一种用于前列腺区域分割的改进水平集算法

前列腺区域的精确分割是提高计算机辅助前列腺癌诊断准确率的重要前提.本文提出了一种新的精确的前列腺区域分割模型,分为4个步骤：首先,读取T₂加权磁共振（MR）图像;其次,利用半径为5个像素的8邻域模板（8x5）的局部二值模式（LBP）特征模板计算前列腺磁共振图像的LBP特征图;然后,利用改进的距离正则化水平集（DRLSE）模型对特征图进行分割,提取前列腺粗轮廓;最后将原始水平集能量函数进行优化,构造一个新的能量函数,提取局部灰度信息和梯度信息,并在此新的能量函数的基础上,将粗轮廓迭代演化为最终的细轮廓.本文将该模型在203组来自于国际光学与光子学学会-美国医学物理学家协会-国家癌症研究所（SPIE-AAPM-NCI）前列腺MR分类挑战数据库的T2W磁共振图像上进行了测试,并与医生手工分割结果进行了比较,结果表明本文提出模型得到的分割结果的Dice系数为0.94±0.01,相对体积差（RVD）为-1.21%±2.44%,95% Hausdorff距离（HD）为6.15±0.66 mm;与文献中现有的分割模型相比,使用本文提出的模型得到的前列腺区域分割结果更接近于手工分割的结果.     

基于二维集合经验模式分解的距离正则化水平集磁共振图像分割

针对现有磁共振(MR)图像分割算法大多直接在原图像上进行处理,分割效果受噪声影响较大的问题,本文引入二维集合经验模式分解(BEEMD)算法,提高距离正则化水平集(DRLSE)方法对MR图像的分割精度.算法中首先使用BEEMD将待分割MR图像分解为多个二维固有模式函数(BIMF),通过对各BIMF赋予不同加权系数重构待分割图像,从而增强分割目标;然后在DRLSE的边界指示函数中添加部分BIMF分量,恢复因高斯平滑被模糊的目标轮廓,并使用DRLSE方法对重构图像进行分割.通过对仿真图像和临床MR图像分割验证,表明本文算法具有较高的分割精度和鲁棒性,能有效实现对临床MR图像的分割.     

基于混合能量模型水平集的合成孔径声纳图像分割方法

本文讨论了合成孔径声纳图像分割问题。首先介绍了Chan-Vese模型水平集方法,针对该模型存在的边界定位和重复初始化等问题,提出了一种改进的水平集方法。该方法的能量模型由区域信息项、边界信息项和距离约束函数构成的内部能量项三部分混合形成,既兼顾了全局优化特性和局部定位精度,又避免了水平集函数重复初始化,提高了运算效率。实验结果表明,该模型对于噪声干扰严重、边缘模糊的合成孔径声纳图像分割效果良好。     

结合小波融合和深度学习的脑胶质瘤自动分割

针对水肿区域边界模糊和瘤内结构复杂多变导致的脑胶质瘤分割不精确问题,本文提出了一种基于小波融合和3D-UNet网络的脑胶质瘤磁共振图像自动分割算法.首先,对脑胶质瘤磁共振图像的T1、T1ce、T2、Flair四种模态进行小波融合以及偏置场校正;然后,提取待分类的图像块;再利用提取的图像块训练3D-UNet网络以对图像块中的像素进行分类;最后加载损失率较小的网络模型进行分割,并采用基于连通区域的轮廓提取方法,以降低假阳性率.对57组Brats2018（Brain Tumor Segmentation 2018）磁共振图像测试集进行分割的结果显示,肿瘤的整体、核心和水肿部分的平均分割准确率（DSC）分别达到90.64%、80.74%和86.37%,这表明该算法分割脑胶质瘤准确率较高,与金标准相近.相比多模态图像融合前,该算法在减少输入网络数据量和图像冗余信息的同时,还一定程度上解决了胶质瘤边界模糊、分割不精确的问题,提高了分割的准确度和鲁棒性.     

