Three-dimensional imaging by deconvolution microscopy

Deconvolution is a computational method used to reduce out-of-focus fluorescence in three-dimensional (3D) microscope images. It can be applied in principle to any type of microscope image but has most often been used to improve images from conventional fluorescence microscopes. Compared to other forms of 3D light microscopy, like confocal microscopy, the advantage of deconvolution microscopy is that it can be accomplished at very low light levels, thus enabling multiple focal-plane imaging of light-sensitive living specimens over long time periods. Here we discuss the principles of deconvolution microscopy, describe different computational approaches for deconvolution, and discuss interpretation of deconvolved images with a particular emphasis on what artifacts may arise.     

图像反卷积复原技术在玉米45S rDNA转录图式研究中的运用

由于成像焦平面外杂光的干扰,宽场荧光显微镜所得的图像往往较模糊,使其不适合用来观察植物细胞核内的精细结构。该实验讨论了反卷积软件中对图像复原结果有较大影响的几个重要参数的设置。经过合适的图像反卷积复原,由宽场荧光显微镜获取的玉米45S rRNA原位杂交信号图像得以清楚显示。对所得杂交图像的分析表明:玉米45S rDNA转录往往先发生在核仁外围,且随着核仁转录活性的提高逐渐向核仁内部扩散,并最终与5S rRNA一起,在核仁内部的空洞结构中形成成熟rRNA。研究结果显示,反卷积复原可有效提高宽场荧光显微镜所得二维图像的分辨率,从而使宽场荧光显微镜在植物细胞核内精细结构研究中发挥更多的作用。     

FISH Finder: a high-throughput tool for analyzing FISH images

MOTIVATION: Fluorescence in situ hybridization (FISH) is used to study the organization and the positioning of specific DNA sequences within the cell nucleus. Analyzing the data from FISH images is a tedious process that invokes an element of subjectivity. Automated FISH image analysis offers savings in time as well as gaining the benefit of objective data analysis. While several FISH image analysis software tools have been developed, they often use a threshold-based segmentation algorithm for nucleus segmentation. As fluorescence signal intensities can vary significantly from experiment to experiment, from cell to cell, and within a cell, threshold-based segmentation is inflexible and often insufficient for automatic image analysis, leading to additional manual segmentation and potential subjective bias. To overcome these problems, we developed a graphical software tool called FISH Finder to automatically analyze FISH images that vary significantly. By posing the nucleus segmentation as a classification problem, compound Bayesian classifier is employed so that contextual information is utilized, resulting in reliable classification and boundary extraction. This makes it possible to analyze FISH images efficiently and objectively without adjustment of input parameters. Additionally, FISH Finder was designed to analyze the distances between differentially stained FISH probes. AVAILABILITY: FISH Finder is a standalone MATLAB application and platform independent software. The program is freely available from: http://code.google.com/p/fishfinder/downloads/list.     

Normalization of multicolor fluorescence in situ hybridization (M-FISH) images for improving color karyotyping.

BACKGROUND: Multiplex or multicolor fluorescence in situ hybridization (M-FISH) is a recently developed cytogenetic technique for cancer diagnosis and research on genetic disorders. By simultaneously viewing the multiply labeled specimens in different color channels, M-FISH facilitates the detection of subtle chromosomal aberrations. The success of this technique largely depends on the accuracy of pixel classification (color karyotyping). Improvements in classifier performance would allow the elucidation of more complex and more subtle chromosomal rearrangements. Normalization of M-FISH images has a significant effect on the accuracy of classification. In particular, misalignment or misregistration across multiple channels seriously affects classification accuracy. Image normalization, including automated registration, must be done before pixel classification. METHODS AND RESULTS: We studied several image normalization approaches that affect image classification. In particular, we developed an automated registration technique to correct misalignment across the different fluor images (caused by chromatic aberration and other factors). This new registration algorithm is based on wavelets and spline approximations that have computational advantages and improved accuracy. To evaluate the performance improvement brought about by these data normalization approaches, we used the downstream pixel classification accuracy as a measurement. A Bayesian classifier assumed that each of 24 chromosome classes had a normal probability distribution. The effects that this registration and other normalization steps have on subsequent classification accuracy were evaluated on a comprehensive M-FISH database established by Advanced Digital Imaging Research (http://www.adires.com/05/Project/MFISH_DB/MFISH_DB.shtml). CONCLUSIONS: Pixel misclassification errors result from different factors. These include uneven hybridization, spectral overlap among fluors, and image misregistration. Effective preprocessing of M-FISH images can decrease the effects of those factors and thereby increase pixel classification accuracy. The data normalization steps described in this report, such as image registration and background flattening, can significantly improve subsequent classification accuracy. An improved classifier in turn would allow subtle DNA rearrangements to be identified in genetic diagnosis and cancer research.     

