数字人脑切片图像中小脑组织的连续自动分割

提出了一种基于改进Snake模型的分割方法,用于数字人脑切片数据集中小脑组织的连续自动分割.在基本的Snake模型中添加了向心力、气球力,并采用自适应的能量约束项系数,根据相邻切片图像中小脑轮廓具有相似性,依次将单张切片的分割结果作为相邻切片分割的初始轮廓,进而实现整个数据集中小脑组织的连续自动分割.自动分割结果与专家手动分割结果的一致性较好,分割相似指数的平均值达到92.95％,最大为97.87％.结果表明该方法能够较为准确地从彩色人脑切片图像中提取出复杂的小脑组织,克服了现有方法对大量人工参与的依赖,并提高了分割的精度.     

序列磁共振颅脑影像的脑组织自动提取方法

为自动从MR脑影像中提取脑组织,提出一种新颖的脑组织提取算法.该算法在水平集算法的基础上,通过结合形态学方法,可以较为准确地截断脑组织与非脑组织粘连的部分.首先采用C-V模型对输入的影像进行预分割,由于某些脑组织会与视觉神经等部位的灰度相同,而C-V模型是基于区域平均灰度的分割,因此导致分割后无法提取脑组织.为了解决这一问题,采用一种形态学的腐蚀膨胀算法,通过循环腐蚀边界,得到粘连组织分离时刻的影像,再通过膨胀算法,使分离后的影像膨胀到腐蚀前的位置,与水平集算法结果取交集,从而完成脑组织的正确提取.为了提高实用性,采用改进后的水平集算法进行求解,在确保结果正确的基础上极大地提高了分割速度.算法适用于二维及三维的脑组织提取,实验结果表明,该算法具备良好的准确性、通用性与实用性.     

一种基于改进的边缘搜索和CANNY算法的图像分割方法

提出了一种基于边缘搜索和CANNY算法相结合的简捷而有效的图像分割方法.该算法中使用了ROBERT法来检测边缘,再用改进的带权启发式边缘搜索法来搜索所有的边缘信息,最后用CANNY算法自增强边缘.将该算法应用于ICT图像自动分割中,获得了边缘清晰、平滑、定位精确的分割图像.     

多尺度区域生长与去粘连模型的乳腺细胞分割

乳腺癌已经成为女性最常见的恶性肿瘤,组织切片显微图像的病理分析是诊断的主要手段,细胞的准确分割是病理分析的重要环节。该文提出了一种新的乳腺细胞显微图像的自动分割算法:首先结合小波分解和多尺度区域生长算法分离细胞和背景,实现对细胞的精确定位;然后采用改进的数学形态学对粘连细胞进行一次细分割;接着再采用基于曲率尺度空间(CSS)的角点检测分割算法对粘连细胞进行二次细分割;两次细分割方法构成了一个双策略去粘连模型,保证了去粘连的准确性和鲁棒性。将算法应用到22幅乳腺细胞显微图像上,可以对不同类型的乳腺细胞图像进行全自动分割,有较高的分割灵敏度(0.944±0.024)和特异度(0.937±0.038),且具有较好的普适性。     

基于规则划分和RJMCMC的可变类图像分割

为了自动确定遥感图像分割中的类别数,提出了一种结合规则划分和逆跳马尔科夫链蒙特卡洛(RJMCMC)算法的可变类图像分割方法。首先,将图像域划分成若干个不同的规则子块,并假设每个子块内的像素满足同一独立的多值Gaussian分布;在此基础上,根据贝叶斯定理,建立基于区域的图像分割模型;然后利用RJMCMC算法模拟该分割模型,以自动确定图像类别数并实现区域分割;为了进一步提高分割精度,设计了精细化操作。利用本文提出的方法,分别对合成及彩色遥感图像进行可变图像分割,实验结果表明,提出的方法不仅能自动确定图像类别数,还可以实现区域分割,从而验证提出算法的可行性及有效性。     

基于改进的图论最小生成树及骨架距离直方图分割细胞图像

为了解决模糊且有粘连的细胞图像的难以分割问题,本文针对医学细胞图像的特点,应用图论的思想提出了一种图论与数学形态学结合的图像分割算法.该算法先对图像进行去噪和增强,然后用改进的图论最小生成树(MST)算法对细胞图像进行初始分割.改进的主要内容是在算法中引入了细胞尺寸和形状的信息,从而在一定程度上改善了图论算法过分割的缺陷.在进一步的图像分割中,为了解决二值图像中的细胞粘连问题,结合数学形态学的骨架边界距离信息找出分裂线将粘连细胞分离.与常规的分水岭算法完全不同,该算法没有重复性的运算.一系列细胞图像的试验表明,该算法能够很好地分割模糊且有粘连的细胞图像,其结果令人满意.     

