挖掘机器人铲斗目标图像的改进分水岭分割

挖掘机器人自主挖掘目标的实现过程中,利用视觉信息跟踪、识别挖掘机器人铲斗目标是关键技术之一.传统的阈值分割方法很难将铲斗从复杂环境中分割出来,提出了改进的分水岭铲斗图像目标分割方法,首先对铲斗目标图像进行模糊C-均值（C为预定的类别数目）聚类分割,再以初步分割后的图像为基础得到梯度图像,将梯度值与设定的阈值比较得到标记点,最后以标记点作为极小值点进行分水岭分割.实验表明分割效果得到了改善.     

A statistical approach for intensity loss compensation of confocal microscopy images

In this paper, a probabilistic technique for compensation of intensity loss in confocal microscopy images is presented. For single-colour-labelled specimen, confocal microscopy images are modelled as a mixture of two Gaussian probability distribution functions, one representing the background and another corresponding to the foreground. Images are segmented into foreground and background by applying Expectation Maximization algorithm to the mixture. Final intensity compensation is carried out by scaling and shifting the original intensities with the help of parameters estimated for the foreground. Since foreground is separated to calculate the compensation parameters, the method is effective even when image structure changes from frame to frame. As intensity decay function is not used, complexity associated with estimation of the intensity decay function parameters is eliminated. In addition, images can be compensated out of order, as only information from the reference image is required for the compensation of any image. These properties make our method an ideal tool for intensity compensation of confocal microscopy images that suffer intensity loss due to absorption/scattering of light as well as photobleaching and the image can change structure from optical/temporal section-to-section due to changes in the depth of specimen or due to a live specimen. The proposed method was tested with a number of confocal microscopy image stacks and results are presented to demonstrate the effectiveness of the method.     

Testing mounting media to eliminate background noise in confocal microscope 3-D images of insect genitalia

Recently, the confocal laser scanning microscope (CLSM) has been used to image and generate three-dimensional reconstructions of miniscule insect tissues and cuticular structures. These three-dimensional reconstructions provide the investigator with key information concerning the spatial relationship among structures and substructures. Unfortunately, there can be high levels of background "noise" which can obscure the specimen in these three-dimensional reconstructions. This background "noise" might be a result of the mounting media either autofluorescing or reflecting and scattering the imaged specimen's fluorescence. The standard nonpermanent mounting medium is glycerine jelly (a 1:17:17 ratio of porcine gelatin to glycerine to water). In this study, the organic molecule (lipid, protein, or carbohydrate) added to the glycerine water mixture was varied. The relative background to specimen signal (the mean voxel brightness reading in ImageJ freeware) was compared across mountants. The mounting media tested are ranked from best (least background noise) to worst (most background noise) as follows: agarose, agar, pectin, gelatin (the standard), petroleum jelly. A 1% agarose mountant (1:50:50 ratio of agarose to glycerine to water) is recommended because it causes little to no background noise, provides consistent high quality contrast between specimen and background with increasing depth, and is easy to handle.     

Six-color segmentation of multicolor images in the infection studies of Listeria monocytogenes

Multiple immunofluorescent staining is a powerful strategy for visualizing the spatial and temporal relationship between antigens, cell populations, and tissue components in histological sections. To segment different cell populations from the multicolor image generated by immunostaining based on color addition theory, a systems approach is proposed for automatic segmentation of six colors. After image acquisition and processing, images are automatically segmented with the proposed approach and six-pseudo channels for individual or colocalized fluorescent dye are generated to distinguish different cell types. The principle of this approach is the classification of each pixel into one of six colors (red, green, blue, yellow, magenta, and cyan) by choosing the minimal angular deviation between the RGB vector of the given pixel and six classically defined edge vectors. In the present infection studies of Listeria monocytogenes, the new multicolor staining methods based on the color addition were applied and the proposed color segmentation was performed for multicolor analysis. Multicolor analysis was accomplished to study the migration and interaction of Listeria and different cell subpopulations such as CD4CD25 double positive T regulatory cells; we also visualized simultaneously the B cells, T cells, dendritic cells, macrophages, and Listeria in another experiment. After Listeria infection, ERTR9 macrophages and dendritic cells formed cluster with Listeria in the infection loci. The principle of color addition and the systems approach for segmentation may be widely applicable in infection and immunity studies requiring multicolor imaging and analysis. This approach can also be applied for image analysis in the multicolor in vivo imaging, multicolor FISH or karyotyping or other studies requiring multicolor analysis.     