Concepts in imaging and microscopy. Exploring biological structure and function with confocal microscopy

Confocal microscopy is providing new and exciting opportunities for imaging cell structure and physiology in thick biological specimens, in three dimensions, and in time. The utility of confocal microscopy relies on its fundamental capacity to reject out-of-focus light, thus providing sharp, high-contrast images of cells and subcellular structures within thick samples. Computer controlled focusing and image-capturing features allow for the collection of through-focus series of optical sections that may be used to reconstruct a volume of tissue, yielding information on the 3-D structure and relationships of cells. Tissues and cells may also be imaged in two or three spatial dimensions over time. The resultant digital data, which encode the image, are highly amenable to processing, manipulation and quantitative analyses. In conjunction with a growing variety of vital fluorescent probes, confocal microscopy is yielding new information about the spatiotemporal dynamics of cell morphology and physiology in living tissues and organisms. Here we use mammalian brain tissue to illustrate some of the ways in which multidimensional confocal fluorescence imaging can enhance studies of biological structure and function.     

Deconvolution in 3-D optical microscopy

Summary Fluorescent probes are becoming ever more widely used in the study of subcellular structure, and determination of their three-dimensional distributions has become very important. Confocal microscopy is now a common technique for overcoming the problem of out-of-focus flare in fluorescence imaging, but an alternative method uses digital image processing of conventional fluorescence images — a technique often termed deconvolution or restoration. This review attempts to explain image deconvolution in a non-technical manner. It is also applicable to 3-D confocal images, and can provide a further significant improvement in clarity and interpretability of such images. Some examples of the application of image deconvolution to both conventional and confocal fluorescence images are shown.     

Hybrid Nature Inspired SMO-GBM Classifier for Exudate Classification on Fundus Retinal Images

Background: The diabetic retinopathy can result in loss of vision if not detected in the earlier stages. Exudates are the lesions which play a crucial role in early diagnosis of diabetic retinopathy. The localization of exudates lesions with high values of performance metrics is complicated due to presence of blood vessels and other noisy artifacts. Method: We present computer aided system for classification of retinal fundus images using a novel nature inspired spider monkey optimization for parameter tuning of gradient boosting machines classifier. The image enhancement has been performed with histogram equalization and contourlet transform. The pixels belonging to optic disc region are detected and eliminated using circular Hough transform and Otsu's segmentation method. We have employed Kirsch's matrices for blood vessel detection. The GLCM based feature vector extraction has been employed for textural features. The classification has been performed with hybrid SMO-GBM classifier. Result: We have utilized the STARE database for validation of proposed technique. The proposed system can effectively classify entire image set from test data. The SMO-GBM classifier can further sub-segregate into sub classes with an average accuracy of 97.5%. Conclusion: The proposed approach provides detection and grading of diabetic retinopathy. The abnormality is further categories as soft, moderate and severe. The hybrid SMO-GBM classifier yields a better statistical metrics than the existing exudates classification approaches.     

SCAPEVIEWER: preliminary results of a landscape perception classification system based on neural network technology

In this paper, the implementation of a pilot computerized system for the classification of landscape images (SCAPEVIEWER) is presented. A total of 108 landscape photographs have been organized, according to the mean estimation of scenic beauty from seven experts, into three classes: indistinctive (C1), typical or common (C2), and distinctive (C3). For each of the landscape photographs, 10 indices are estimated. These indices are then fed to a classifier based on neural network (NN) technology. In order to examine whether NNs are suitable for this specific application, two different approaches have been tested and compared against a linear discrimination method (LDM) classifier. The first approach is a feed forward NN (Classic-NN), while the second approach (Hybrid-NN) is based on the Classic-NN modified by using genetic algorithms (GAs). The correct classification performances achieved by the Classic-NN and the Hybrid-NN were 87% and 84%, respectively, while the classification performance of the LDM classifier was only 68%. Although the Classic-NN achieved slightly better results than the Hybrid-NN, the latter is preferred due to its ability of index selection and automatical adjustment of internal NN parameters. The pilot system has shown the feasibility for classifying landscape photographs according to scenic beauty by means of a computerized system combining the knowledge of an expert with a NN classifier.     

