生物医学模拟曲线的再生分析

为了更好利用已经积累的各种医学信息，本文讨论了一种利用Ｂ－样条平滑变换和图象边缘轮廓跟踪法识别坐标纸上曲线的方法，该方法在相当大的正规化参数范围内，可以在有 的去除不需要的细节噪声的同时，能很好地保证提取的曲线精度，为自理生物医学信号提供了新的有效手段，具有很好的应用前景。     

微血管网络图象特征提取的研究

微血管网络图象特征的提取是微血管网络图象自动分析的基础。在本研究中采用数字图象处理技术,实现了微血管网图象中微血管网轮廓结构、任意形状局部血管网直方图特征、任意血管截面光密度值分布曲线及频谱特征曲线、局部血管网纹理特征、局部血管网图象(最大256×256象素)二维空间谐特征等多种微血管网络图象特征的提取。     

基于形变模型的医学图像分割算法研究

结合形变模型和模糊C-均值（FCM）分割技术，提出了一种基于形变模型的医学图像解剖结构轮廓分割方法，在FCM分类的基础上，利用成员隶属函数定义一种模糊约束力并附加于形变模型的外部约束力中．在该种复合外部约束作用下，使形变模型能更好地收缩于解剖结构的轮廓。图像实验结果表明该方法的有效性和可行性。     

一种基于提取轮廓的医学图象数据压缩编码方法

本文提出了一种对医学图象进行轮廓编码和采用二维快速离散余弦变换（2D－FDCT）对其背景图象数据压缩编码相结合的方法。首先对2^t*2^t（t=9)，点的原始医学数字图象采用可变阈值的Sobel算子提出其边缘图象，原始图象与边缘图象之差为背景图象，利用5＊5点邻域窗函数对此背景图象2：1内抽成2t^-1*2^t-1点的数字图象，利用上述方法对此2t-1*2t-1点的数字图象进行分解……直到剩下64＊64点的背景图象，本文对几级轮廓图象采用等值线编码压缩，对64＊64点的背景图象通过采用快速多项式变换（FPT）计算2D－FDCT来进行数据压缩编码，在接收端，在接收端，对恢复的各级背景图象再叠加上相应的[边缘图象可减少重建图象产生的边缘模糊效应，我们在IBM－PC／XT微机组成的小型图象处理系统上进行了医学的编码压缩实验，图象数据压缩比可达20：1以上。     

生物组织切片的三维重构及灰度阴影显示

本文较详尽地阐述了在Cromemco CS-2H型微型计算机图象系统上对生物组织连续切片进行三维重构和灰度阴影显示的原理和方法。在图象数据获取过程中采用了轮廓填充的方法,使切片数据获得深度信息。在变换和重组过程中采取逐层覆盖的方法,实现了隐面消除,避免了大量复杂运算。在显示方法上将重构模型的数据结构进行了深度—灰度变换及灰度拉伸处理,以象点的亮暗程度表现模型各可见部位的深浅变化,实现了灰度阴影显示。利用动画技术使重建的三维模型在屏上转动,更增加了立体感和观察上的方便。在重构过程中还对一些形态学特征参量进行了测量,并给出了相应的计算公式。     

一种基于广义模糊特征点配准的眼底图象拼接算法

本文将广义模糊集合引入到眼底图象的拼接方面，运用广义模糊算子对图象模板进行处理，能精确地获得该模板的特征点。应用这些特征点进行眼底图象的配准，最终将各部分眼底图象拼接成一较完整的图象。实验证明，与一些常规配准算法相比，该算法具有速度快、配准精确等优点     

一种基于广义模糊特征点配准的眼义图象拼接算法

本文将广义模糊集合引入到眼底图象的拼接方面，运用广义模糊算子对图象模板进行处理，能精确地获得该模板的特征点。应用这些特征点进行眼底图象的配准，最终将各部分眼底图象拼接成一较完整的图象。实验证明，这一些常规配准算法相比，该算法具有速度快、配准精确等优点。     

一种基于人类感知的医学图象压缩方法

作者详细地介绍了一种基于人类感知的医学图象压缩算法，它利用人类视觉的运动特性，空间频率特性及时间频率特性对静止灰度图象进行有限失真压缩，该方法能大大压缩图象数据提高压缩比，对医学图象的压缩是一种比较有效的方法。     

