and cardiac MR images in coronary artery disease patients. Int J Cardiovasc Imaging, 2003.19(4): p. 281-93.
[12] Sanchez-Ortiz, G.I., D. Rueckert, and P. Burger, Knowledge-based tensor anisotropic diffusion of cardiac magnetic resonance images. Med Image Anal, 1999. 3(1): p. 77-101.
[13]Lelieveldt, B.P., et al., Anatomical model matching with fuzzy implicit surfaces for segmentation of thoracic volume scans. IEEE Trans Med Imaging, 1999.18(3): p. 218-30.
[14]Tanki, N., et al., Quantification of left ventricular volumes from cardiac cine MRI using active contour model combined with gradient vector flow. Magn Reson Med Sci,2005. 4(4): p. 191-6.
[15]Mitchell, S.C., et al., Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images. IEEE Trans Med Imaging, 2001. 20(5): p. 415-23.
[16]Saring, D., et al., Computer-assisted analysis of 4D cardiac MR image sequences after myocardial infarction. Methods Inf Med, 2006. 45(4): p. 377-83.
[17]Pednekar, A.S. and I.A. Kakadiaris, Image segmentation based on fuzzy connectedness using dynamic weights. IEEE Trans Image Process, 2006. 15(6): p. 1555-62.
[18]Pednekar, A.S., et al., Automatic identification of the left ventricle in cardiac cine-MR images: dual-contrast cluster analysis and scout-geometry approaches. J Magn Reson Imaging, 2006. 23(5): p. 641-51.
[19]Sermesant, M., H. Delingette, and N. Ayache, An electromechanical model of the heart for image analysis and simulation. IEEE Trans Med Imaging, 2006. 25(5): p. 612-25.
[20]Ulzheimer, S. and W.A. Kalender, Assessment of calcium scoring performance in cardiac computed tomography. Eur Radiol, 2003.13(3): p. 484-97.
[21]Machac, J., Cardiac positron emission tomography imaging. Semin Nucl Med, 2005. 35(1): p. 17-36.
[1] R. M. Haralick and L. G. Shapiro, Image Segmentation Techniques, Comput. Vis. Graph. Ira. Proc., Vol. 29, pp. 100-132, 1985
[2] Stan Z.Li. Markov random field modeling in image analysis. Springer-Verlag Tokyo, 2001.
[3] CHEN Wu-Fan, LU Xian-Qing, CHEN Jian-Jun, and Wu Guo-Xiong, ANew Algorithm of Edge Detection for Color Image: Generalized Fuzzy Operator, SCIENCE in China, Vol. 38, No. 10, pp. 1272-1280, 1995
[4] S. Geman and D. Geman, Stochastic Relaxation, Gibbs Distribution, and Bayesian Restoration of Images, IEEE TPAMI, Vol. 6, pp. 721-741, Nov. 1984
[5] Fenster, A. and B. Chiu, Evaluation of Segmentation algorithms for Medical Imaging. ConfProc IEEE Eng Med Biol Soc, 2005.7: p. 7186-9.
[6] V. Caselles, F. Catte, T. Coll, and F. Dibos, A geometric model for active contours[J], Numerische Mathematik, vol. 66, 1993,pp. 1-31
[7] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[8] Xiao, M., S. Xia, and S. Wang, Geometric active contour model with color and intensity priors for medical image segmentation. Conf Proc IEEE Eng Med Biol Soc, 2005. 6: p. 6496-9.
[9] C. Y. Xu and J. L. Prince, Generalized Gradient Vector Flow External Forces for Active Contours, Signal Processing, Vol. 71, No. 2, pp. 131-139, December 1998
[10]XiaoLan Zeng, Lawrence H. Staib, and et al, Segmentation and Measurement of the Cortex from 3D MRI Using Coupled-Surfaces Propagation, IEEE TMI, Vol.18, No. 10, pp. 927-937, Oct. 1999
[11]MacDonald, D., Avis, D. and Evans, Proximity Constraints in Deformable Models for Cortical Surface Identification, Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 650-659,1998
[12] Lin, X., B. Cowan, and A. Young, Model-based Graph Cut Method for Segmentation of the Left Ventricle. Conf Proc IEEE Eng Med Biol Soc, 2005.3: p. 3059-62.
[13] Yee Lau, P. and S. Ozawa, A region-based approach combining marker-controlled active contour model and morphological operator for image segmentation. Conf Proc IEEE Eng Med Biol Soc, 2004. 3: p. 1652-5.
[14] Jasjit S. Suri, Kecheng Liu, Sameer Singh etc. Shape recovery algorithm using level sets in 2-D/3-D Medical Imagery: a state-of-the-art review[J]. IEEE Transitions on information technology in biomedicine. VOL.6, NO.1, Mar 2002, pp.8-27.
