形状约束下活动轮廓模型冠脉血管图像多尺度分割

目的 由于计算机断层血管造影(CTA)图像的复杂性,临床诊断冠脉疾病往往需要经验丰富的医师对冠状动脉进行手动分割,快速、准确自动分割出冠状动脉对提高冠脉疾病诊断效率具有重要意义。针对双源CT图像特点以及传统单一基于区域或边界的活动轮廓模型的不足,研究了心脏冠脉3维分割算法,提出一种基于血管形状约束的活动轮廓模型分割方法。方法 首先,利用改进的FCM(fuzzy C-means)对心脏CT图像感兴趣区域初分割,其结果用于初始化C-V模型水平集演化曲线及控制参数,提取感兴趣区域轮廓。接着,由3维心脏图像数据获取多尺度梯度矢量信息构造边界型能量泛函,然后利用基于Hessian矩阵的多尺度血管函数对心脏感兴趣区域3维体数据增强滤波,获取血管先验形状信息用于约束能量泛函。最后融合边界、区域能量泛函并利用变分原理及水平集方法得到适合冠脉血管分割的水平集演化方程。结果 由于血管图像的灰度不均匀,血管末端区域更为细小,所以上述算法的实施是面向被划分多个子区域的血管,在缩小的范围内进行轮廓的演化。相比于传统的血管分割方法,该方法充分融合血管图像的先验信息及梯度场信息,能够从灰度及造影剂分布不均匀的冠脉血管图像中准确分割出冠状动脉,对于细小的血管结构亦能获得较好的分割效果。实验结果表明,该方法只需在给定初始轮廓前提下,有效提取3维冠脉血管。结论 对多组心脏CT图像进行分割,本文基于血管先验形状约束的活动轮廓模型可以准确分割出冠脉结构完整轮廓,并且人工交互简单。该方法在双源CT冠脉图像自动分割方面具有较好的正确率与优越性。     

一种低对比度CT图像的血管分割方法

CT图像血管分割技术在疾病的诊断,手术规划等许多实际应用中发挥着重要的作用.由于个体性差异和成像设备的限制,造影后的血管通常存在对比度低和噪声高的缺陷.针对该数据特点提出了一套分割方法,首先采用直方图对图像进行预处理,以增强血管和周围区域的对比度;其次,改进Hessian矩阵血管增强的判别方法,使其对细小和模糊的管状结构更加敏感;最后,采用区域生长算法对增强后的数据进行血管提取,获得血管分支较丰富的分割数据.实验证明本文的分割方法可以准确地实现血管分割,有效地避免了误分割,具有较好的鲁棒性.     

多相期增强CT中肝内血管的自动分割

目的 在肝脏手术规划系统中,肝内精确的血管模型是实施肝脏分段和手术模拟的重要基础。为此提出一种基于多相期增强CT影像的肝内血管自动分割方法。方法 首先,采用各向异性滤波的方式减少图像上的噪声干扰。然后将图像灰度信息和汉森矩阵的特征值相结合,设计了一种新的滤波器,增强图像中的血管结构,以解决传统方法中血管连接处断裂的问题。最后,应用迭代式的自适应区域增长算法,进一步分割出增强图像中的血管。结果 使用5组临床上的真实数据测试算法的有效性,实验结果显示肝内血管由粗到细被完整分割出来。结论 本文肝脏CT血管分割方法,分别在不同尺度的增强图像对其进行处理,使得肝内血管从粗壮的主枝到细小的末端都能被很好地分割出来,能够获得正确的血管拓扑结构。     

基于多尺度2D Gabor小波的视网膜血管自动分割

眼底视网膜血管分割对临床视网膜疾病诊断具有重要意义. 由于视网膜血管结构微小, 血管轮廓边界模糊, 加上图像采集时噪声的影响, 视网膜血管分割非常困难. 本文提出一种视网膜血管自动分割新方法. 首先, 应用对比度受限的自适应直方图均衡法增强视网膜图像;然后, 采用不同尺度的2D Gabor小波对视网膜图像进行变换, 并分别应用形态学重构 (Morphological reconstruction, MR)和区域生长法 (Region growing, RG)对变换后的图像进行分割; 最后, 对以上两种方法分割的视网膜血管和背景像素点重新标记识别, 得到视网膜血管最终分割结果. 通过对DRIVE和STARE数据库视网膜图像的分割实验, 证明了该算法的有效性.     