医学图像三维重建系统的数据结构表达及表面模型的构建

医学图像三维重建在诊断、放射治疗规划及医学研究中均有着重要应用，本文论述了医学图像三维重建系统程序流程，设计了自动及手工轮廓勾画两种分割方法，并提出了建立了合理的系统数据结构。该数据结构能较好地描述系统数据的层次关系和表达重建的几何模型。对由自动分割和手工勾画出的组织，用MT算法构建其三维表面几何模型 。实现了网格简化的边收缩算法，并对由MT算法生成的表面模型进行了网格简化处理。模型网格经简化90％，依然能较好地保持模型的特征，大大加快了绘制速度。     

心血管双投影下多目标优化截面重建方法

近年来，心血管双平面投影下的三维重建技术作为一个少投影情形下的特例，已日益受到国际上图象重建和临床应用研究工作者的高度重视和深入研究。多目标优化图象重建法由于其在重建图象的质量、稳定性、重建速度以及收敛性等方面超乎寻常图象重建法的独到之处，已被成功地用于少投影图象重建的领域。本文旨在利用多目标优化法重建双平面投影下的心血管３Ｄ截面，得到了相当满意的结果。文中最末给出了重建两个不同类型的血管截面模型的例子。     

Pixel-Feature Hybrid Fusion for PET/CT Images

Color blending is a popular display method for functional and anatomic image fusion. The underlay image is typically displayed in grayscale, and the overlay image is displayed in pseudo colors. This pixel-level fusion provides too much information for reviewers to analyze quickly and effectively and clutters the display. To improve the fusion image reviewing speed and reduce the information clutter, a pixel-feature hybrid fusion method is proposed and tested for PET/CT images. Segments of the colormap are selectively masked to have a few discrete colors, and pixels displayed in the masked colors are made transparent. The colormap thus creates a false contouring effect on overlay images and allows the underlay to show through to give contours an anatomic context. The PET standardized uptake value (SUV) is used to control where colormap segments are masked. Examples show that SUV features can be extracted and blended with CT image instantaneously for viewing and diagnosis, and the non-feature part of the PET image is transparent. The proposed pixel-feature hybrid fusion highlights PET SUV features on CT images and reduces display clutters. It is easy to implement and can be used as complementarily to existing pixel-level fusion methods.     

Three Dimensional Active Contours for the Reconstruction of Abdominal Aortic Aneurysms

An aneurysm is a gradual and progressive ballooning of a blood vessel due to wall degeneration. Rupture of abdominal aortic aneurysm (AAA) constitutes a significant portion of deaths in the US. In this study, we describe a technique to reconstruct AAA geometry from CT images in an inexpensive and streamlined fashion. A 3D reconstruction technique was implemented with a GUI interface in MATLAB using the active contours technique. The lumen and the thrombus of the AAA were segmented individually in two separate protocols and were then joined together into a hybrid surface. This surface was then used to obtain the aortic wall. This method can deal with very poor contrast images where the aortic wall is indistinguishable from the surrounding features. Data obtained from the segmentation of image sets were smoothed in 3D using a Support Vector Machine technique. The segmentation method presented in this paper is inexpensive and has minimal user-dependency in reconstructing AAA geometry (lumen and wall) from patient image sets. The AAA model generated using this segmentation algorithm can be used to study a variety of biomechanical issues remaining in AAA biomechanics including stress estimation, endovascular stent-graft performance, and local drug delivery studies.     

Metal artifact reduction in CT using tissue-class modeling and adaptive prefiltering

High-density objects such as metal prostheses, surgical clips, or dental fillings generate streak-like artifacts in computed tomography images. We present a novel method for metal artifact reduction by in-painting missing information into the corrupted sinogram. The information is provided by a tissue-class model extracted from the distorted image. To this end the image is first adaptively filtered to reduce the noise content and to smooth out streak artifacts. Consecutively, the image is segmented into different material classes using a clustering algorithm. The corrupted and missing information in the original sinogram is completed using the forward projected information from the tissue-class model. The performance of the correction method is assessed on phantom images. Clinical images featuring a broad spectrum of metal artifacts are studied. Phantom and clinical studies show that metal artifacts, such as streaks, are significantly reduced and shadows in the image are eliminated. Furthermore, the novel approach improves detectability of organ contours. This can be of great relevance, for instance, in radiation therapy planning, where images affected by metal artifacts may lead to suboptimal treatment plans.     