[15]Kass M.,Witkin A., and Terzopoulos, Snake:Active Contour Models, Proc 1st Int. Conf., on Comp. Vision, Vol. 1, No. 4, pp. 321-331, 1987
[16] Ma Wanying,Manjunath B S. Edge flow:a framework of boundary detection and image segmentazion .In Proc.of IEEE Conf.on Computer Vision Pattern ecognition,l 997:744—749
[17]D. L. Pham, C. Xu, and J. L. Prince, A Survey of Current Methods in Medical Image Segmentation, Annual Review of Biomedical Engineering, Vol. 2, pp. 315-338,2000
[18]J. A. Sethian, Fast Marching Level Set Method for Mono- toncally Adavancing Fronts, Proceedings of the National Academy of Sciences 93, Vol. 4, pp.1591-1595,1996
[19]K. Siddiqui, Y. B. Lauriere, and et al., Area and Length Minimizing Flows for Shape Segmentation, IEEE TIP, Vol. 7, pp. 433-443, 1998
[20] Charles A. Bouman and Michael Shapiro, A Multiscale Random Field Model for Bayesian Images Segemntation, IEEE Transactions on Image Processing, Vol. 3, No. 2, pp. 162-177,1994
[21] J. S. Suri, S. K. Setarehdan, and S. Singh, Advanced Algorithmic Approaches to Medical Image Segmentation: State-of-the-Art Applications in Cardiology, Neurology, Mammography and pathology, 1st ed. London, U. K. Springer-verlag, 2001
[22] Dunn F D, Higgins W E. Optimal Gabor filters for texture segmentation. IEEE Transactions on Image Processing, 1995,4(7) :947-964.
[1] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[2] V. Caselles, F. Catte, T. Coil, and F. Dibos, A geometric model for active contours[J], Numerische Mathematik, vol. 66, 1993,pp. 1—31
[3] CHEN Wu-Fan, LU Xian-Qing, CHEN Jian-Jun, and Wu Guo- Xiong, A New Algorithm of Edge Detection for Color Image: Generalized Fuzzy Operator, SCIENCE in China, Vol. 38, No. 10, pp. 1272-1280, 1995
[4] 袁华，吴效明，袁支润，岑人经，GFO在边缘检测中的关键参数定量计算研究，电子学报，Vol．29，No．7，pp．888-890，July，2001
[5] C. Xu and J. L. Prince, Snakes, Shapes, and Gradient Vector Flow[J], IEEE Transactions on Image Processing, 7(3), March 1998. pp. 359-369,
[6] N. Paragios, O. Mellina-Gottardo & V. Ramesh. Gradient Vector Flow Fast Geometric Active Contours[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, pp. 402-407.
[7] 周寿军，梁斌，陈武凡，心脏序列图像运动估计新方法：基于广义模糊梯度矢量流场的形变曲线运动估计与跟踪，计算机学报，Vol．26 No．11 Nov．2003，pp．1470-1478．
[8] Wufan Chen, Shoujun Zhou, Bin Liang: LV contour tracking in MRI sequences based on the generalized fuzzy GVF. ICIP 2004:373-376
[9] Michael Leventon, W.Eric L.Grimson, Oliver Faugeras, Statistical shape influence in geodesics active contours[A], Proc. IEEE Conf Comp. Vision Pattern Recognition, vol. 1,2000, pp..316-323
[10] N. Paragios, Shape-based segmentation and tracking in cardiac image analysis[J], IEEE Trans. Med. Imag. 2003, pp. 773--776.
[11] Stanley J. Osher, Nikos Paragios Geometric Level Set Methods in Imaging Vision and Graphics, Springer Verlag[M], ISBN 0387954880, 2003.
[12] Jasjit S. Suri, Kecheng Liu, Sameer Singh etc. Shape recovery algorithm using level sets in 2-D/3-D Medical Imagery: a state-of-the-art review[J]. IEEE Transitions on information technology in biomedicine. VOL.6, NO. 1, Mar 2002, pp.8-27.
[13] D.Huttenlocher, G.Klanderman, and W. Ruchlidge. Comparing images using the hausdorff distance [J]. IEEE Trans. Part. Analysis and Mach. Intell., vol15,1993, pp.850-863.
[14] M. Leventon, E. Grimson, and O. Faugeras. Statistical shape influence in geodesic active contours[C]. In Proc. IEEE Conf. Comp. Vision and Part. Recog., 2000.
[15]Nguyen, D., K. Masterson, and J.P. Vallee, Comparative evaluation of active contour model extensions for automated cardiac MR image segmentation by regional error assessment. Magma
[16] Lynch, M., O. Ghita, and P.F. Whelan, Automatic segmentation of the left ventricle cavity and myocardium in MRI data. Comput Biol Med, 2006. 36(4): p. 389-407.
[17] Chen, Q., et al., Shape statistics variational approach for the outer contour segmentation of left ventricle MR images. IEEE Trans Inf Technol Biomed, 2006. 10(3): p. 588-97.
[18] 11. Zhou, Z., et al., Cardiac MR image segmentation and left ventricle surface reconstruction based on level set method. Stud Health Technol Inform, 2005. 111: p. 629-32.
[19]Uzumcu, M., et al., Multiview active appearance models for simultaneous segmentation of cardiac 2- and 4-chamber long-axis magnetic resonance images. Invest Radiol, 2005.40(4): p. 195-203.
[20]Pluempitiwiriyawej, C, et al., STACS: new active contour scheme for cardiac MR image segmentation. IEEE Trans Med Imaging, 2005. 24(5): p. 593-603.
[21]Ordas, S., et al., Parametric optimization of a model-based segmentation algorithm for cardiac MR image analysis: a grid-computing approach. Stud Health Technol Inform, 2005.112: p. 146-56.