结合MRF能量和DCE-MRI时域特征的乳腺癌灶分割算法

针对动态增强磁共振影像中乳腺癌灶对比度低、边界模糊且亮度不均匀等特点,提出了一种结合马尔科夫随机场能量和动态增强磁共振影像时域特征的混合活动轮廓模型。首先,基于模糊C均方聚类算法以图像的时域变化特征和亮度构建特征向量,构建模糊速度函数作为活动轮廓模型的边缘探测函数。其次,计算图像的隐马尔科夫场能量,以增强乳腺癌病灶与其他组织的差异。最后,以图中每个像素及其邻近像素的马尔科夫场能量为特征,利用k最近邻算法构建活动轮廓模型的区域项。轮廓曲线在病灶边界上时,区域项及边缘项最小,活动轮廓曲线停止演变,完成对乳腺癌灶的分割。实验结果表明,马尔科夫随机场能量和时域特征均能增强癌灶与其他组织的对比度,使所提方法的分割结果较其他活动轮廓模型更接近医生手工分割结果,对实现精确分割乳腺癌灶有重要意义。     

基于水平集的牙齿牙槽骨图像分割

口腔锥形束计算机断层扫描（Cone Beam Computed Tomography,CBCT）图像中牙齿及牙槽骨的分割对骨性结构的三维重建提供了基础,是实现牙齿牙槽骨三维可视化的必要步骤.本文根据牙齿及牙槽骨特点,将一种改进的势阱函数与水平集模型结合,克服以往势阱函数在部分区域出现“停止演化”或“过快演化”的缺陷,并将其应用在对牙齿牙槽骨的分割当中.采用多次小方差高斯滤波叠加的方式对图像进行序贯滤波预处理,解决单一方差高斯滤波难以有效滤除CBCT图像中噪声的问题,为准确分割提供了条件;基于序列图像相邻两张图片中同一牙齿的轮廓变化不大这一特点,以当前层的分割结果作为下一层曲线演化的初始轮廓,使得用更少的迭代次数得到相同结果,从而提高分割速度.另外,本文还将该算法应用于口腔磁共振图像中,并成功对单颗牙齿进行了分割.     

基于能量最小化的肾脏计算断层扫描图像分割方法

随着成像技术的不断发展, 医学图像处理在计算机辅助诊断和病变管理中的重要作用日渐突出, 而计算断层扫描序列图像的肾脏组织分割是其中的关键步骤. 本文结合肾脏序列图像的连续性特征, 提出了一种基于活动轮廓和图割方法的能量最小化分割模型来自动分割肾脏组织. 根据相邻切片图像的形状差异与层间距之间的关系, 计算出序列图像中适合图割优化能量函数的最优范围. 能量函数采用测地活动轮廓模型和Chan-Vese模型的综合形式, 兼顾了目标的边界和区域信息. 随后, 利用图割方法优化离散化的能量函数, 驱使活动轮廓逐渐向目标边界靠近, 直至收敛为止. 对30组腹腔序列图像进行了算法测试, 实验表明基于能量最小化的分割方法能够有效地提取出序列图像中的肾脏组织, 其分割结果的平均Dice系数达到了93.7%. 关键词： 计算层析 肾脏分割 能量最小化 连续性     

基于小波变换的多尺度水平集算法研究

针对传统水平集算法在处理低对比度图像时,出现的在局部梯度极大值区域及虚假边缘处停止演化等问题,提出了一种基于小波变换的多尺度水平集算法.采用高斯函数的导函数作为小波函数,使用独立强度传播模型来估计小波函数每一点尺度因子的值,再将沿x,y两个方向小波变换模的递减函数作为水平集速度停止项,对待处理图像进行水平集演化运算.实验结果表明,该方法优于传统水平集变换法.     