Interactive 3D segmentation using connected orthogonal contours

This paper describes a new method for interactive segmentation that is based on cross-sectional design and 3D modelling. The method represents a 3D model by a set of connected contours that are planar and orthogonal. Planar contours overlayed on image data are easily manipulated and linked contours reduce the amount of user interaction.1 This method solves the contour-to-contour correspondence problem and can capture extrema of objects in a more flexible way than manual segmentation of a stack of 2D images. The resulting 3D model is guaranteed to be free of geometric and topological errors. We show that manual segmentation using connected orthogonal contours has great advantages over conventional manual segmentation. Furthermore, the method provides effective feedback and control for creating an initial model for, and control and steering of, (semi-)automatic segmentation methods.     

A Knowledge-Based Approach for Carpal Tunnel Segmentation from Magnetic Resonance Images

Carpal tunnel syndrome (CTS) has been reported as one of the most common peripheral neuropathies. Carpal tunnel segmentation from magnetic resonance (MR) images is important for the evaluation of CTS. To date, manual segmentation, which is time-consuming and operator dependent, remains the most common approach for the analysis of the carpal tunnel structure. Therefore, we propose a new knowledge-based method for automatic segmentation of the carpal tunnel from MR images. The proposed method first requires the segmentation of the carpal tunnel from the most proximally cross-sectional image. Three anatomical features of the carpal tunnel are detected by watershed and polygonal curve fitting algorithms to automatically initialize a deformable model as close to the carpal tunnel in the given image as possible. The model subsequently deforms toward the tunnel boundary based on image intensity information, shape bending degree, and the geometry constraints of the carpal tunnel. After the deformation process, the carpal tunnel in the most proximal image is segmented and subsequently applied to a contour propagation step to extract the tunnel contours sequentially from the remaining cross-sectional images. MR volumes from 15 subjects were included in the validation experiments. Compared with the ground truth of two experts, our method showed good agreement on tunnel segmentations by an average margin of error within 1 mm and dice similarity coefficient above 0.9.     

How does CT image noise affect 3D deformable image registration for image-guided radiotherapy planning?

PURPOSE: To measure the sensitivity of deformable image registration to image noise. Deformable image registration can be used to map organ contours and other treatment planning data from one CT to another. These CT studies can be acquired with either conventional fan-beam CT systems or more novel cone-beam CT techniques. However, cone-beam CT images can have higher noise levels than fan-beam CT, which might reduce registration accuracy. We have investigated the effect of image quality differences on the deformable registration of fan-beam CTs and CTs with simulated cone-beam noise. METHOD: Our study used three CT studies for each of five prostate patients. Each CT was contoured by three experienced radiation oncologists. For each patient, one CT was designated the source image and the other two were target images. A deformable image registration process was used to register each source CT to each target CT and then transfer the manually drawn treatment planning contours from the source CT to the target CTs. The accuracy of the automatically transferred contours (and thus of the deformable registration process) was assessed by comparing them to the manual contours on the target CTs, with the differences evaluated with respect to interobserver variability in the manual contours. Then each of the target CTs was modified to include increased noise characteristic of cone-beam CT and the tests were repeated. Changes in registration accuracy due to increased noise were detected by monitoring changes in the automatically transferred contours. RESULTS: We found that the additional noise caused no significant loss of registration accuracy at magnitudes that exceeded what would normally be found in an actual cone-beam CT. SUMMARY: We conclude that noise levels in cone-beam CTs that might reduce manual contouring accuracy do not reduce image registration and automatic contouring accuracy.     

Identifying same-cell contours in image stacks: a key step in making 3D reconstructions

Identification of contours belonging to the same cell is a crucial step in the analysis of confocal stacks and other image sets in which cell outlines are visible, and it is central to the making of 3D cell reconstructions. When the cells are close packed, the contour grouping problem is more complex than that found in medical imaging, for example, because there are multiple regions of interest, the regions are not separable from each other by an identifiable background and regions cannot be distinguished by intensity differences. Here, we present an algorithm that uses three primary metrics—overlap of contour areas in adjacent images, co-linearity of the centroids of these areas across three images in a stack, and cell taper—to assign cells to groups. Decreasing thresholds are used to successively assign contours whose membership is less obvious. In a final step, remaining contours are assigned to existing groups by setting all thresholds to zero and groups having strong hour-glass shapes are partitioned. When applied to synthetic data from isotropic model aggregates, a curved model epithelium in which the long axes of the cells lie at all possible angles to the transection plane, and a confocal image stack, algorithm assignments were between 97 and 100% accurate in sets having at least four contours per cell. The algorithm is not particularly sensitive to the thresholds used, and a single set of parameters was used for all of the tests. The algorithm, which could be extended to time-lapse data, solves a key problem in the translation of image data into cell information.     