[22] Angelie, E., et al., Optimizing the automatic segmentation of the left ventricle in magnetic resonance images. Med Phys, 2005.32(2): p. 369-75. 16. Lotjonen, J., et al., Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Med Image Anal, 2004. 8(3): p. 371-86.
[23]Lorenzo-Valdes, M., et al., Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal, 2004. 8(3): p. 255-65.
[24] Shankaranarayanan, A., et al., Segmented k-space and real-time cardiac cine MR imaging with radial trajectories. Radiology, 2001. 221(3): p. 827-36.
[25] Francois, C.J., et al., Left ventricular mass: manual and automatic segmentation of true FISP and FLASH cine MR images in dogs and pigs. Radiology, 2004. 230(2): p. 389-95.
[1] van den Bosch, A.E., B.J. Krenning, and J.R. Roelandt, Three-dimensional echocardiography. Minerva Cardioangiol, 2005.53(3): p. 177-84.
[2] Noble, J.A. and D. Boukerroui, Ultrasound image segmentation: a survey. IEEE Trans Med Imaging, 2006.25(8): p. 987-1010.
[3] Liu, H., et al., Multiresolution medical image segmentation based on wavelet transform. ConfProc IEEE Eng Med Biol Soc, 2005.4: p. 3418-21.
[4] T ao, Z., Beaty, J., Jaffe, etc. Gray level models for segmenting myocardium and blood in cardiac ultrasound images. In: Conference Proceedings of International Symposium on Biomedical Imaging 2002, pp. 265-269.
[5] Nikos Paragios, Marie-Pierre Jolly, Maxime Taron, etc. Active Shape Models and Segmentation of the Left Ventricle in Echocardiography. Scale-Space 2005: 131-142
[6] Gao, Y. Gao, S.Ding, etc. Semi-automatic segmentation of the endocardial boundaryin intracardiac echocardiographic images, EMBC 2004, Vol.3, pp. 1911-1913
[7] Angelini, E.D., Laine, A.F., Takuma, S., etc., LV volume quantification via spatiotemporal analysis of real-time 3-d echocardiography. IEEE Transactions on Medical Imaging (2001). 20 (6), 457-469.
[8] S. Guptal, R. C. Chauhanl and S. C. Sexana, Wavelet-based statistical approach for speckle reduction in medical ultrasound images, Medical and Biological Engineering and Computing, Springer Berlin / Heidelberg, March 2004, Vol.42, pp: 189-192
[9] Mallat, S.G.,A theory for multiresolution signal decomposition: the wavelet representation, IEEE PAMI Jul 1988 vol. 11 ,pp.:674-693
[10] Osher S, Sethian J A. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[11]Tony F. Chan, Luminita A. Vese: Active contours without edges. IEEE Transactions on Image Processing 2001 vol. 10(2), pp.: 266-277
[12]Manivannan, J., et al., Quantitative evaluation of left ventricle performance from two dimensional echo images. Echocardiography, 2006. 23(2): p. 87-92.
[13]Zagrodsky, V., et al., Registration-assisted segmentation of real-time 3-D echocardiographic data using deformable models. IEEE Trans Med Imaging, 2005. 24(9): p. 1089-99.
[14]Corsi, C, et al., A semi-automatic method for left ventricle volume estimate: an in vivo validation study. Comput Cardiol, 2001. 28: p. 109-12.
[15]Corsi, C, et al., Real-time 3D echocardiographic data analysis for left ventricular volume estimation. Comput Cardiol, 2000. 27: p. 107-10.
[16] Song, M., et al., Integrated surface model optimization for freehand three-dimensional echocardiography. IEEE Trans Med Imaging, 2002. 21(9): p. 1077-90.
[17] Ye, X., J.A. Noble, and D. Atkinson, 3-D freehand echocardiography for automatic left ventricle reconstruction and analysis based on multiple acoustic windows. IEEE Trans Med Imaging, 2002. 21(9): p. 1051-8.
[18]Malassiotis, S. and M.G. Strintzis, Tracking the left ventricle in echocardiographicimages by learning heart dynamics. IEEE Trans Med Imaging, 1999. 18(3): p. 282-90.
[19] Santos Conde, J.E., et al., [Algorithm for automatic endocardium identification in digital echocardiography image sequences]. Biomed Tech (Berl), 1998.43(7-8): p. 221-6.
[20]Mikic, I., S. Krucinski, and J.D. Thomas, Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates. IEEE Trans Med Imaging, 1998. 17(2): p. 274-84.
[21]Hackstein, J., O. Pichler, and A. Teuner, [Computer-assisted analysis of ultrasound sequences of the left ventricle for determining ejection fraction]. Biomed Tech (Berl), 1996.41(5): p. 118-22
[22]T. Chan and B. Sandberg and L. Vese,Active contours without edges. IEEE Trans. on Image Processing, 2001,10(2):266-277.
[23]Christophe C , Philippe R, Vlady B. Statistical region snake based segmentation adapted to different physical noise models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999 ,21 (11): 1145-1157.
[24] Pascal M, Philippe R, Francois G, et al. Influence of the noise model on level set active contour segmentation. IEEE Transactions on Pat tern Analysis and Machine Intelligence, 2004 ,26 (6) :799-803.
[25]Ning L, Weichuan Y, J ames S D. Combinative multi scale level set framework for echocardiographic image segmentation . Medical Image Analysis , 2004, 7(4) :529-537.
