Regular gridding and segmentation for microarray images

An automated method for gridding and clustering-based segmentation of cDNA microarray images

Microarray technology has become a power tool in the field of bioinformatics. It is used to measure gene expression levels and similar to any other image capturing processes is prone to noise. There are different kinds of noise, during preparation, hybridization and scanning in microarray images which usually are modeled by Gaussian noise. Since introduction of wavelets in 1970s, many more forms and extensions of this transform have been developed and used, such as stationary wavelet transform (SWT), complex wavelet transform (CWT), curvelet transform (CURV) and contourlet transform (CNT). By developing of more sparse transforms, it is important to have a perspective of how efficient the transforms are in different applications, such as microarray image analysis. In this paper, we compare the efficiency of common sparse transforms including ordinary discrete wavelet transform (DWT), SWT, CWT, CURV, CNT, Contourlet-SD decomposition, steerable pyramid (STP) and shearlet transform (SHR) for microarray image denoising. Therefore after converting microarray image into x-let transform, BayesShrink method, soft and hard thresholding are used to perform denoising of these images. Both local and general thresholds are calculated for each subband in order to evaluate the effect of incorporating intrascale dependency on top of sparsity property in statistical modeling of x-let's coefficients. Our simulation results show that CWT and SHR outperforms the others when using global thresholding and SWT is the preferred transform when using local thresholding. Although STP and SHR have better performance for some criteria like structural similarity (SSIM) index, but CWT is faster.

The Stanford Microarray Database (SMD) (http://smd.stanford.edu) is a research tool for hundreds of Stanford researchers and their collaborators. In addition, SMD functions as a resource for the entire biological research community by providing unrestricted access to microarray data published by SMD users and by disseminating its source code. In addition to storing GenePix (Axon Instruments) and ScanAlyze output from spotted microarrays, SMD has recently added the ability to store, retrieve, display and analyze the complete raw data produced by several additional microarray platforms and image analysis software packages, so that we can also now accept data from Affymetrix GeneChips (MAS5/GCOS or dChip), Agilent Catalog or Custom arrays (using Agilent's Feature Extraction software) or data created by SpotReader (Niles Scientific). We have implemented software that allows us to accept MAGE-ML documents from array manufacturers and to submit MIAME-compliant data in MAGE-ML format directly to ArrayExpress and GEO, greatly increasing the ease with which data from SMD can be published adhering to accepted standards and also increasing the accessibility of published microarray data to the general public. We have introduced a new tool to facilitate data sharing among our users, so that datasets can be shared during, before or after the completion of data analysis. The latest version of the source code for the complete database package was released in November 2004 (http://smd.stanford.edu/download/), allowing researchers around the world to deploy their own installations of SMD.

A wavelet-based Markov random field segmentation model in segmenting microarray experiments

Image segmentation is an important step in several computer vision applications. The segmentation of images into homogeneous and meaningful regions is a fundamental technique for image analysis. Textures occupy a vital role in a wide range of computer vision research fields; from microscopic images to images sent down to earth by satellites, from the analysis of multi- spectral scan images to outdoor scenes, all consist of texture. Although several methods have been proposed, less work has been done in developing suitable techniques for segmentation of texture images. After a careful and in-depth survey on wavelet transforms, the present study found that efficient numerical solutions in the signal processing applications can be found using Stationary Wavelet Transform (SWT). SWT is redundant, linear and shift invariant, that's why it gives a better approximation than the DWT. In this paper a novel texture segmentation method based on ―SWT and Textural Properties‖ is proposed. Multi scale SWT with Textural Properties and morphological treatment is used in the present study to detect fine edges from texture images for a fine segmentation.