Detection of Plaque in Coronary Artery in CMRI Images and 3D Visualization of Blood Flow

Detection of blocks in coronary arteries is becoming crucial interest for early detection of heart attacks. In this paper we propose a framework for detection of plaque in coronary arteries from cardio vascular magnetic resonance imaging(CMRI). It is a quantitative tool for the assessment of cardiovascular diseases. First, select a region of interest and segment the region of coronary artery using enhanced region based active contour (ERAC). Secondly the centreline extraction and lumen segmentation are integrated to extract the artery centreline using geometric moments and the vessel direction using Hessian matrix and segment the vessel lumen in each slice using ERAC. A boundary searching method is adapted to fine tune the segmented surface in each slice of CMRI image. Third, the soft plaques in the coronary artery are extracted by thresholding the segmented region. Finally a 3D visualization of blood flow in coronary artery is presented and the volume of blood flow is calculated. In the experiments we have employed 22 datasets of CMRI images. The experimental results show an average accuracy of 97.6% and with a mean and standard deviation of false discovery rate of 2.48 ± 0.002.

     

虚拟肝脏的规则和非规则手术切除技术

为了提高肝癌手术治疗计划的可靠性,在利用腹部CT图像数据进行肝脏三维重建的基础上,实现了任意角度对虚拟肝脏进行平面切割和切割面结构的显示;通过构造可以调节大小、位置的球体模型,实现了球体切除;通过在肝脏三维模型表面上勾画不规则封闭区域,实现了任意曲面肝脏切除;并依据肝内血管结构进行肝段划分,实现了解剖性肝段切除.临床实验结果表明,文中所述的技术能够满足虚拟手术的需求,有利于医生制定安全可靠的术前计划,提高手术成功率.     

基于Hessian矩阵和区域生长的肝血管树的分割算法研究

由于血管成像设备的限制和血管本身形态结构的复杂性,使得血管分割成为一个难题。针对CT肝脏血管图像的特征,设计一种将Hessian矩阵多尺度滤波、形态学和三维区域生长相结合的方法,实现血管分割。首先,使用灰度变换突出目标区域,利用基于Hessian矩阵的多尺度滤波方法对血管进行增强;其次,对增强后的血管图像进行闭运算,并进行三维区域生长;最后,利用膨胀运算将血管的弱连接进行连接。实验表明该方法具有一定的可行性和有效性,能够很好地实现血管的分割,所产生的血管连续光滑,很适合作为三维重建的数据集。     

基于两阶段区域生长的肝内血管分割算法

提出一种基于两阶段区域生长法的肝内血管分割算法。在第一阶段,使用三维区域生长法从CT图像序列中提取出肝脏,区域生长法的生长准则由均值和方差双阈值来决定。分别通过形态学运算和中值滤波对分割出的肝脏序列进行降噪处理。在第二阶段,再次利用区域生长法从已经得到的三维肝脏图像序列中分割出血管,区域生长法的生长准则仅由均值作为单阈值决定。对两阶段区域生长法的实验结果进行三维重建,与传统区域生长法的三维重建结果相比较,能够体现出该算法的准确性。     

The use of a projection method to simplify portal and hepatic vein segmentation in liver anatomy

In living donor liver transplantation, the volume of the potential graft must be measured to ensure sufficient liver function after surgery. Couinaud divided the liver into 8 functionally independent segments. However, this method is not simple to perform in 3D space directly. Thus, we propose a rapid method to segment the liver based on the hepatic vessel tree. The most important step of this method is vascular projection. By carefully selecting a projection plane, a 3D point can be fixed in the projection plane. This greatly helps in rapid classification. This method was validated by applying it to a 3D liver depicted on CT images, and the result was in good agreement with Couinaud's classification.     