[1] N. Paragios, Shape-based segmentation and tracking in cardiac image analysis, IEEE Trans. Med. Imag. 2003 p.773-776.
[2] Setser, R.M., S.E. Fischer, and C.H. Lorenz, Quantification of left ventricular function with magnetic resonance images acquired in real time. J Magn Reson Imaging, 2000. 12(3): p. 430-8.
[3] van der Geest, R.J. and J.H. Reiber, Quantification in cardiac MRI. J Magn Reson Imaging, 1999. 10(5): p. 602-8.
[4] Tanki, N., et al., Quantification of left ventricular volumes from cardiac cine MRI using active contour model combined with gradient vector flow. Magn Reson Med Sci, 2005.4(4): p. 191-6.
[5] Petitjean, C., N. Rougon, and P. Cluzel, Assessment of myocardial function: a review of quantification methods and results using tagged MRI. J Cardiovasc Magn Reson, 2005.7(2): p. 501-16.
[6] Maim, S., et al., Quantification of resting myocardial blood flow velocity in normal humans using real-time contrast echocardiography. A feasibility study. Cardiovasc Ultrasound, 2005.3: p. 16.
[7] Inaba, Y., et al., Strain rate imaging for noninvasive functional quantification of the left atrium: comparative studies in controls and patients with atrial fibrillation. J Am Soc Echocardiogr, 2005.18(7): p. 729-36.
[8] Toyoda, T., et al., Assessment of regional myocardial strain by a novel automated tracking system from digital image files. J Am Soc Echocardiogr, 2004. 17(12): p. 1234-8.
[9] van der Geest, R.J., B.P. Lelieveldt, and J.H. Reiber, Quantification of global and regional ventricular function in cardiac magnetic resonance imaging. Top Magn Reson Imaging, 2000.11(6): p. 348-58.
[10]Schuijf, J.D., et al., Quantification of myocardial infarct size and transmurality by contrast-enhanced magnetic resonance imaging in men. Am J Cardiol, 2004.94(3): p. 284-8.
[1] Heye Zhang, Chun Lok Wong, Pengcheng Shi. An Inverse Recovery of Cardiac Electrical Propagation from Image Sequences. MIAR 2006:132-139
[2] Heye Zhang, Chun Lok Wong, Pengcheng Shi: Estimation of Cardiac Electrical Propagation from Medical Image Sequence. MICCAI (2) 2006:528-535
[3] Toili, T, et al., Artificially enlarged training set in image segmentation. Med Image Comput Comput Assist Interv Int Conf Med Image Comput Comput Assist Interv, 2006.9(Pt 1): p. 75-82.
[4] Yah, A.T., et al., Characterization ofmicrovascular dysfunction after acute myocardial infarction by cardiovascular magnetic resonance first-pass perfusion and late gadolinium enhancement imaging. J Cardiovasc Magn Reson, 2006.8(6): p. 831-7.
[5] Schuijf, J.D., et al., Quantification of myocardial infarct size and transmurality by contrast-enhanced magnetic resonance imaging in men. Am J Cardiol, 2004. 94(3): p. 284-8.
[6] Petitjean, C., N. Rougon, and P. Cluzel, Assessment of myocardial function: a review of quantification methods and results using tagged MRI. J Cardiovasc Magn Reson, 2005.7(2): p. 501-16.
[2] 中华人民共和国卫生部 中国卫生统计年鉴2005，北京：人民卫生出版社 2005．
[3] Sating, D., et al., Computer-assisted analysis of 4D cardiac MR image sequences alter myocardial infarction. Methods Inf Med, 2006.45(4): p. 377-83.
[4] Dawson, D., et al., Quantitative 3-dimensional echocardiography for accurate and rapid cardiac phenotype characterization in mice. Circulation, 2004. 110(12): p. 1632-7.
[5] van der Geest, R.J., et al., Evaluation of a new method for automated detection of left ventricular boundaries in time series of magnetic resonance images using an Active Appearance Motion Model. J Cardiovasc Magn Reson, 2004. 6(3): p. 609-17.
[6] Sugioka, K., et al., Rapid and accurate noninvasive assessment of global left ventricular systolic function using biplane advanced automated contour tracking method. J Am Soc Echocardiogr, 2003. 16(12): p. 1237-43.
[7] Podgoreanu, M.V., et al., Quantitative echocardiographic assessment of regional wall motion and left ventricular asynchrony with color kinesis in cardiac surgery patients. Anesth Analg, 2003. 96(5): p. 1294-300, table of contents.
[8] Wolf, I., et al., ROPES: a semiautomated segmentation method for accelerated analysis of three-dimensional echocardiographic data. IEEE Trans Med Imaging, 2002. 21(9): p. 1091-104.
[9] van der Geest, R.J. and J.H. Reiber, Quantification in cardiac MRI. J Magn Reson Imaging, 1999.10(5): p. 602-8.
[10] Wise, R.G., et al., Geometrical models of left ventricular contraction from MRI of the normal and spontaneously hypertensive rat heart. Phys Med Biol, 1999.44(10): p. 2657-76.
[11]Rademakers, F.E. and J. Bogaert, Left ventricular myocardial tagging. Int J Card Imaging, 1997. 13(3): p. 233-45.