基于背景减除的彩色铁谱图像自动分割

提出一种基于背景减除和标记分水岭算法的彩色铁谱图像自动分割方法.其分割流程为:基于颜色分量比对彩色铁谱图像的背景进行减除,实现磨粒与背景的分离;通过对分离后的图像进行形态学处理使其成为后续分水岭分割的基础图像;结合形态学复合开闭重建和阈值极小值提取技术得到磨粒前景标记图像,对磨粒测地影响区骨架进行提取得到图像背景标记;利用形态学极小值强加技术修改基础图像,并利用分水岭算法实现其自动分割.     

一种核模糊C均值聚类算法及其应用

图像分割在许多医学成像应用中起着重要的作用。本文提出了一种新的用于图像分割的聚类算法。该算法通过利用核距离修改FCM-AWA算法中的目标函数而实现,即用核距离替代FCM-AWA中的欧氏距离,相应的得到核FCM-AWA聚类算法——KAWA-FCM聚类算法。利用该算法进行合成和真实图像分割的实验结果表明,当图像含有噪声时,与FCM-AWA算法相比,HAWA-FCM算法具有更好的性能。此外,基于该算法进行了牙菌斑量化的实验,实验结果表明,相对于利用菌斑指数的量化结果,基于KAWA-FCM的量化结果具有定量、自动和客观等特点。     

脑灰质的一种自动分割算法研究

针对MRI脑部图像,提出一种脑灰质的自动分割算法。根据观察和研究发现,人脑MRI中的脑灰质部分存在一种分布形式,把这种分布形式抽象成一种曲线形式从而进行分割,可以得到一种较为准确的脑部图像分割效果。自动分割算法主要分为3个步骤:首先,计算出图像的直方图并对直方图进行模糊;其次,利用模糊聚类算法计算出聚类中心;最后,根据模糊聚类中心计算出脑灰质区域的曲线,从而实现阈值分割。自动分割算法经过大量模拟和真实MRI脑部图像进行了验证。     

高精度贴片机视觉系统图像预处理算法研究

针对高精度自动贴片机的视觉系统图像预处理算法进行了研究,提出了针对贴片机PCB板标记点及元件图像处理的预处理方法.开发了针对视觉定位系统的图像识别软件,并用PCB板图像及元件图像进行实验验证.实验结果表明,该预处理算法能够有效地分割原始图像目标区及背景区、排除干扰噪声、增强图像特征,为贴片机进一步的图像识别及定位提供了有利条件.     

Tumor detection from enhanced magnetic resonance imaging using fuzzy curvelet

Effective medical image analysis is possible by the use of technique known as segmentation. Segmentation is a very challenging task because there is not any standard segmentation method is available for any medical application. In this article, we have proposed an automatic brain MR image segmentation method. Fast discrete curvelet transform and spatial fuzzy C-mean algorithm is used for noise removal and segmentation of brain MR image. Fuzzy entropy has been used for calculating adaptive and optimal threshold to separate out the image segments. Our proposed system is exclusively based on the information contained by the image itself. No extra information and no human intervention are required in our proposed system. We have tested our proposed system on different T1, T2 and PD brain MR images.     

Dense nuclei segmentation based on graph cut and convexity–concavity analysis

With the rapid advancement of 3D confocal imaging technology, more and more 3D cellular images will be available. However, robust and automatic extraction of nuclei shape may be hindered by a highly cluttered environment, as for example, in fly eye tissues. In this paper, we present a novel and efficient nuclei segmentation algorithm based on the combination of graph cut and convex shape assumption. The main characteristic of the algorithm is that it segments nuclei foreground using a graph‐cut algorithm with our proposed new initialization method and splits overlapping or touching cell nuclei by simple convexity and concavity analysis. Experimental results show that the proposed algorithm can segment complicated nuclei clumps effectively in our fluorescent fruit fly eye images. Evaluation on a public hand‐labelled 2D benchmark demonstrates substantial quantitative improvement over other methods. For example, the proposed method achieves a 3.2 Hausdorff distance decrease and a 1.8 decrease in the merged nuclei error per slice.     

Amended bacterial foraging algorithm for multilevel thresholding of magnetic resonance brain images

Magnetic Resonance (MR) brain image segmentation into several tissue classes is of significant interest to visualize and quantify individual anatomical structures. Traditionally, the segmentation is performed manually in a clinical environment that is operator dependant, difficult to reproduce and computationally expensive. To overcome these drawbacks, this paper proposes a new heuristic optimization algorithm, amended bacterial foraging (ABF) algorithm for multilevel thresholding of MR brain images. The optimal thresholds are found by maximizing Kapur’s (entropy criterion) and Otsu’s (between-class variance) thresholding functions using ABF algorithm. The proposed method is evaluated on 10 axial, T₂ weighted MR brain image slices and compared with other evolutionary algorithms such as bacterial foraging (BF), particle swarm optimization (PSO) algorithm and genetic algorithm (GA). From the experimental results, it is observed that the new method is computationally more efficient, prediction wise more accurate and shows faster convergence compared to BF, PSO and GA methods. Applying the proposed thresholding algorithm to these images can help for the best segmentation of gray matter, white matter and cerebrospinal fluid which offers the possibility of improved clinical decision making and diagnosis.     