Accelerated liver tumor segmentation in four-phase computed tomography images

Segmentation and volume measurement of liver tumor are important tasks for surgical planning and cancer follow-up. In this work, a segmentation method from four-phase computed tomography images is proposed. It is based on the combination of the Expectation-Maximization algorithm and the Hidden Markov Random Fields. The latter considers the spatial information given by voxel neighbors of two contrast phases. The segmentation algorithm is applied on a volume of interest that decreases the number of processed voxels. To accelerate the classification steps within the segmentation process, a Bootstrap resampling scheme is also adopted. It consists in selecting randomly an optimal representative set of voxels. The experimental results carried out on three clinical datasets show the performance of our liver tumor segmentation method. It has been notably observed that the computing time of the classification algorithm is reduced without any significant impact on the segmentation accuracy.     

基于层级血管树的肝脏分段方法

针对经典肝脏功能性分段方法对门静脉血管数据的敏感性,结合Couinaud肝脏分段理论和门静脉分布特征,提出了基于层级血管树的肝脏分段方法：首先对腹腔CT数据进行肝脏分割、血管提取和骨架化;接着统计分析血管树分支半径,确定二级子树集合,按照供血区域对二级子树进行聚类完成对二级子树的归类划分;进而采用最短距离归类算法划分肝脏,得到各个肝段;最后运用三维可视化方法展现肝脏内部的解剖结构,并进行肝段诠析,提取临床感兴趣信息。实验结果表明该方法对分支较多、结构较复杂的血管树可以取得较好的分级效果,考虑了大部分二级分支的供血作用,分割得到的肝段分布和属性信息也符合Couinaud肝段分割理论。     

Connectivity-based local adaptive thresholding for carotid artery segmentation using MRA images

The computer algorithms for the delineation of anatomical structures and other regions of interest on the medical imagery are important component in assisting and automating specific radiological tasks. In addition, the segmentation of region is an important first step for variety image related application and visualization tasks. In this paper, we propose a fast and automated connectivity-based local adaptive thresholding (CLAT) algorithm to segment the carotid artery in sequence medical imagery. This algorithm provides the new feature that is the circumscribed quadrangle on the segmented carotid artery for region-of-interest (ROI) determination. By using the preserved connectivity between consecutive slice images, the size of the ROI is adjusted like a moving window according to the segmentation result of previous slice image. The histogram is prepared for each ROI and then smoothed by local averaging for the threshold selection. The threshold value for carotid artery segmentation is locally selected on each slice image and is adaptively determined through the sequence image. In terms of automated features and computing time, this algorithm is more effective than region growing and deformable model approaches. This algorithm is also applicable to segment the cylinder shape structures and tree-like blood vessels such as renal artery and coronary artery in the medical imagery. Experiments have been conducted on synthesized images, phantom and clinical data sets with various Gaussian noise.     

定向区域生长算法及其在血管分割中的应用

针对医学图像中微细管道结构灰度连续性差,采用常规区域生长法进行分割容易丢失末梢的问题,提出一种定向区域生长算法,可以在生长过程中跨越管道结构中的低灰度 区域。算法向图像中已生长区域外灰度最高的方向进行生长,每次将一个体素加入已生长区域,将图像转变为一颗以种子点为根结点的树,再从叶子结点进行回溯以确定感兴趣区 域。对实现算法的数据结构进行了讨论。算法可以应用于任意维的图像。对2维和3维图像的测试结果表明,相对于常规的区域生长法,算法可以分割出更多的血管分支。算法对3维 图像的运行时间为秒钟量级,可以满足临床应用的要求。     

联合注意力和Transformer的视网膜血管分割网络

视网膜血管分割在许多眼科疾病诊断和治疗方面至关重要。对复杂的视网膜结构及低对比度眼底图像来说,准确地分割视网膜图像的血管特征仍具有挑战性。联合注意力和Transformer的视网膜血管分割网络JAT-Net,通过对编码阶段特征的通道信息和位置信息联合关注增强编码局部细节特征,利用Transformer增强对长距离上下文信息和空间依赖关系建模的能力。在DRIVE和CHASE数据集上进行视网膜血管分割实验,其准确率分别为0.970 6和0.977 4,F1分数分别为0.843 3和0.815 4,在视网膜血管分割方面表现不错。     

A teacher-student framework for liver and tumor segmentation under mixed supervision from abdominal CT scans

Neural Computing and Applications - Liver and tumor segmentation from abdominal CT scans and an important step towards computer-assisted diagnosis or treatment planning for various hepatic...     