[1] 柏树令，应大君，王海杰等．系统解剖学．北京：人民卫生出版社，2002
[2] 李坤成，孙泽民，赵世华，D．Revel．心血管磁共振成像诊断学．北京：人民卫生出版社，1997
[3] Santarelli, M.F., et al., Automated cardiac MR image segmentation: theory and measurement evaluation. Med Eng Phys, 2003.25(2): p. 149-59.
[4] Krug, R., J.M. Boese, and L.R. Schad, Determination of aortic compliance from magnetic resonance images using an automatic active contour model. Phys Med Biol, 2003.48(15): p. 2391-404.
[5] Mitchell, S.C., et al., 3-D active appearance models: segmentation of cardiac MR. and ultrasound images. IEEE Trans Med Imaging, 2002.21(9): p. 1167-78.
[6] Oost, C.R., et al., Multi-View Active Appearance Models: application to X-ray LV angiography and cardiac MRI. InfProcess Med Imaging, 2003.18: p. 234-45.
[7] Makowski, P., et al., Two-phase active contour method for semiautomatic segmentation of the heart and blood vessels from MRI images for 3D visualization. Comput Med Imaging Graph, 2002. 26(1): p. 9-17.2
[8] Miller, S., et al., Conventional high resolution versus fast T(2)-weighted MR imaging of the heart: assessment of reperfusion induced myocardial injury in an animal model. Magn Reson Imaging, 2000.18(9): p. 1069-77.
[9] Aladl, U.E., et al., Automated image registration of gated cardiac single-photon emission computed tomography and magnetic resonance imaging. J Magn Reson Imaging, 2004. 19(3): p. 283-90.
[10]Makela, T., et al., A 3-D model-based registration approach for the PET, MR and MCG cardiac data fusion. Med Image Anal, 2003. 7(3): p. 377-89.
[11] Sturm, B., et al., Registration of 3D CT angiography and cardiac MR images in coronary artery disease patients. Int J Cardiovasc Imaging, 2003.19(4): p. 281-93.
[12] Sanchez-Ortiz, G.I., D. Rueckert, and P. Burger, Knowledge-based tensor anisotropic diffusion of cardiac magnetic resonance images. Med Image Anal, 1999. 3(1): p. 77-101.
[13]Lelieveldt, B.P., et al., Anatomical model matching with fuzzy implicit surfaces for segmentation of thoracic volume scans. IEEE Trans Med Imaging, 1999.18(3): p. 218-30.
[14]Tanki, N., et al., Quantification of left ventricular volumes from cardiac cine MRI using active contour model combined with gradient vector flow. Magn Reson Med Sci,2005. 4(4): p. 191-6.
[15]Mitchell, S.C., et al., Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images. IEEE Trans Med Imaging, 2001. 20(5): p. 415-23.
[16]Saring, D., et al., Computer-assisted analysis of 4D cardiac MR image sequences after myocardial infarction. Methods Inf Med, 2006. 45(4): p. 377-83.
[17]Pednekar, A.S. and I.A. Kakadiaris, Image segmentation based on fuzzy connectedness using dynamic weights. IEEE Trans Image Process, 2006. 15(6): p. 1555-62.
[18]Pednekar, A.S., et al., Automatic identification of the left ventricle in cardiac cine-MR images: dual-contrast cluster analysis and scout-geometry approaches. J Magn Reson Imaging, 2006. 23(5): p. 641-51.
[19]Sermesant, M., H. Delingette, and N. Ayache, An electromechanical model of the heart for image analysis and simulation. IEEE Trans Med Imaging, 2006. 25(5): p. 612-25.
[20]Ulzheimer, S. and W.A. Kalender, Assessment of calcium scoring performance in cardiac computed tomography. Eur Radiol, 2003.13(3): p. 484-97.
[21]Machac, J., Cardiac positron emission tomography imaging. Semin Nucl Med, 2005. 35(1): p. 17-36.
[1] R. M. Haralick and L. G. Shapiro, Image Segmentation Techniques, Comput. Vis. Graph. Ira. Proc., Vol. 29, pp. 100-132, 1985
[2] Stan Z.Li. Markov random field modeling in image analysis. Springer-Verlag Tokyo, 2001.
[3] CHEN Wu-Fan, LU Xian-Qing, CHEN Jian-Jun, and Wu Guo-Xiong, ANew Algorithm of Edge Detection for Color Image: Generalized Fuzzy Operator, SCIENCE in China, Vol. 38, No. 10, pp. 1272-1280, 1995
[4] S. Geman and D. Geman, Stochastic Relaxation, Gibbs Distribution, and Bayesian Restoration of Images, IEEE TPAMI, Vol. 6, pp. 721-741, Nov. 1984
[5] Fenster, A. and B. Chiu, Evaluation of Segmentation algorithms for Medical Imaging. ConfProc IEEE Eng Med Biol Soc, 2005.7: p. 7186-9.
[6] V. Caselles, F. Catte, T. Coll, and F. Dibos, A geometric model for active contours[J], Numerische Mathematik, vol. 66, 1993,pp. 1-31
[7] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[8] Xiao, M., S. Xia, and S. Wang, Geometric active contour model with color and intensity priors for medical image segmentation. Conf Proc IEEE Eng Med Biol Soc, 2005. 6: p. 6496-9.
