基于改进的变分水平集和区域生长的图像分割方法的研究

针对水平集和区域生长方法都存在对噪声和初始边界敏感以及容易从弱边缘处泄露等不稳定的问题,提出了结合待分割目标灰度统计信息和图像梯度信息的水平集演化函数对水平集方法进行改进,并利用区域生长方法解决水平集方法对初始边界敏感的问题.分别用传统区域生长方法、阈值方法、GAC模型、C-V模型、Snake模型以及本文方法进行从腹部CT图像分割肝脏区域的实验比较,实验结果表明:本文方法不仅可以减少图像分割的时间,而且显著地提高了分割质量.     

基于图割和边缘行进的肝脏CT序列图像分割

提出一种新的基于图割和边缘行进的腹部CT序列图像肝脏分割方法。首先,针对输入序列的数据特征,建立肝脏亮度和外观模型,突出肝脏区域抑制非肝脏区域;然后,将肝脏亮度、外观模型以及相邻切片之间的位置信息有效融入图割能量函数,实现CT序列肝脏的自动初步分割;最后,针对血管欠分割问题,提出了一种基于边缘行进的结果优化方法。通过对XHCSU14和SLIVER07数据库提供的30个病人肝脏序列的分割实验,以及与其他多种肝脏分割方法的比较,表明该方法能完整有效地分割肝脏,准确性高,鲁棒性强。     

基于感兴趣区域轮廓的图像分割方法

针对耗时和区域边界不精确的图像分割问题,对边缘检测方法和区域生长方法进行研究、改进,提出以边缘检测和区域生长相结合的感兴趣区域轮廓的图像分割方法,该方法能够更加精确地对图像进行分割。实验结果表明,该方法对复杂环境下感兴趣区域的图像分割具有良好的效果。     

一种基于灰度连续区域分割的视频对象分割方法

针对目前许多分割方法中分割边界不精确、计算复杂和缓存帧多等问题，提出了一种结合空间区域分割和运动象素检测的自动分割方法：先将当前视频帧分割为不同的灰度连续区域，再利用二次帧差确定视频图像中的运动象素，然后按一定的规则确定哪些灰度连续区域属于运动区域，从而有效地从静止的复杂背景中分割出运动对象区域。实验结果表明这种分割方法计算简单、分割边界比较精确。     

基于序列间先验约束和多视角信息融合的肝脏CT图像分割

医学电子计算机断层扫描(CT)序列图像中肝脏的准确分割是实现计算机辅助肝手术的重要前提,然而图像中存在的组织病变、边界模糊或缺失、不同组织间的粘连给肝脏分割带来极大挑战。针对这些问题,该文提出一种基于图像序列间先验约束的半自动分割方法,并进一步采取了多视角信息融合的方式实现肝脏的准确分割。该方法的优势在于无需大量数据的收集和复杂的先验训练。在Sliver07公开数据集合的验证结果显示,和领域内主要方法相比,该方法具有较高的分割准确度,特别是当肝脏区域存在病灶、边界模糊或缺失的情况下具有明显提升。     

基于级联网络的肝脏肿瘤CT图像分割

肝脏肿瘤计算机断层扫描（Computed Tomography,CT）图像分割是肝癌诊断与治疗过程的重要环节。近年来,基于U型结构的卷积神经网络在该分割任务取得了巨大的成功,但仍存在一些挑战,如肿瘤边界分割不精确、小肿瘤难以检测等。为提高肝脏肿瘤的分割精度,提出一种级联网络MCPUNet用于肝脏肿瘤分割任务。MCPUNet引入MDB(MDconv Block)和MP(Mixing Pooling)以获取上下文信息,MDB通过混合深度可分离卷积和坐标注意力机制提取图像的多尺度特征,MP用于下采样减少图像尺寸。实验证明,与原始的U-Net模型相比,该模型在肝脏肿瘤分割任务上的交并比（Intersection over Union,IoU）、准确度和召回率指标分别提高3.8%、2.5%和2.0%,为肝癌诊断和治疗提供了可靠依据。     