一种合成孔径声呐图像目标分割方法

合成孔径声呐图像的信噪比低于普通光学图像,使图像分割成为合成孔径声呐图像处理中的重要环节。本文研究了表示合成孔径声呐图像数据分布的瑞利混合模型,结合马尔科夫随机场模型,将其应用于声呐图像水下目标(亮区)分割;通过最大期望算法分别估计目标和背景的瑞利混合模型参数,并利用该参数使用Graph cut方法进行马尔科夫随机场图像分割,通过重复迭代,最后形成稳定的目标分割结果;对实际的声呐图像进行了数据分析及目标分割,结果表明瑞利混合模型在描述合成孔径声呐声图上有良好的性能,可以改善目标分割的效果。     

The significance of 3-D transfer functions in confocal scanning microscopy

The three-dimensional (3-D) transfer function is a useful concept for describing image formation in confocal scanning microscopy. From it we can derive the corresponding 2-D transfer function for in-focus imaging. In confocal transmission this can be derived analytically. The 1-D transfer function for on-axis imaging, which can be expressed in an analytical form even for confocal fluorescence with differing wavelengths of excitation and fluorescence, can be derived from the 3-D transfer function. The 2-D transfer function for in-focus imaging in confocal fluorescence microscopy with a finite-sized detector is also presented, which is shown to exhibit sign changes and can therefore result in reversals of image contrast.     

Adaptive striping watershed segmentation method for processing microscopic images of overlapping irregular‐shaped and multicentre particles

Oversegmentation is a major drawback of the morphological watershed algorithm. Here, we study and reveal that the oversegmentation is not only because of the irregular shapes of the particle images, which people are familiar with, but also because of some particles, such as ellipses, with more than one centre. A new parameter, the striping level, is introduced and the criterion for striping parameter is built to help find the right markers prior to segmentation. An adaptive striping watershed algorithm is established by applying a procedure, called the marker searching algorithm, to find the markers, which can effectively suppress the oversegmentation. The effectiveness of the proposed method is validated by analysing some typical particle images including the images of gold nanorod ensembles.     

Segmentation of confocal microscope images of cell nuclei in thick tissue sections

Segmentation of intact cell nuclei from three-dimensional (3D) images of thick tissue sections is an important basic capability necessary for many biological research studies. However, segmentation is often difficult because of the tight clustering of nuclei in many specimen types. We present a 3D segmentation approach that combines the recognition capabilities of the human visual system with the efficiency of automatic image analysis algorithms. The approach first uses automatic algorithms to separate the 3D image into regions of fluorescence-stained nuclei and unstained background. This includes a novel step, based on the Hough transform and an automatic focusing algorithm to estimate the size of nuclei. Then, using an interactive display, each nuclear region is shown to the analyst, who classifies it as either an individual nucleus, a cluster of multiple nuclei, partial nucleus or debris. Next, automatic image analysis based on morphological reconstruction and the watershed algorithm divides clusters into smaller objects, which are reclassified by the analyst. Once no more clusters remain, the analyst indicates which partial nuclei should be joined to form complete nuclei. The approach was assessed by calculating the fraction of correctly segmented nuclei for a variety of tissue types: Caenorhabditis elegans embryos (839 correct out of a total of 848), normal human skin (343/362), benign human breast tissue (492/525), a human breast cancer cell line grown as a xenograft in mice (425/479) and invasive human breast carcinoma (260/335). Furthermore, due to the analyst's involvement in the segmentation process, it is always known which nuclei in a population are correctly segmented and which not, assuming that the analyst's visual judgement is correct.     