[9] C. Y. Xu and J. L. Prince, Generalized Gradient Vector Flow External Forces for Active Contours, Signal Processing, Vol. 71, No. 2, pp. 131-139, December 1998
[10]XiaoLan Zeng, Lawrence H. Staib, and et al, Segmentation and Measurement of the Cortex from 3D MRI Using Coupled-Surfaces Propagation, IEEE TMI, Vol.18, No. 10, pp. 927-937, Oct. 1999
[11]MacDonald, D., Avis, D. and Evans, Proximity Constraints in Deformable Models for Cortical Surface Identification, Proceedings of the First International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 650-659,1998
[12] Lin, X., B. Cowan, and A. Young, Model-based Graph Cut Method for Segmentation of the Left Ventricle. Conf Proc IEEE Eng Med Biol Soc, 2005.3: p. 3059-62.
[13] Yee Lau, P. and S. Ozawa, A region-based approach combining marker-controlled active contour model and morphological operator for image segmentation. Conf Proc IEEE Eng Med Biol Soc, 2004. 3: p. 1652-5.
[14] Jasjit S. Suri, Kecheng Liu, Sameer Singh etc. Shape recovery algorithm using level sets in 2-D/3-D Medical Imagery: a state-of-the-art review[J]. IEEE Transitions on information technology in biomedicine. VOL.6, NO.1, Mar 2002, pp.8-27.
[15]Kass M.,Witkin A., and Terzopoulos, Snake:Active Contour Models, Proc 1st Int. Conf., on Comp. Vision, Vol. 1, No. 4, pp. 321-331, 1987
[16] Ma Wanying,Manjunath B S. Edge flow:a framework of boundary detection and image segmentazion .In Proc.of IEEE Conf.on Computer Vision Pattern ecognition,l 997:744—749
[17]D. L. Pham, C. Xu, and J. L. Prince, A Survey of Current Methods in Medical Image Segmentation, Annual Review of Biomedical Engineering, Vol. 2, pp. 315-338,2000
[18]J. A. Sethian, Fast Marching Level Set Method for Mono- toncally Adavancing Fronts, Proceedings of the National Academy of Sciences 93, Vol. 4, pp.1591-1595,1996
[19]K. Siddiqui, Y. B. Lauriere, and et al., Area and Length Minimizing Flows for Shape Segmentation, IEEE TIP, Vol. 7, pp. 433-443, 1998
[20] Charles A. Bouman and Michael Shapiro, A Multiscale Random Field Model for Bayesian Images Segemntation, IEEE Transactions on Image Processing, Vol. 3, No. 2, pp. 162-177,1994
[21] J. S. Suri, S. K. Setarehdan, and S. Singh, Advanced Algorithmic Approaches to Medical Image Segmentation: State-of-the-Art Applications in Cardiology, Neurology, Mammography and pathology, 1st ed. London, U. K. Springer-verlag, 2001
[22] Dunn F D, Higgins W E. Optimal Gabor filters for texture segmentation. IEEE Transactions on Image Processing, 1995,4(7) :947-964.
[1] Osher S, Sethian J. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[2] V. Caselles, F. Catte, T. Coil, and F. Dibos, A geometric model for active contours[J], Numerische Mathematik, vol. 66, 1993,pp. 1—31
[3] CHEN Wu-Fan, LU Xian-Qing, CHEN Jian-Jun, and Wu Guo- Xiong, A New Algorithm of Edge Detection for Color Image: Generalized Fuzzy Operator, SCIENCE in China, Vol. 38, No. 10, pp. 1272-1280, 1995
[4] 袁华，吴效明，袁支润，岑人经，GFO在边缘检测中的关键参数定量计算研究，电子学报，Vol．29，No．7，pp．888-890，July，2001
[5] C. Xu and J. L. Prince, Snakes, Shapes, and Gradient Vector Flow[J], IEEE Transactions on Image Processing, 7(3), March 1998. pp. 359-369,
[6] N. Paragios, O. Mellina-Gottardo & V. Ramesh. Gradient Vector Flow Fast Geometric Active Contours[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, pp. 402-407.
[7] 周寿军，梁斌，陈武凡，心脏序列图像运动估计新方法：基于广义模糊梯度矢量流场的形变曲线运动估计与跟踪，计算机学报，Vol．26 No．11 Nov．2003，pp．1470-1478．
[8] Wufan Chen, Shoujun Zhou, Bin Liang: LV contour tracking in MRI sequences based on the generalized fuzzy GVF. ICIP 2004:373-376
[9] Michael Leventon, W.Eric L.Grimson, Oliver Faugeras, Statistical shape influence in geodesics active contours[A], Proc. IEEE Conf Comp. Vision Pattern Recognition, vol. 1,2000, pp..316-323
[10] N. Paragios, Shape-based segmentation and tracking in cardiac image analysis[J], IEEE Trans. Med. Imag. 2003, pp. 773--776.
[11] Stanley J. Osher, Nikos Paragios Geometric Level Set Methods in Imaging Vision and Graphics, Springer Verlag[M], ISBN 0387954880, 2003.
[12] Jasjit S. Suri, Kecheng Liu, Sameer Singh etc. Shape recovery algorithm using level sets in 2-D/3-D Medical Imagery: a state-of-the-art review[J]. IEEE Transitions on information technology in biomedicine. VOL.6, NO. 1, Mar 2002, pp.8-27.
