共查询到20条相似文献,搜索用时 156 毫秒
1.
为了从眼底图像中分割出具不同形态特征的视网膜血管,提出了基于改进相位一致性算法的眼底血管分割方法。采用二维离散Hilbert变换实现相位一致性算法,利用相位一致性算法在频域提取眼底图像特征并用于视网膜血管分割。采用STARE眼底图像数据库进行实验并以专家手工分割结果为标准,实验结果表明,提出的改进相位一致性算法可较好完成视网膜血管分割,能够有效避免图像亮度和对比度对分割结果的影响。 相似文献
2.
对超声主颈动脉(Common Carotid Artery,CCA)横向图像中血管的内外膜进行分割,分割结果可用于对斑块大小、厚度和形状的定性估计及定量测量。首先选用局部C-V(Local Chan-Vese,LCV)模型对外膜进行分割,而用C-V模型对内膜进行分割,并引入内外膜距离限制项来提高内膜分割准确度,同时使用稀疏场方法(Sparse Field Method,SFM)提高水平集算法的效率,最后通过全正交法(Full-Orthogonal Method,FOM)、射线法、相似系数分析法等多种评价方法对分割结果进行分析。实验结果表明,LCV模型可有效地分割颈动脉血管外膜,而C-V模型可有效地分割血管内膜,改进方法提升了程序运行速度并且提高了内外膜的分割精度。 相似文献
3.
眼底图像的视网膜血管分割是眼底图像处理的重要组成部分,视网膜血管对于医学研究和临床诊断有着重要的作用。传统图像分割算法都有一定的缺陷,而相位一致性算法由于不受对亮度和对比度的影响,且有着较好的分割效果,可以用于图像特征的提取和分割。为此提出了将相位一致性算法应用于眼底图像的血管提取中,采用真实的眼底图像数据库进行实践,证明了可较好地用于眼底图像视网膜血管分割。 相似文献
4.
针对现有冠脉血管分割方法对于小血管和低对比度血管分割效果差的问题,提出了一种基于融合的冠状动脉血管分割方法。首先分别采用形态学的头帽法和高斯滤波法对同一幅血管图像进行增强,得到两幅增强图像;然后采用基于局部熵的过渡区提取的分割方法提取血管,得到两幅含有冠脉血管的图像;最后将两幅图像通过区域连通性的分析进行融合,分割出最终的血管。实验结果表明,新算法在小血管的提取、连通性和有效性方面取得了更好的效果。另外,该方法对辅助医疗诊断具有一定价值。 相似文献
5.
6.
两种超声颈动脉血管斑块图像分割方法比较与改进 总被引:1,自引:1,他引:0
针对颈动脉超声图像,实现了两种颈动脉血管斑块的分割方法—活动形状模型(Active Shape Models,ASM)和活动表观模型(Active Appearance Models,AAM),对38组颈动脉超声图像进行了内外轮廓分割,并比较了两类算法对颈动脉内外轮廓分割的有效性。在综合分析实验结果的基础上,结合颈动脉超声图像的特点,通过引入比例不变性改进了ASM算法。统计结果表明,在运行时间上,ASM和改进ASM的运行时间相近,AAM大约为ASM和改进ASM的16倍。同时,采用FOM和RAY两种方法对分割效果进行评价,结果表明,改进ASM算法的分割效果较ASM有了很大的提高,是最适合颈动脉血管斑块超声图像分割的算法。 相似文献
7.
8.
9.
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。 相似文献
10.
医学图象的识别与分析能够为临床提供定量比的诊断依据,而图象分割是其中最关键的一步。为提高医学图象侵分割效果,提出了一种基于特征距离的阈值分割算法,并将其与颜色特征分类相结合,来对眼科裂隙灯生物显微镜图象上的角膜充血区进行分割,分割结果可用于角膜充血区的定量体分析,另外,该算法中的样本典型值是通过一种三维直方图分块算法来确定的,实验结果表明,该算法可以有效地分割出角膜充血,其分割效果优于欧氏距离阈值法,且分析数据的精度能够达到临床诊断的要求。 相似文献
11.
山脊线有主脉和支脉之分,主脉连贯突出且长度较长,控制了地形整体特征和态势,支脉则相对短小、分布于主脉两侧,反映了地形局部变化与细节。然而,现有方法提取的山脊线包含支脉多,提取结果偏差大、连续性差,无法支持实际应用。为此,结合多尺度分析与图像融合理论,提出了一种主脉的提取方法。新方法以不同参数的高斯核函数对数字高程(DEM)数据做多尺度分解,分别提取各尺度下山脊线,再以高斯尺度参数构造各尺度山脊线权重,采用加权平均法融合各尺度山脊线,获得更能体现宏观地形特征的主脉。实验结果表明,该方法简单易行,提取的主脉清晰、连续,与实际地形较为相符。 相似文献
12.