Automatic macroscopic density artefact removal in a Nissl‐stained microscopic atlas of whole mouse brain

Acquiring a whole mouse brain at the micrometer scale is a complex, continuous and time‐consuming process. Because of defects caused by sample preparation and microscopy, the acquired image data sets suffer from various macroscopic density artefacts that worsen the image quality. We have to develop the available preprocessing methods to improve image quality by removing the artefacts that effect cell segmentation, vascular tracing and visualization. In this study, a set of automatic artefact removal methods is proposed for images obtained by tissue staining and optical microscopy. These methods significantly improve the complicated images that contain various structures, including cells and blood vessels. The whole mouse brain data set with Nissl staining was tested, and the intensity of the processed images was uniformly distributed throughout different brain areas. Furthermore, the processed image data set with its uniform brightness and high quality is now a fundamental atlas for image analysis, including cell segmentation, vascular tracing and visualization.     

An automatic segmentation algorithm for 3D cell cluster splitting using volumetric confocal images

With the rapid advance of three-dimensional (3D) confocal imaging technology, more and more 3D cellular images will be available. Segmentation of intact cells is a critical task in automated image analysis and quantification of cellular microscopic images. One of the major complications in the automatic segmentation of cellular images arises due to the fact that cells are often closely clustered. Several algorithms are proposed for segmenting cell clusters but most of them are 2D based. In other words, these algorithms are designed to segment 2D cell clusters from a single image. Given 2D segmentation methods developed, they can certainly be applied to each image slice with the 3D cellular volume to obtain the segmented cell clusters. Apparently, in such case, the 3D depth information with the volumetric images is not really used. Often, 3D reconstruction is conducted after the individualized segmentation to build the 3D cellular models from segmented 2D cellular contours. Such 2D native process is not appropriate as stacking of individually segmented 2D cells or nuclei do not necessarily form the correct and complete 3D cells or nuclei in 3D. This paper proposes a novel and efficient 3D cluster splitting algorithm based on concavity analysis and interslice spatial coherence. We have taken the advantage of using the 3D boundary points detected using higher order statistics as an input contour for performing the 3D cluster splitting algorithm. The idea is to separate the touching or overlapping cells or nuclei in a 3D native way. Experimental results show the efficiency of our algorithm for 3D microscopic cellular images.     

基于差商的油液监测铁谱图像自适应分割

针对油液监测中铁谱磨粒图像分割阈值难以选取的问题,本文提出一种基于差商的自适应铁谱图像分割算法。首先,将铁谱磨粒灰度图像转换成三维灰度直方图,并对其进行切片分析;然后,引入Newton插值多项式,将不同切片所得的频数作为切片灰度-频数曲线的插值点,基于差商构造第一类可接受函数和第二类可接受函数,结合实验数据确定两类误差,选取同时满足两类误差的最小灰度值作为分割阈值;最后,用本文方法对不同类型的磨粒图像以及添加高斯噪声和椒盐噪声后图像分别进行分割实验,并与经典的迭代阈值法、Otsu算法、最大熵法进行了比较。实验结果表明,本文方法受噪声干扰较小,误检率和漏检率整体优于其他3种算法。对分割所得的磨粒图像进行特征提取,并利用支持向量机进行识别,本文方法对3种故障磨粒识别准确率最高,达到82.86%,虽在运行时间上无明显优势,但综合性能最优,能满足油液监测过程中铁谱图像自适应分割的需求。     

MRI brain lesion image detection based on color-converted K-means clustering segmentation

We present a preliminary design and experimental results of tumor objects tracking method for magnetic resonance imaging (MRI) brain images (some stock images) that utilizes color-converted segmentation algorithm with K-means clustering technique. The method is capable of solving unable exactly contoured lesion objects problem in MRI image by adding the color-based segmentation operation. The key idea of color-converted segmentation algorithm with K-means is to solve the given MRI image by converting the input gray-level image into a color space image and operating the image labeled by cluster index. In this paper we investigate the possibility of employing this approach for image-based-MRI application. The application of the proposed method for tracking tumor is demonstrated to help pathologists distinguish exactly lesion size and region.     

视频监控系统中的一种运动检测算法

提出了一种用于数字视频监控系统中运动人体检测和报警的算法，该算法是一种基于背景减除法的运动目标检测算法，同时采用一种基于统计关系的双阈值分割，能够有效地检测出图像中的运动人体。实验结果验证了上述算法的有效性。     

Brain tumor segmentation in multi‐spectral MRI using convolutional neural networks (CNN)

A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research.