DNA microarray technology has permitted the analysis of global gene expression profiles in clinical diagnosis, treatment, and environmental health research for several diseases including cancer. Microarray images analysis, processing and segmentation are decisive steps in gene expression analysis, since any error leads to improper diagnosis. These techniques increased and enhanced over the past few years. However, the segmentation of the unshaped spots within the microarray image is still a problem due to the variations of spots in shapes and sizes. Hence, we introduce a new unshaped microarray spot segmentation model, which focuses on spots detection and segmentation regardless of their size and shape using fractal dimensions transform. Real microarray images from the Stanford Microarray Images Database (SMD) and Universal Microarray Images Database (UNC) are used to evaluate the efficiency of the proposed model. The numerical and visual results show that the proposed model improves the accuracy and the efficiency of the spots segmentation process. Biological researchers can use this model in their labs and clinics, as a free priceless software instead of using expensive ones like ScanAlyze, GenePix or spot software.

Gaussian-input Gaussian mixture model for representing density maps and atomic models.

Microarray technology provides a powerful tool for the quantification of the expression level for a large number of genes simultaneously. Image analysis is a crucial step for data extraction of microarray gene expression experiments. In this paper we propose a supervised method for the segmentation of microarray images. The Bayes classifier is employed for a pixel by pixel classification. The proposed method classifies the pixels of the image in two classes, foreground and background pixels. For this task, an informative set of features is used from both green and red channels. The method is evaluated using a set of 5184 spots (consisting of approximately 15000000 pixels), from the Stanford Microarray Database (SMD) and the reported classification accuracy is 82%.

This paper presents a new hybrid and parallel processing image fusion technique for multi-focus images. Here, two different methods are used i.e. Stationary Wavelet Transform (SWT) and Principal Component Analysis (PCA) that are implemented on the input images in parallel. These two methods are applied on same input dataset. This method is although computationally bit slower than the compared method but still it shows better results. The fused images obtained from the SWT and PCA are later again fused using PCA method. This is a parallel processing technique. The result of proposed method is compared with other traditional and conventional methods like DWT, SWT and PCA. It is observed that the result of proposed method is better than the compared methods. The result of the proposed method is analyzed qualitatively (visual appearance) and quantitatively using CC (Correlation Coefficient), UIQI (Universal Image Quality Index), and PSNR (Peak Signal-to-Noise Ratio). The proposed technique will have the capability to be implemented in real time applications of Visual Sensor Network (VSN).

The Stanford Microarray Database (SMD) is a DNA microarray research database that provides a large amount of data for public use. This chapter describes the use of the primary tools for searching, browsing, retrieving, and analyzing data available for SMD. With this introduction, researchers and students will be able to examine and analyze a large body of gene expression and other experiments. Additional tools for depositing, annotating, sharing, and analyzing data, available only to registered users, are also described. SMD is available for installation as a local database.

BackgroundBiomedical ontologies are being widely used to annotate biological data in a computer-accessible, consistent and well-defined manner. However, due to their size and complexity, annotating data with appropriate terms from an ontology is often challenging for experts and non-experts alike, because there exist few tools that allow one to quickly find relevant ontology terms to easily populate a web form.ResultsWe have produced a tool, OntologyWidget, which allows users to rapidly search for and browse ontology terms. OntologyWidget can easily be embedded in other web-based applications. OntologyWidget is written using AJAX (Asynchronous JavaScript and XML) and has two related elements. The first is a dynamic auto-complete ontology search feature. As a user enters characters into the search box, the appropriate ontology is queried remotely for terms that match the typed-in text, and the query results populate a drop-down list with all potential matches. Upon selection of a term from the list, the user can locate this term within a generic and dynamic ontology browser, which comprises the second element of the tool. The ontology browser shows the paths from a selected term to the root as well as parent/child tree hierarchies. We have implemented web services at the Stanford Microarray Database (SMD), which provide the OntologyWidget with access to over 40 ontologies from the Open Biological Ontology (OBO) website [1]. Each ontology is updated weekly. Adopters of the OntologyWidget can either use SMD's web services, or elect to rely on their own. Deploying the OntologyWidget can be accomplished in three simple steps: (1) install Apache Tomcat [2] on one's web server, (2) download and install the OntologyWidget servlet stub that provides access to the SMD ontology web services, and (3) create an html (HyperText Markup Language) file that refers to the OntologyWidget using a simple, well-defined format.ConclusionWe have developed OntologyWidget, an easy-to-use ontology search and display tool that can be used on any web page by creating a simple html description. OntologyWidget provides a rapid auto-complete search function paired with an interactive tree display. We have developed a web service layer that communicates between the web page interface and a database of ontology terms. We currently store 40 of the ontologies from the OBO website [1], as well as a several others. These ontologies are automatically updated on a weekly basis. OntologyWidget can be used in any web-based application to take advantage of the ontologies we provide via web services or any other ontology that is provided elsewhere in the correct format. The full source code for the JavaScript and description of the OntologyWidget is available from .