Enhanced background rejection in thick tissue with differential-aberration two-photon microscopy

When a two-photon excited fluorescence (TPEF) microscope is used to image deep inside tissue, out-of-focus background can arise from both ballistic and nonballistic excitation. We propose a solution to largely reject TPEF background in thick tissue. Our technique is based on differential-aberration imaging with a deformable mirror. By introducing extraneous aberrations in the excitation beam path, we preferentially quench in-focus TPEF signal while leaving out-of-focus TPEF background largely unchanged. A simple subtraction of an aberrated, from an unaberrated, TPEF image then removes background while preserving signal. Our differential aberration (DA) technique is simple, robust, and can readily be implemented with standard TPEF microscopes with essentially no loss in temporal resolution when using a line-by-line DA protocol. We analyze the performance of various induced aberration patterns, and demonstrate the effectiveness of DA-TPEF by imaging GFP-labeled sensory neurons in a mouse olfactory bulb and CA1 pyramidal cells in a hippocampus slice.     

Quantification of fluorescence in situ hybridization signals by image cytometry.

In this study we aimed at the development of a cytometric system for quantification of specific DNA sequences using fluorescence in situ hybridization (ISH) and digital imaging microscopy. The cytochemical and cytometric aspects of a quantitative ISH procedure were investigated, using human peripheral blood lymphocyte interphase nuclei and probes detecting high copy number target sequences as a model system. These chromosome-specific probes were labeled with biotin, digoxigenin, or fluorescein. The instrumentation requirements are evaluated. Quantification of the fluorescence ISH signals was performed using an epi-fluorescence microscope with a multi-wavelength illuminator, equipped with a cooled charge couple device (CCD) camera. The performance of the system was evaluated using fluorescing beads and a homogeneously fluorescing specimen. Specific image analysis programs were developed for the automated segmentation and analysis of the images provided by ISH. Non-uniform background fluorescence of the nuclei introduces problems in the image analysis segmentation procedures. Different procedures were tested. Up to 95% of the hybridization signals could be correctly segmented using digital filtering techniques (min-max filter) to estimate local background intensities. The choice of the objective lens used for the collection of images was found to be extremely important. High magnification objectives with high numerical aperture, which are frequently used for visualization of fluorescence, are not optimal, since they do not have a sufficient depth of field. The system described was used for quantification of ISH signals and allowed accurate measurement of fluorescence spot intensities, as well as of fluorescence ratios obtained with double-labeled probes.     

A workingperson's guide to deconvolution in light microscopy.

Thefluorescence microscope is routinely used to study cellular structure in many biomedical research laboratories and is increasingly used as a quantitative assay system for cellular dynamics. One of the major causes of image degradation in the fluorescence microscope is blurring. Deconvolution algorithms use a model of the microscope imaging process to either subtract or reassign out-of-focus blur. A variety of algorithms are now commercially available, each with its own characteristic advantages and disadvantages. In this article, we review the imaging process in the fluorescence microscope and then discuss how the various deconvolution methods work. Finally, we provide a summary of practical tips for using deconvolution and discuss imaging artifacts and how to minimize them.     

A Slantlet transform based intelligent system for magnetic resonance brain image classification

The present paper proposes the development of a new approach for automated diagnosis, based on classification of magnetic resonance (MR) human brain images. Wavelet transform based methods are a well-known tool for extracting frequency space information from non-stationary signals. In this paper, the proposed method employs an improved version of orthogonal discrete wavelet transform (DWT) for feature extraction, called Slantlet transform, which can especially be useful to provide improved time localization with simultaneous achievement of shorter supports for the filters. For each two-dimensional MR image, we have computed its intensity histogram and Slantlet transform has been applied on this histogram signal. Then a feature vector, for each image, is created by considering the magnitudes of Slantlet transform outputs corresponding to six spatial positions, chosen according to a specific logic. The features hence derived are used to train a neural network based binary classifier, which can automatically infer whether the image is that of a normal brain or a pathological brain, suffering from Alzheimer's disease. An excellent classification ratio of 100% could be achieved for a set of benchmark MR brain images, which was significantly better than the results reported in a very recent research work employing wavelet transform, neural networks and support vector machines.     

Interval-coded texture features for artifact rejection in automated cervical cytology

In order to improve the separation between abnormal cells and noncellular artifacts in the CERVIFIP automated cervical cytology prescreening system, 22 different object texture features were investigated. The features were all statistical parameters of the pixel density histograms or one-dimensional filtered values of central and border regions of the object images. The features were calculated for 231 images (100 cells and 131 artifacts) detected as Suspect Cells by the current CERVIFIP and were then tested in hierarchical and linear discriminant classifiers. After selecting the two best features for use in a hierarchical classifier, 83% correct classification was achieved. One of these features was specifically designed to remove poorly focused objects. With maximum likelihood discrimination using all 22 features, an overall correct classification rate of 90% was obtained.     