Retinal vessels segmentation based on level set and region growing

Retinal vessels play an important role in the diagnostic procedure of retinopathy. Accurate segmentation of retinal vessels is crucial for pathological analysis. In this paper, we propose a new retinal vessel segmentation method based on level set and region growing. Firstly, a retinal vessel image is preprocessed by the contrast-limited adaptive histogram equalization and a 2D Gabor wavelet to enhance the vessels. Then, an anisotropic diffusion filter is used to smooth the image and preserve vessel boundaries. Finally, the region growing method and a region-based active contour model with level set implementation are applied to extract retinal vessels, and their results are combined to achieve the final segmentation. Comparisons are conducted on the publicly available DRIVE and STARE databases using three different measurements. Experimental results show that the proposed method reaches an average accuracy of 94.77% on the DRIVE database and 95.09% on the STARE database.     

鲁棒的超声多普勒肾动脉血流信号提取方法

声多普勒肾动脉血流速度信号是进一步提取血流速度信号特征的前提。而超声多普勒肾动脉血流速度信号特征是肾动脉狭窄早期诊断的重要手段。因强烈的斑噪影响和其它信息干扰,从超声图像中准确提取肾动脉血流速度信号是比较困难的。提出了局部自适应的置信连接分割方法,该方法用于分离信号区域和背景,在灰度分布不均匀和强噪声条件下仍能实现有效分割;然后使用连通域标号的方法填补小空隙,以消除干扰信息的影响,通过局部统计特性修正提取的信号并使用Mean Shift方法为信号降噪,最终实现了鲁棒的肾动脉血流速度信号的提取。实验结果显示,该方法能准确提取肾动脉血流速度信号,鲁棒性强。     

基于条件能量对抗网络的肝脏和肝肿瘤分割

从图像中分割出肝脏和肝肿瘤是肝部疾病诊断重要手段之一,现有基于卷积神经网络（Convolutional Neural Network,CNN）方法通过为输入图像中每个像素分配类别标签来实现肝脏和肝肿瘤分割。CNN在对每个像素分类过程中没有使用邻域内其他像素类别信息,容易出现小目标漏检和目标边界分割模糊问题。针对这些问题,提出了条件能量对抗网络用于肝脏和肝肿瘤分割。该方法基于能量生成对抗网络（Energy-Based Generative Adversarial Network,EBGAN）和条件生成对抗网络（Conditional Generative Adversarial Network,CGAN）,使用一个基于CNN的分割网络作为生成器与一个自编码器作为判别器,通过将判别器作为一种损失函数来度量并提升分割结果与真实标注之间的相似度。在对抗训练过程中,判别器将生成器输出的分割结果作为输入并将原始图像作为条件约束,通过学习像素类别之间的高阶一致性提高分割精度,使用能量函数作为判别器避免了对抗网络训练中容易出现的梯度消失或梯度爆炸,更易于训练。在MICCAI 2017肝肿瘤分割（LiTS）挑战赛的数据集和3DIRCADb数据集上对提出的方法进行验证,实验结果表明,该方法不仅实现了肝脏与肝肿瘤的自动分割,还利用像素类别之间的高阶一致性提升了肿瘤和肝脏边界的分割精度,减少了小体积肿瘤的漏检。     

基于条件生成对抗网络的书法字笔画分割

毛笔书法作为中华传统艺术的精华, 需要在新的时代背景下继续传承和发扬. 书法字是以笔画为基本单元组成的复杂图形, 如果要分析书法结构, 笔画分割是首要的步骤. 传统的笔画分割方法主要利用细化法从汉字骨架上提取特征点, 分析交叉区域的子笔画拓扑结构关系来分割笔画. 本文分析了传统笔画分割基于底层特征拆分笔画的局限性, 利用条件生成对抗网络(Conditional generative adversarial network, CGAN)的对抗学习机制直接分割笔画, 使提取笔画从先细化再分割改进为直接分割. 该方法能有效提取出精确的笔画, 得到的高层语义特征和保留完整信息的单个笔画利于后续对书法轮廓和结构的评价.