[13] D.Huttenlocher, G.Klanderman, and W. Ruchlidge. Comparing images using the hausdorff distance [J]. IEEE Trans. Part. Analysis and Mach. Intell., vol15,1993, pp.850-863.
[14] M. Leventon, E. Grimson, and O. Faugeras. Statistical shape influence in geodesic active contours[C]. In Proc. IEEE Conf. Comp. Vision and Part. Recog., 2000.
[15]Nguyen, D., K. Masterson, and J.P. Vallee, Comparative evaluation of active contour model extensions for automated cardiac MR image segmentation by regional error assessment. Magma
[16] Lynch, M., O. Ghita, and P.F. Whelan, Automatic segmentation of the left ventricle cavity and myocardium in MRI data. Comput Biol Med, 2006. 36(4): p. 389-407.
[17] Chen, Q., et al., Shape statistics variational approach for the outer contour segmentation of left ventricle MR images. IEEE Trans Inf Technol Biomed, 2006. 10(3): p. 588-97.
[18] 11. Zhou, Z., et al., Cardiac MR image segmentation and left ventricle surface reconstruction based on level set method. Stud Health Technol Inform, 2005. 111: p. 629-32.
[19]Uzumcu, M., et al., Multiview active appearance models for simultaneous segmentation of cardiac 2- and 4-chamber long-axis magnetic resonance images. Invest Radiol, 2005.40(4): p. 195-203.
[20]Pluempitiwiriyawej, C, et al., STACS: new active contour scheme for cardiac MR image segmentation. IEEE Trans Med Imaging, 2005. 24(5): p. 593-603.
[21]Ordas, S., et al., Parametric optimization of a model-based segmentation algorithm for cardiac MR image analysis: a grid-computing approach. Stud Health Technol Inform, 2005.112: p. 146-56.
[22] Angelie, E., et al., Optimizing the automatic segmentation of the left ventricle in magnetic resonance images. Med Phys, 2005.32(2): p. 369-75. 16. Lotjonen, J., et al., Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Med Image Anal, 2004. 8(3): p. 371-86.
[23]Lorenzo-Valdes, M., et al., Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal, 2004. 8(3): p. 255-65.
[24] Shankaranarayanan, A., et al., Segmented k-space and real-time cardiac cine MR imaging with radial trajectories. Radiology, 2001. 221(3): p. 827-36.
[25] Francois, C.J., et al., Left ventricular mass: manual and automatic segmentation of true FISP and FLASH cine MR images in dogs and pigs. Radiology, 2004. 230(2): p. 389-95.
[1] van den Bosch, A.E., B.J. Krenning, and J.R. Roelandt, Three-dimensional echocardiography. Minerva Cardioangiol, 2005.53(3): p. 177-84.
[2] Noble, J.A. and D. Boukerroui, Ultrasound image segmentation: a survey. IEEE Trans Med Imaging, 2006.25(8): p. 987-1010.
[3] Liu, H., et al., Multiresolution medical image segmentation based on wavelet transform. ConfProc IEEE Eng Med Biol Soc, 2005.4: p. 3418-21.
[4] T ao, Z., Beaty, J., Jaffe, etc. Gray level models for segmenting myocardium and blood in cardiac ultrasound images. In: Conference Proceedings of International Symposium on Biomedical Imaging 2002, pp. 265-269.
[5] Nikos Paragios, Marie-Pierre Jolly, Maxime Taron, etc. Active Shape Models and Segmentation of the Left Ventricle in Echocardiography. Scale-Space 2005: 131-142
[6] Gao, Y. Gao, S.Ding, etc. Semi-automatic segmentation of the endocardial boundaryin intracardiac echocardiographic images, EMBC 2004, Vol.3, pp. 1911-1913
[7] Angelini, E.D., Laine, A.F., Takuma, S., etc., LV volume quantification via spatiotemporal analysis of real-time 3-d echocardiography. IEEE Transactions on Medical Imaging (2001). 20 (6), 457-469.
[8] S. Guptal, R. C. Chauhanl and S. C. Sexana, Wavelet-based statistical approach for speckle reduction in medical ultrasound images, Medical and Biological Engineering and Computing, Springer Berlin / Heidelberg, March 2004, Vol.42, pp: 189-192
[9] Mallat, S.G.,A theory for multiresolution signal decomposition: the wavelet representation, IEEE PAMI Jul 1988 vol. 11 ,pp.:674-693
[10] Osher S, Sethian J A. Fronts propagating with curvature-dependent speed: algorithm based on Hamilton-Jacobi formulations[J]. Journal of Computational Physics, 1988,79: pp. 12-49
[11]Tony F. Chan, Luminita A. Vese: Active contours without edges. IEEE Transactions on Image Processing 2001 vol. 10(2), pp.: 266-277
[12]Manivannan, J., et al., Quantitative evaluation of left ventricle performance from two dimensional echo images. Echocardiography, 2006. 23(2): p. 87-92.
[13]Zagrodsky, V., et al., Registration-assisted segmentation of real-time 3-D echocardiographic data using deformable models. IEEE Trans Med Imaging, 2005. 24(9): p. 1089-99.
[14]Corsi, C, et al., A semi-automatic method for left ventricle volume estimate: an in vivo validation study. Comput Cardiol, 2001. 28: p. 109-12.