基于非凸正则化项的合成孔径雷达图像分割新算法

合成孔径雷达图像中乘性噪音的存在使合成孔径雷达图像分割变得非常困难.针对这一难题,本文以提高分割准确度,保护图像的几何结构边缘和提高算法的鲁棒性为目的,提出了一种适用于处理合成孔径雷达图像分割的新模型.新模型结合合成孔径雷达图像的区域和边缘信息,首先通过引入非凸的正则化项,定义了能量泛函;然后极小化能量泛函,建立了水平集函数演化的偏微分方程;最后对水平集演化方程的数值求解,实现了对合成孔径雷达图像感兴趣区域的分割.分别采用仿真图像和实测合成孔径雷达图像对新模型进行验证,结果表明,新模型对合成孔径雷达图像具有很强的边缘定位能力,能使目标区域分割更完整.     

基于非凸正则化项的合成孔径雷达图像分割新算法

合成孔径雷达图像中乘性噪音的存在使合成孔径雷达图像分割变得非常困难.针对这一难题,本文以提高分割准确度,保护图像的几何结构边缘和提高算法的鲁棒性为目的,提出了一种适用于处理合成孔径雷达图像分割的新模型.新模型结合合成孔径雷达图像的区域和边缘信息,首先通过引入非凸的正则化项,定义了能量泛函;然后极小化能量泛函,建立了水平集函数演化的偏微分方程;最后对水平集演化方程的数值求解,实现了对合成孔径雷达图像感兴趣区域的分割.分别采用仿真图像和实测合成孔径雷达图像对新模型进行验证,结果表明,新模型对合成孔径雷达图像具有很强的边缘定位能力,能使目标区域分割更完整.     

Adaptive segmentation of magnetic resonance images with intensity inhomogeneity using level set method

It is a big challenge to segment magnetic resonance (MR) images with intensity inhomogeneity. The widely used segmentation algorithms are region based, which mostly rely on the intensity homogeneity, and could bring inaccurate results. In this paper, we propose a novel region-based active contour model in a variational level set formulation. Based on the fact that intensities in a relatively small local region are separable, a local intensity clustering criterion function is defined. Then, the local function is integrated around the neighborhood center to formulate a global intensity criterion function, which defines the energy term to drive the evolution of the active contour locally. Simultaneously, an intensity fitting term that drives the motion of the active contour globally is added to the energy. In order to segment the image fast and accurately, we utilize a coefficient to make the segmentation adaptive. Finally, the energy is incorporated into a level set formulation with a level set regularization term, and the energy minimization is conducted by a level set evolution process. Experiments on synthetic and real MR images show the effectiveness of our method.     

Magnetic Resonance Imaging Segmentation via Weighted Level Set Model Based on Local Kernel Metric and Spatial Constraint

Magnetic resonance imaging (MRI) segmentation is a fundamental and significant task since it can guide subsequent clinic diagnosis and treatment. However, images are often corrupted by defects such as low-contrast, noise, intensity inhomogeneity, and so on. Therefore, a weighted level set model (WLSM) is proposed in this study to segment inhomogeneous intensity MRI destroyed by noise and weak boundaries. First, in order to segment the intertwined regions of brain tissue accurately, a weighted neighborhood information measure scheme based on local multi information and kernel function is designed. Then, the membership function of fuzzy c-means clustering is used as the spatial constraint of level set model to overcome the sensitivity of level set to initialization, and the evolution of level set function can be adaptively changed according to different tissue information. Finally, the distance regularization term in level set function is replaced by a double potential function to ensure the stability of the energy function in the evolution process. Both real and synthetic MRI images can show the effectiveness and performance of WLSM. In addition, compared with several state-of-the-art models, segmentation accuracy and Jaccard similarity coefficient obtained by WLSM are increased by 0.0586, 0.0362 and 0.1087, 0.0703, respectively.     