3D boundary extraction of confocal cellular images using higher order statistics

In recent years, cell biologists have benefited greatly from using confocal microscopy to study intracellular organelles. For high-level image analysis, 3D boundary extraction of cell structure is a preliminary requisite in confocal cellular imaging. To detect the object boundaries, most investigators have used gradient/Laplacian operator as a principal tool. In this paper we propose a higher order statistics (HOS) based boundary extraction algorithm for confocal cellular image data set using kurtosis. After the initial pre-processing, kurtosis boundary map is estimated locally for the entire volume using a cubic sliding window and subsequently the noisy kurtosis value is removed by thresholding. Voxels having positive kurtosis value with zero-crossing on its surface are then identified as boundary voxels. Typically used in signal processing, kurtosis for 3D cellular image processing is a novel application of HOS. Its reliable and robust nature of computing makes it very suitable for volumetric cellular boundary extraction.     

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.     

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.     

Automatic measurement of volume percentage stroma in endometrial images using texture segmentation

The popularity of digital microscopy and tissue microarrays allow the use of high-throughput imaging for pathology research. To coordinate with this new technique, it is essential to automate the process of extracting information from such high amount of images. In this paper, we present a new model called the Subspace Mumford-Shah model for texture segmentation of microscopic endometrial images. The model incorporates subspace clustering techniques into a Mumford-Shah model to solve texture segmentation problems. The method first uses a supervised procedure to determine several optimal subspaces. These subspaces are then embedded into a Mumford-Shah objective function so that each segment of the optimal partition is homogeneous in its own subspace. The method outperforms a widely used method in bioimaging community called k-means segmentation since it can separate textures which are less separated in the full feature space, which confirm the usefulness of subspace clustering in texture segmentation. Experimental results also show that the proposed method is well performed on diagnosing premalignant endometrial disease and is very practical for segmenting image set sharing similar properties.     

Adaptive-weighted cubic B-spline using lookup tables for fast and efficient axial resampling of 3D confocal microscopy images

Confocal laser scanning microscopy has become a most powerful tool to visualize and analyze the dynamic behavior of cellular molecules. Photobleaching of fluorochromes is a major problem with confocal image acquisition that will lead to intensity attenuation. Photobleaching effect can be reduced by optimizing the collection efficiency of the confocal image by fast z-scanning. However, such images suffer from distortions, particularly in the z dimension, which causes disparities in the x, y, and z directions of the voxels with the original image stacks. As a result, reliable segmentation and feature extraction of these images may be difficult or even impossible. Image interpolation is especially needed for the correction of undersampling artifact in the axial plane of three-dimensional images generated by a confocal microscope to obtain cubic voxels. In this work, we present an adaptive cubic B-spline-based interpolation with the aid of lookup tables by deriving adaptive weights based on local gradients for the sampling nodes in the interpolation formulae. Thus, the proposed method enhances the axial resolution of confocal images by improving the accuracy of the interpolated value simultaneously with great reduction in computational cost. Numerical experimental results confirm the effectiveness of the proposed interpolation approach and demonstrate its superiority both in terms of accuracy and speed compared to other interpolation algorithms.     

Automated tracing and volume measurements of neurons from 3-D confocal fluorescence microscopy data

Three-dimensional (3-D) image analysis algorithms and experimental results that demonstrate the feasibility of fully automated tracing of neurons from fluorescence confocal microscopy data are presented. The input to the automated analysis is a set of successive optical slices that have been acquired using a confocal scanning laser microscope. The output of the system is a labelled graph representation of the neuronal topology that is spatially aligned with the 3-D image data. A variety of topological and metric analyses can be carried out using this representation. For instance, precise measurements of volumes, lengths, diameters and tortuosities can be made over specific portions of the neuron that are specified in terms of the graph representation. The effectiveness of the method is demonstrated for a set of sample fields featuring selectively stained neurons. Additional work will be needed to refine the method for unsupervised use with complex data involving multiple intertwined neurons and extremely fine dendritic structures.     