基于先验信息遗传算法的图像分割

医学图像分割通常由医生根据器官位置、形状等先验信息从图像中手动圈出疑似的肿瘤区域,以便用于确定治疗计划与诊断。手动分割的方法存在主观差异性与分割的不一致性,可能造成疾病诊断的误判,延误治疗时机。由于器官间对比度较弱,且不存在明确的分割界限,自动医学图像分割应用于疾病诊断还具有很大的挑战。本文在遗传算法的基础上,结合已知形状、区域属性和目标位置等先验信息,提出了一种新颖有效的自动医学图像分割算法。为了验证提出算法的有效性,在盆腔CT图像上应用该算法进行前列腺癌的分割。实验结果分析表明,文中提出的算法可以清楚地区分出目标器官的边界,准确地分割出前列腺区域,对模糊的图像也有较好的检测分割效果,适合用于肿瘤的自动分割。     

基于模糊能量聚类的变分水平集遥感图像分割算法

提出一种基于模糊能量聚类的变分水平集遥感图像分割算法,该算法保留了变分水平集能够综合利用区域和边界信息的特点,改善了变分水平集方法对带噪声遥感图像进行分割时存在去噪效果不明显、分割精度不高的问题。在通过变分法得到能量泛函取极小值的水平集函数演化方程的基础上,采用了连续的最优隶属度函数,得到模糊能量聚类的变分水平集。实验仿真及对比结果表明,该算法分割后的图像区域具有明显灰度差和边界区分,去噪效果良好,而且分割精度优于对比算法。     

采用奇异值分解的图像模糊区域检测分割新方法

针对局部模糊图像的模糊区域检测分割问题,提出了一种改进的基于奇异值分解和图像抠图的模糊区域自动检测分割算法。首先,采用分块的方法对局部模糊图像进行再次模糊,通过比较前后图像块的奇异值特征变化差异将其标识模糊块或清晰块以得到一个标识图。其次,根据标识图,结合图像抠图技术对图像的局部模糊区域进行自动提取。实验结果表明,该方法可以较为精确地检测并分割出局部模糊图像中的模糊区域。      

改进的Fast Marching肝脏分割方法

为提高肝脏分割效率、改善分割效果,针对传统Fast Marching(FM)方法固定参数值T对肝脏分割结果的影响,提出了一种改进的FM肝脏分割方法。根据对腹部CT图像序列的肝脏区域灰度统计信息,估算出每幅图像上肝脏区域大小,进而自适应调整FM中的到达时间参数T,有效消除传统的固定参数值对分割效率和准确率的影响。对10套腹部CT图像序列的实验结果表明,该方法能够全自动、快速、准确的分割出肝脏区域。其中,处理单副CT图像所需的平均时间为0.3s,平均准确率为97%,其高效性、准确性为临床诊断和手术导航提供了有利信息。      

Tumor segmentation in lung CT images based on support vector machine and improved level set

In lung CT images, the edge of a tumor is frequently fuzzy because of the complex relationship between tumors and tissues, especially in cases that the tumor adheres to the chest and lung in the pathology area. This makes the tumor segmentation more difficult. In order to segment tumors in lung CT images accurately, a method based on support vector machine (SVM) and improved level set model is proposed. Firstly, the image is divided into several block units; then the texture, gray and shape features of each block are extracted to construct eigenvector and then the SVM classifier is trained to detect suspicious lung lesion areas; finally, the suspicious edge is extracted as the initial contour after optimizing lesion areas, and the complete tumor segmentation can be obtained by level set model modified with morphological gradient. Experimental results show that this method can efficiently and fast segment the tumors from complex lung CT images with higher accuracy.     

基于softmax回归与图割法的脑肿瘤分割算法

从医学图像中分割脑肿瘤区域可以为脑肿瘤的诊断以及放射治疗提供帮助.但肿瘤区域的变化异常且边界非常模糊,因此自动或半自动地分割脑肿瘤非常困难.针对这一问题,本文结合softmax回归和图割法提出一种脑肿瘤分割算法.首先融合多序列核磁共振图像(MRI)并标记训练样本,再用softmax回归训练模型参数并计算每个点属于各个类别的概率,最后将概率融入到图割法中,用最小切/最大流方法得到最终分割结果.实验表明提出的方法可以更好地得到脑肿瘤的边界,并能较准确地分割出脑肿瘤区域.     