叶脉分割是叶片模式分析的一个重要步骤, 对大豆的品种识别、表型研究具有十分重要的意义. 由于大豆叶脉结构十分复杂, 叶脉所在叶片区域的低对比度, 只借助灰度信息分割叶脉一般无法取得理想的分割效果. 本文提出了一种结合多尺度灰度无约束击中或击不中变换 (UHMT) 算法和基于HSI颜色空间的色调信息处理方法的大豆叶脉分割方法. 该方法将RGB颜色空间中的灰度信息和HSI颜色空间中的色调信息, 分别用于大豆叶片图像的全局叶脉分割和局部一级、二级叶脉分割. 前者采用迭代阈值分割提取叶片区域, 通过膨胀腐蚀消除叶片外轮廓以及叶柄等干扰因素, 得到叶片区域图像, 然后, 运用多尺度灰度UHMT算法得到全局叶脉图像. 后者, 针对一级和二级叶脉分割效果差的问题, 使用色调信息扩大叶脉与其他像素点灰度值差异, 以实现局部一级、二级叶脉的分割. 将获得的全局叶脉和局部叶脉图像融合, 获得最终的大豆叶脉图像. 为验证算法的有效性, 本文使用了大豆品种叶片图像数据库SoyCultivar中的大豆叶片图像进行实验. 结果表明, 该方法比现有的叶脉分割方法好, 不仅能够完整地提取大豆叶脉, 而且能够很好地消除背景以及叶片外轮廓、叶柄等无关成分. 相似文献
13.
14.
15.
Saez M González-Vázquez S González-Penedo M Barceló MA Pena-Seijo M Coll de Tuero G Pose-Reino A 《Computer methods and programs in biomedicine》2012,108(1):367-376
There are some evidence of the association between the calibre of the retinal blood vessels and hypertension. Computer-assisted procedures have been proposed to measure the calibre of retinal blood vessels from high-resolution photopraphs. Most of them are in fact semi-automatic. Our objective in this paper is twofold, to develop a totally automated system to classify retinal vessels into arteries and veins and to compare the measurements of the arteriolar-to-venular diameter ratio (AVR) computed from the system with those computed from observers. Our classification method consists of four steps. First, we obtain the vascular tree structure using a segmentation algorithm. Then, we extract the profiles. After that, we select the best feature vectors to distinguish between veins and arteries. Finally, we use a clustering algorithm to classify each detected vessel as an artery or a vein. Our results show that compared with an observer-based method, our method achieves high sensitivity and specificity in the automated detection of retinal arteries and veins. In addition the system is robust enough independently of the radii finally chosen, which makes it more trustworthy in its clinical application. We conclude that the system represents an automatic method of detecting arteries and veins to measure the calibre of retinal microcirculation across digital pictures of the eye fundus. 相似文献
16.
P Cugini L Di Palma P Battisti A Coppola F Cipriano G Leone 《M.D. computing : computers in medical practice》1991,8(1):26-31
Clinical research has defined the criteria for identifying "curable" renovascular hypertension. The prediction is based on the measurement of plasma renin activity in peripheral veins, renal veins, and the aorta. Renin profiles can be examined with the method of Laragh and coworkers (the so-called incremental method), in which values for plasma renin activity are incorporated into formulas to compute indexed parameters. A score is attributed to each index and the prediction is based on the final score. Because the identification of curable renovascular hypertension is made according to numerical rules, the method is easily transformed into a computer-assisted process. The program is written in BASIC, and it is short enough to run on a personal computer. 相似文献
17.
In this study, we propose an effective method of easy and intuitive modeling of various types of multiple leaves from plants, including flowering plants and trees, and of naturally visualizing them. This method consists of two processes. The first is the procedural modeling of leaf venation patterns. The proposed method enables modeling of the growth of leaf veins based on the information of auxin detected from a binary image of a leaf blade. Therefore, a contour-based method is designed to automatically obtain information on the target auxin, required for the growth, according to blade shapes. In addition, the growth of leaf veins is procedurally modeled by dividing the veins into main, lateral, and tertiary veins. To this end, we propose a two-level growth model. The second method we introduce is a color model based on convolution sums of divisor functions to naturally simulate the color patterns of leaf surfaces. This approach automatically defines various color patterns by creating color tables for consistent changes in the convolution sums. In addition, it synthesizes three layers consisting of noise and vein glow maps. Furthermore, we perform experiments to verify whether the proposed method is effective for generating various realistic leaves. 相似文献
18.
19.
Characteristics of tongue pose the most important information for Traditional Chinese Medicine diagnosis. So far, extensive studies have been made on extracting tongue surface features, but rarely refer to sublingual vein that is also diagnostically important. This paper focuses on establishing a feature quantification framework for the inspection of sublingual veins, composed of two parts: the segmentation of sublingual veins and the feature quantification of them. Pixel-based sublingual vein segmentation algorithm and adaptive sublingual vein segmentation algorithm for color sublingual images with visible contrast and low contrast are proposed respectively. The experiments prove that the proposed algorithms perform well on the segmentation of sublingual veins from color sublingual images with both visible contrast and low contrast. A chromatic system in conformity with diagnostic standard of tongue diagnosis is established to characterize the chromatic feature of sublingual veins. Experimental results reveal that the breadth and chromatic features quantified by the proposed framework are properly consistent with the diagnostic standard summarized by tongue diagnosis. 相似文献
20.
提出了一种改进的叶脉建模方法。该方法将L-system加入到Runions的叶脉建模方法当中,较好地解决了主侧脉生长比较慢的问题。作为整体算法中的一步,采用一种新的dart-throwing算法得到均匀分布的营养点集,有效地提高了整个算法的绘制速度。实验结果表明,改进后的方法能够以更快的速度生成更加逼真的叶脉模型。 相似文献