Algorithms for accurate 3D registration of neuronal images acquired by confocal scanning laser microscopy

This paper presents automated and accurate algorithms based on high‐order transformation models for registering three‐dimensional (3D) confocal images of dye‐injected neurons. The algorithms improve upon prior methods in several ways, and meet the more stringent image registration needs of applications such as two‐view attenuation correction recently developed by us. First, they achieve high accuracy (≈ 1.2 voxels, equivalent to 0.4 µm) by using landmarks, rather than intensity correlations, and by using a high‐dimensional affine and quadratic transformation model that accounts for 3D translation, rotation, non‐isotropic scaling, modest curvature of field, distortions and mechanical inconsistencies introduced by the imaging system. Second, they use a hierarchy of models and iterative algorithms to eliminate potential instabilities. Third, they incorporate robust statistical methods to achieve accurate registration in the face of inaccurate and missing landmarks. Fourth, they are fully automated, even estimating the initial registration from the extracted landmarks. Finally, they are computationally efficient, taking less than a minute on a 900‐MHz Pentium III computer for registering two images roughly 70 MB in size. The registration errors represent a combination of modelling, estimation, discretization and neuron tracing errors. Accurate 3D montaging is described; the algorithms have broader applicability to images of vasculature, and other structures with distinctive point, line and surface landmarks.     

Segmentation of 3D microtomographic images of granular materials with the stochastic watershed

Segmentation of 3D images of granular materials obtained by microtomography is not an easy task. Because of the conditions of acquisition and the nature of the media, the available images are not exploitable without a reliable method of extraction of the grains. The high connectivity in the medium, the disparity of the object's shape and the presence of image imperfections make classical segmentation methods (using image gradient and watershed constrained by markers) extremely difficult to perform efficiently. In this paper, we propose a non‐parametric method using the stochastic watershed, allowing to estimate a 3D probability map of contours. Procedures allowing to extract final segmentation from this function are then presented.     

A method for the evaluation of thousands of automated 3D stem cell segmentations

There is no segmentation method that performs perfectly with any dataset in comparison to human segmentation. Evaluation procedures for segmentation algorithms become critical for their selection. The problems associated with segmentation performance evaluations and visual verification of segmentation results are exaggerated when dealing with thousands of three‐dimensional (3D) image volumes because of the amount of computation and manual inputs needed. We address the problem of evaluating 3D segmentation performance when segmentation is applied to thousands of confocal microscopy images (z‐stacks). Our approach is to incorporate experimental imaging and geometrical criteria, and map them into computationally efficient segmentation algorithms that can be applied to a very large number of z‐stacks. This is an alternative approach to considering existing segmentation methods and evaluating most state‐of‐the‐art algorithms. We designed a methodology for 3D segmentation performance characterization that consists of design, evaluation and verification steps. The characterization integrates manual inputs from projected surrogate ‘ground truth’ of statistically representative samples and from visual inspection into the evaluation. The novelty of the methodology lies in (1) designing candidate segmentation algorithms by mapping imaging and geometrical criteria into algorithmic steps, and constructing plausible segmentation algorithms with respect to the order of algorithmic steps and their parameters, (2) evaluating segmentation accuracy using samples drawn from probability distribution estimates of candidate segmentations and (3) minimizing human labour needed to create surrogate ‘truth’ by approximating z‐stack segmentations with 2D contours from three orthogonal z‐stack projections and by developing visual verification tools. We demonstrate the methodology by applying it to a dataset of 1253 mesenchymal stem cells. The cells reside on 10 different types of biomaterial scaffolds, and are stained for actin and nucleus yielding 128 460 image frames (on average, 125 cells/scaffold × 10 scaffold types × 2 stains × 51 frames/cell). After constructing and evaluating six candidates of 3D segmentation algorithms, the most accurate 3D segmentation algorithm achieved an average precision of 0.82 and an accuracy of 0.84 as measured by the Dice similarity index where values greater than 0.7 indicate a good spatial overlap. A probability of segmentation success was 0.85 based on visual verification, and a computation time was 42.3 h to process all z‐stacks. While the most accurate segmentation technique was 4.2 times slower than the second most accurate algorithm, it consumed on average 9.65 times less memory per z‐stack segmentation.     

3D multiscale segmentation and morphological analysis of x‐ray microtomography from cold‐sprayed coatings

X‐ray microtomography from cold‐sprayed coatings brings a new insight on this deposition process. A noise‐tolerant segmentation algorithm is introduced, based on the combination of two segmentations: a deterministic multiscale segmentation and a stochastic segmentation. The stochastic approach uses random Poisson lines as markers. Results on a X‐ray microtomographic image of aluminium particles are presented and validated.