基于BP神经网络的CT图像骨皮质分割

目的在CT图像中通过对骨皮质的分割与测量,测定骨量、骨骼的几何形状以及骨强度,并计算相应的组织形态计量学参数。方法通过DCMTK解读CT图像,提取相应的图像信息。利用OpenCV对图像进行预处理,在感兴趣的区域(ROI)设置的基础上,提取图像的纹理特征作为输入向量;以对训练样本手工分割的结果作为导师信号,对BP神经网络进行训练;用训练好的网络对CT图像序列中的骨皮质进行分割,并对分割后的结果进行后处理及显示。结果骨皮质CT图像的神经网络分割效率符合实际应用的需求,分割结果形状明显,与周围组织区分度高,满足临床诊断需求。结论纹理特征明显的情况下,可以达到较为满意的分割效果。分割结果轮廓平滑,分割精度高、成功率高、适应性强;而且图像分割过程人工介入少,可以用于整套CT图像骨皮质的批量分割。不足之处在于此方法神经网络训练时间相对较长。     

An Image-Based Comprehensive Approach for Automatic Segmentation of Left Ventricle from Cardiac Short Axis Cine MR Images

Segmentation of the left ventricle is important in the assessment of cardiac functional parameters. Manual segmentation of cardiac cine MR images for acquiring these parameters is time-consuming. Accuracy and automation are the two important criteria in improving cardiac image segmentation methods. In this paper, we present a comprehensive approach to segment the left ventricle from short axis cine cardiac MR images automatically. Our method incorporates a number of image processing and analysis techniques including thresholding, edge detection, mathematical morphology, and image filtering to build an efficient process flow. This process flow makes use of various features in cardiac MR images to achieve high accurate segmentation results. Our method was tested on 45 clinical short axis cine cardiac images and the results are compared with manual delineated ground truth (average perpendicular distance of contours near 2 mm and mean myocardium mass overlapping over 90%). This approach provides cardiac radiologists a practical method for an accurate segmentation of the left ventricle.     

Multiscale registration of medical images based on edge preserving scale space with application in image-guided radiation therapy

Mutual information (MI) is a well-accepted similarity measure for image registration in medical systems. However, MI-based registration faces the challenges of high computational complexity and a high likelihood of being trapped into local optima due to an absence of spatial information. In order to solve these problems, multi-scale frameworks can be used to accelerate registration and improve robustness. Traditional Gaussian pyramid representation is one such technique but it suffers from contour diffusion at coarse levels which may lead to unsatisfactory registration results. In this work, a new multi-scale registration framework called edge preserving multiscale registration (EPMR) was proposed based upon an edge preserving total variation L1 norm (TV-L1) scale space representation. TV-L1 scale space is constructed by selecting edges and contours of images according to their size rather than the intensity values of the image features. This ensures more meaningful spatial information with an EPMR framework for MI-based registration. Furthermore, we design an optimal estimation of the TV-L1 parameter in the EPMR framework by training and minimizing the transformation offset between the registered pairs for automated registration in medical systems. We validated our EPMR method on both simulated mono- and multi-modal medical datasets with ground truth and clinical studies from a combined positron emission tomography/computed tomography (PET/CT) scanner. We compared our registration framework with other traditional registration approaches. Our experimental results demonstrated that our method outperformed other methods in terms of the accuracy and robustness for medical images. EPMR can always achieve a small offset value, which is closer to the ground truth both for mono-modality and multi-modality, and the speed can be increased 5-8% for mono-modality and 10-14% for multi-modality registration under the same condition. Furthermore, clinical application by adaptive gross tumor volume re-contouring for clinical PET/CT image-guided radiation therapy throughout the course of radiotherapy is also studied, and the overlap between the automatically generated contours for the CT image and the contours delineated by the oncologist used for the planning system are on average 90%.