Microarray image compression: SLOCO and the effect of information loss

The topic of this thesis is the development of novel methods of biomedical data analysis in software and hardware. A novel system has been developed for the extraction of texture features from images and video. This system has been implemented in software, which is optimized for execution time, and hardware, which efficiently uses the features of the FPGA. The system calculates second order statistical features based on the gray level cooccurrence matrix. The hardware implementation is capable of calculating four 16-dimensional texture features, significantly reducing the necessary computational time, while preserving the accuracy of the results. The system has been evaluated on reference videos and achieves real time operation. A novel method for the calculation of the logarithm function has also been developed, which achieves fast operation, high accuracy and low resource utilization. It is based on a piecewise linear approximation using an arbitrarily high number of segments. Additionally, it provides adaptability to the input data set, which further enhances the accuracy. The evaluation of the hardware architecture was performed with regards to accuracy, speed of computation and required resources, whereas the experimental results illustrate its advantageous performance in comparison to state of the art methods. Finally, a novel method for automatic microarray image gridding has been developed. Microarray images contain a matrix of spots, which are separated by a grid based on the maximization of the margin between consecutive rows or columns of spots. This method employs image processing techniques to identify the spot positions and sizes, and subsequently selects the valid spots based on the spot size distribution. The valid spots are then provided as a training set to a number of linear support vector machine classifiers, which produce the grid lines. This method performs highly accurate microarray gridding on images that are affected by rotation, intense artifacts and spots of low or zero intensity. The evaluation was performed on reference microarray images, in comparison to state of the art methods

Level set method and Gaussian Mixture model (GMM) are two very valuable tools for natural image segmentation. The former aims to acquire good geometrical continuity of segmentation boundaries, while the latter focuses on analyzing statistical properties of image feature data. Some studies on the integration between them have been reported due to their complementarity in the last 10 years. However, these studies generally supposed that the image-featured data density distribution of every segmented domain is independent with each other and can be separately approximated by Gaussian model or GMM, which conflicts with the fundamental idea of GMM clustering-based image segmentation. To remedy this problem, we give a new insight at image segmentation objective under the combined framework between Bayesian theory and GMM density approximation. Thereby, a novel level set image segmentation method integrated with GMM (GMMLS) is proposed. Then, the theoretical analysis on GMMLS is given, in which some valuable results are demonstrated. At last, several types of natural image segmentation experiments are reported and the corresponding results indicate that GMMLS can obtain better or at least equivalent performance compared with existing relevant methods in almost all cases.

Gridding and spot segmentation are two critical steps in microarray gene expression data analysis. However, the problems of noise contamination and donut-shaped spots often make signal extraction process a laborintensive task. In this paper, we propose a three-step method for automatic gridding and spot segmentation. The method starts with a background removal and noise eliminating step, and then proceeds in two steps. The first step applies a fully unsupervised method to extract blocks and grids from the cleaned data. The second step applies a simple, progressive spot segmentation method to deal with inner holes and noise in spots. We tested its performance on real microarray images against a widely used software GenePix. Our results show that the proposed method deals effectively with poor-conditioned microarray images in both gridding and spot segmentation.