An adaptive multi-feature segmentation model for infrared image

Active contour models (ACM) have been extensively applied to image segmentation, conventional region-based active contour models only utilize global or local single feature information to minimize the energy functional to drive the contour evolution. Considering the limitations of original ACMs, an adaptive multi-feature segmentation model is proposed to handle infrared images with blurred boundaries and low contrast. In the proposed model, several essential local statistic features are introduced to construct a multi-feature signed pressure function (MFSPF). In addition, we draw upon the adaptive weight coefficient to modify the level set formulation, which is formed by integrating MFSPF with local statistic features and signed pressure function with global information. Experimental results demonstrate that the proposed method can make up for the inadequacy of the original method and get desirable results in segmenting infrared images.     

A joint shape evolution approach to medical image segmentation using expectation-maximization algorithm

This study proposes an expectation–maximization (EM)-based curve evolution algorithm for segmentation of magnetic resonance brain images. In the proposed algorithm, the evolution curve is constrained not only by a shape-based statistical model but also by a hidden variable model from image observation. The hidden variable model herein is defined by the local voxel labeling, which is unknown and estimated by the expected likelihood function derived from the image data and prior anatomical knowledge. In the M-step, the shapes of the structures are estimated jointly by encoding the hidden variable model and the statistical prior model obtained from the training stage. In the E-step, the expected observation likelihood and the prior distribution of the hidden variables are estimated. In experiments, the proposed automatic segmentation algorithm is applied to multiple gray nuclei structures such as caudate, putamens and thalamus of three-dimensional magnetic resonance imaging in volunteers and patients. As for the robustness and accuracy of the segmentation algorithm, the results of the proposed EM-joint shape-based algorithm outperformed those obtained using the statistical shape model-based techniques in the same framework and a current state-of-the-art region competition level set method.     

An improved Chan–Vese model by regional fitting for infrared image segmentation

In this paper, a regional fitting method is proposed for infrared image segmentation. In our model, the intensity of each pixel in a region is described by using the sum of the class center and the weighted variance of the region, in order to build energy function for encouraging the similarity pixels to be clustered together. The adoption of such way can thereby eliminate the issue associated with the drift of the class center that is existed in Chan–Vese model. Particularly, followed by incorporating energy function into the level set evolution without re-initialization framework, the variational formulation can force the level set function to be closed to object boundaries. Experiments on some representative and real infrared images have demonstrated that our model has higher performance of segmentation in comparison with Chan–Vese model without re-initialization, and some existing methods, including LBF and LCV model.     

基于C-V模型的改进快速水平集图像分割法

针对水平集方法计算复杂度高,无法满足实时系统要求的缺陷,提出一种改进的快速水平集算法。该算法对快速水平集算法进行简化,采用单链表表示轮廓曲线。利用C-V模型的二值拟合项来设计曲线演化的速度函数,保留了C-V模型的全局优化特性。还给出了一个基于单链表中轮廓点个数变化的水平集演化终止准则。该算法不仅明显提高了分割速度,且对噪声图像也能实现高效的分割。     

基于局部和全局信息的自适应水平集图像分割

针对仅采用局部或全局信息无法快速准确分割灰度不均匀图像的问题,提出了一种基于局部和全局信息的自适应水平集图像分割模型。首先,利用图像局部信息和全局信息建立局部能量项和全局能量项,并且利用演化曲线轮廓内外小邻域的灰度均值差作为自变量,建立了权重函数模型,实现了局部能量项和全局能量项之间权重的自适应调整,提高了模型分割灰度不均匀图像的效率和准确性。其次,提出了一种新的能量惩罚项,避免了水平集函数的重新初始化,增强了数值计算的稳定性。最后,为验证模型的优越性,将模型与CV模型、LBF模型和LGIF模型进行了对比,并通过分割时间、迭代次数以及相似度等指标对分割结果进行了客观、定量分析。最终结果表明:该模型不但对初始轮廓具有较高鲁棒性,而且对灰度不均匀图像具有较高的分割准确性与分割效率。