Automatic greenhouse insect pest detection and recognition based on a cascaded deep learning classification method

Inspection of insect sticky paper traps is an essential task for an effective integrated pest management (IPM) programme. However, identification and counting of the insect pests stuck on the traps is a very cumbersome task. Therefore, an efficient approach is needed to alleviate the problem and to provide timely information on insect pests. In this research, an automatic method for the multi-class recognition of small-size greenhouse insect pests on sticky paper trap images acquired by wireless imaging devices is proposed. The developed algorithm features a cascaded approach that uses a convolutional neural network (CNN) object detector and CNN image classifiers, separately. The object detector was trained for detecting objects in an image, and a CNN classifier was applied to further filter out non-insect objects from the detected objects in the first stage. The obtained insect objects were then further classified into flies (Diptera: Drosophilidae), gnats (Diptera: Sciaridae), thrips (Thysanoptera: Thripidae) and whiteflies (Hemiptera: Aleyrodidae), using a multi-class CNN classifier in the second stage. Advantages of this approach include flexibility in adding more classes to the multi-class insect classifier and sample control strategies to improve classification performance. The algorithm was developed and tested for images taken by multiple wireless imaging devices installed in several greenhouses under natural and variable lighting environments. Based on the testing results from long-term experiments in greenhouses, it was found that the algorithm could achieve average F₁-scores of 0.92 and 0.90 and mean counting accuracies of 0.91 and 0.90, as tested on a separate 6-month image data set and on an image data set from a different greenhouse, respectively. The proposed method in this research resolves important problems for the automated recognition of insect pests and provides instantaneous information of insect pest occurrences in greenhouses, which offers vast potential for developing more efficient IPM strategies in agriculture.     

A method for the enumeration of bacterial adhesion to epithelial cells using image analysis

Abstract Computerised image analysis was utilised to enumerate the attachment of Staphylococcus epidermidis to HEp2 cell monolayers. A differential staining technique was employed such that individual staphylococcal cells stood out in sharp contrast against the uneven cell surface and granular contents of the epithelial cells. The primary image analysis operation involved subtracting an out-of-focus image from an in-focus image of the bacteria on the monolayer, thereby accentuating the bacterial image. Enumeration, using a particle counting routine, was rapid and reproducible, facilitating counting in excess of 700 bacteria per field at ×500 magnification. The computerised programme compared favourably with manual counting and would provide a rapid, objective and morphologically discriminatory method for evaluating bacterial attachment to various tissues.     

Optical sectioning microscopy

Confocal scanning microscopy, a form of optical sectioning microscopy, has radically transformed optical imaging in biology. These devices provide a powerful means to eliminate from images the background caused by out-of-focus light and scatter. Confocal techniques can also improve the resolution of a light microscope image beyond what is achievable with widefield fluorescence microscopy. The quality of the images obtained, however, depends on the user's familiarity with the optical and fluorescence concepts that underlie this approach. We describe the core concepts of confocal microscopes and important variables that adversely affect confocal images. We also discuss data-processing methods for confocal microscopy and computational optical sectioning techniques that can perform optical sectioning without a confocal microscope.     

Automated image analysis for quantitative fluorescence in situ hybridization with environmental samples

When fluorescence in situ hybridization (FISH) analyses are performed with complex environmental samples, difficulties related to the presence of microbial cell aggregates and nonuniform background fluorescence are often encountered. The objective of this study was to develop a robust and automated quantitative FISH method for complex environmental samples, such as manure and soil. The method and duration of sample dispersion were optimized to reduce the interference of cell aggregates. An automated image analysis program that detects cells from 4',6'-diamidino-2-phenylindole (DAPI) micrographs and extracts the maximum and mean fluorescence intensities for each cell from corresponding FISH images was developed with the software Visilog. Intensity thresholds were not consistent even for duplicate analyses, so alternative ways of classifying signals were investigated. In the resulting method, the intensity data were divided into clusters using fuzzy c-means clustering, and the resulting clusters were classified as target (positive) or nontarget (negative). A manual quality control confirmed this classification. With this method, 50.4, 72.1, and 64.9% of the cells in two swine manure samples and one soil sample, respectively, were positive as determined with a 16S rRNA-targeted bacterial probe (S-D-Bact-0338-a-A-18). Manual counting resulted in corresponding values of 52.3, 70.6, and 61.5%, respectively. In two swine manure samples and one soil sample 21.6, 12.3, and 2.5% of the cells were positive with an archaeal probe (S-D-Arch-0915-a-A-20), respectively. Manual counting resulted in corresponding values of 22.4, 14.0, and 2.9%, respectively. This automated method should facilitate quantitative analysis of FISH images for a variety of complex environmental samples.