[15]Corsi, C, et al., Real-time 3D echocardiographic data analysis for left ventricular volume estimation. Comput Cardiol, 2000. 27: p. 107-10.
[16] Song, M., et al., Integrated surface model optimization for freehand three-dimensional echocardiography. IEEE Trans Med Imaging, 2002. 21(9): p. 1077-90.
[17] Ye, X., J.A. Noble, and D. Atkinson, 3-D freehand echocardiography for automatic left ventricle reconstruction and analysis based on multiple acoustic windows. IEEE Trans Med Imaging, 2002. 21(9): p. 1051-8.
[18]Malassiotis, S. and M.G. Strintzis, Tracking the left ventricle in echocardiographicimages by learning heart dynamics. IEEE Trans Med Imaging, 1999. 18(3): p. 282-90.
[19] Santos Conde, J.E., et al., [Algorithm for automatic endocardium identification in digital echocardiography image sequences]. Biomed Tech (Berl), 1998.43(7-8): p. 221-6.
[20]Mikic, I., S. Krucinski, and J.D. Thomas, Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates. IEEE Trans Med Imaging, 1998. 17(2): p. 274-84.
[21]Hackstein, J., O. Pichler, and A. Teuner, [Computer-assisted analysis of ultrasound sequences of the left ventricle for determining ejection fraction]. Biomed Tech (Berl), 1996.41(5): p. 118-22
[22]T. Chan and B. Sandberg and L. Vese,Active contours without edges. IEEE Trans. on Image Processing, 2001,10(2):266-277.
[23]Christophe C , Philippe R, Vlady B. Statistical region snake based segmentation adapted to different physical noise models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999 ,21 (11): 1145-1157.
[24] Pascal M, Philippe R, Francois G, et al. Influence of the noise model on level set active contour segmentation. IEEE Transactions on Pat tern Analysis and Machine Intelligence, 2004 ,26 (6) :799-803.
[25]Ning L, Weichuan Y, J ames S D. Combinative multi scale level set framework for echocardiographic image segmentation . Medical Image Analysis , 2004, 7(4) :529-537.
[1] N. Paragios, Shape-based segmentation and tracking in cardiac image analysis, IEEE Trans. Med. Imag. 2003 p.773-776.
[2] Setser, R.M., S.E. Fischer, and C.H. Lorenz, Quantification of left ventricular function with magnetic resonance images acquired in real time. J Magn Reson Imaging, 2000. 12(3): p. 430-8.
[3] van der Geest, R.J. and J.H. Reiber, Quantification in cardiac MRI. J Magn Reson Imaging, 1999. 10(5): p. 602-8.
[4] Tanki, N., et al., Quantification of left ventricular volumes from cardiac cine MRI using active contour model combined with gradient vector flow. Magn Reson Med Sci, 2005.4(4): p. 191-6.
[5] Petitjean, C., N. Rougon, and P. Cluzel, Assessment of myocardial function: a review of quantification methods and results using tagged MRI. J Cardiovasc Magn Reson, 2005.7(2): p. 501-16.
[6] Maim, S., et al., Quantification of resting myocardial blood flow velocity in normal humans using real-time contrast echocardiography. A feasibility study. Cardiovasc Ultrasound, 2005.3: p. 16.
[7] Inaba, Y., et al., Strain rate imaging for noninvasive functional quantification of the left atrium: comparative studies in controls and patients with atrial fibrillation. J Am Soc Echocardiogr, 2005.18(7): p. 729-36.
[8] Toyoda, T., et al., Assessment of regional myocardial strain by a novel automated tracking system from digital image files. J Am Soc Echocardiogr, 2004. 17(12): p. 1234-8.
[9] van der Geest, R.J., B.P. Lelieveldt, and J.H. Reiber, Quantification of global and regional ventricular function in cardiac magnetic resonance imaging. Top Magn Reson Imaging, 2000.11(6): p. 348-58.
[10]Schuijf, J.D., et al., Quantification of myocardial infarct size and transmurality by contrast-enhanced magnetic resonance imaging in men. Am J Cardiol, 2004.94(3): p. 284-8.
[1] Heye Zhang, Chun Lok Wong, Pengcheng Shi. An Inverse Recovery of Cardiac Electrical Propagation from Image Sequences. MIAR 2006:132-139
[2] Heye Zhang, Chun Lok Wong, Pengcheng Shi: Estimation of Cardiac Electrical Propagation from Medical Image Sequence. MICCAI (2) 2006:528-535
[3] Toili, T, et al., Artificially enlarged training set in image segmentation. Med Image Comput Comput Assist Interv Int Conf Med Image Comput Comput Assist Interv, 2006.9(Pt 1): p. 75-82.
[4] Yah, A.T., et al., Characterization ofmicrovascular dysfunction after acute myocardial infarction by cardiovascular magnetic resonance first-pass perfusion and late gadolinium enhancement imaging. J Cardiovasc Magn Reson, 2006.8(6): p. 831-7.
[5] Schuijf, J.D., et al., Quantification of myocardial infarct size and transmurality by contrast-enhanced magnetic resonance imaging in men. Am J Cardiol, 2004. 94(3): p. 284-8.
[6] Petitjean, C., N. Rougon, and P. Cluzel, Assessment of myocardial function: a review of quantification methods and results using tagged MRI. J Cardiovasc Magn Reson, 2005.7(2): p. 501-16.