Automatic liver and lesion segmentation: a primary step in diagnosis of liver diseases

Computed Tomography (CT) images are widely used for diagnosis of liver diseases and volume measurement for liver surgery and transplantation. Segmentation of liver and lesion is regarded as a major primary step in computer-aided diagnosis of liver diseases. Lesion alone cannot be segmented automatically from the abdominal CT image since there are tissues external to the liver with similar intensity to the lesions. Therefore, it is necessary to segment the liver first so that lesion can then be segmented accurately from it. In this paper, an approach for automatic and effective segmentation of liver and lesion from CT images needed for computer-aided diagnosis of liver is proposed. The method uses confidence connected region growing facilitated by preprocessing and postprocessing functions for automatic segmentation of liver and Alternative Fuzzy C-Means clustering for lesion segmentation. The algorithm is quantitatively evaluated by comparing automatic segmentation results to the manual segmentation results based on volume measurement error, figure of merit, spatial overlap, false positive error, false negative error, and visual overlap.     

Liver Vessels Segmentation Using a Hybrid Geometrical Moments/Graph Cuts Method

This paper describes a fast and fully automatic method for liver vessel segmentation on computerized tomography scan preoperative images. The basis of this method is the introduction of a 3-D geometrical moment-based detector of cylindrical shapes within the minimum-cut/maximum-flow energy minimization framework. This method represents an original way to introduce a data term as a constraint into the widely used Boykov’s graph cuts algorithm, and hence, to automate the segmentation. The method is evaluated and compared with others on a synthetic dataset. Finally, the relevancy of our method regarding the planning of a necessarily accurate percutaneous high-intensity focused ultrasound surgical operation is demonstrated with some examples.      

改进边界指示函数的水平集活动轮廓模型

由于受成像原理的限制,导致超声图像对比度低、边界模糊,因此基于边界的水平集分割效果很不理想。为了提高超声图像的分割精度和分割效率,提出了一种梯度信息与区域信息相结合的水平集分割算法。首先对基于边界的距离正则化水平集演化(DRLSE)模型进行改进,将区域信息引入到边界指示函数中,并用改进后的边界指示函数代替DRLSE模型中的边界指示函数,最后,得到一个梯度与区域信息相结合的水平集演化模型。结果表明,本文中的模型能准确分割甲状腺肿瘤超声图像,且在分割效率和分割精确度方面均比DRLSE模型有所提高。     

Fast and accuracy extraction of infrared target based on Markov random field

Infrared images are characterized by small signal-to-noise ratio (SNR) and low contrast thus making it much difficult to achieve accurate infrared target extraction. This paper proposes a fast and accurate segmentation approach to extract targets from an infrared image. First, the regions of interests (ROIs) which contain the entire targets region and a little background region are detected based on the variance weighted information entropy feature. Second, the infrared image is modeled by Gaussian Markov random field (MRF), and the ROIs are used as the target regions while the remaining region as the background to perform the initial segmentation. Finally, by searching solution space within the ROIs, the targets are accurately extracted by the energy minimization using the iterated condition mode (ICM) based on the fact that targets can only exist in ROIs. Because the iterated segmentation results are updated within the ROIs only, this coarse-to-fine extraction method can greatly accelerate the convergence speed and efficiently reduce the interference of the background clutter and noise. Experimental results of the real infrared images demonstrate that the proposed method can extract single and multiple infrared targets accurately and rapidly.     

Automated brain structure segmentation based on atlas registration and appearance models

Accurate automated brain structure segmentation methods facilitate the analysis of large-scale neuroimaging studies. This work describes a novel method for brain structure segmentation in magnetic resonance images that combines information about a structure's location and appearance. The spatial model is implemented by registering multiple atlas images to the target image and creating a spatial probability map. The structure's appearance is modeled by a classifier based on Gaussian scale-space features. These components are combined with a regularization term in a Bayesian framework that is globally optimized using graph cuts. The incorporation of the appearance model enables the method to segment structures with complex intensity distributions and increases its robustness against errors in the spatial model. The method is tested in cross-validation experiments on two datasets acquired with different magnetic resonance sequences, in which the hippocampus and cerebellum were segmented by an expert. Furthermore, the method is compared to two other segmentation techniques that were applied to the same data. Results show that the atlas- and appearance-based method produces accurate results with mean Dice similarity indices of 0.95 for the cerebellum, and 0.87 for the hippocampus. This was comparable to or better than the other methods, whereas the proposed technique is more widely applicable and robust.