An Automated Gridding and Segmentation Method for cDNA Microarray Image Analysis

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.

Image processing is an important stage of every microarray experiment. Reliability of this stage strongly influences the results of data analysis performed on extracted gene expressions. Multiple methods related to array recognition, spot segmentation and measurement extraction have emerged in this area over past several years. Currently there are various commercial and freeware packages available, which perform microarray image analysis. This paper attempts to review microarray image analysis as a whole and to make some experimental comparison of several computational schemes for signal segmentation and measurement extraction. Also we provide a detailed discussion of automated image quality control for use with microarray images.

cDNA microarray technology enables whole genome study of gene expressions by measuring the differential expression of genes in microarray images. An important first step in analyzing microarray image is the accurate delineation of the cDNA spots in the image. We report here a fully automated spot segmentation algorithm for cDNA microarray images. The algorithm makes use of morphological operations, adaptive multi-level thresholding, and statistical intensity modeling to perform automatic grid addressing and spot segmentation. Our algorithm is robust for even poor quality cDNA microarray images.

Microarray image processing plays an important role among array analysis and its precision will affect the application of gene chip. However, real microarray images drawn from various experimental procedures may contain noises and other artifacts, which result in a lower image processing accuracy. Hence, in this paper, we propose a novel image denoising method by introducing the compressed sensing theory into microarray image noise reduction. To improve the matching pursuit efficiency, the correlation coefficient is adopted. Experiments on 17 simulated images and 59 real microarray images obtained from the DeRisi, SIB and BCM data sets are conducted. Qualitative and quantitative results compared with the Donoho threshold, generalized wavelet and adaptive thresholding algorithm, reveal that our proposed method performs better on reducing the noises.

Bead encoding is a key problem central to all multiplexed bead-based microarrays. Most existing bead-based microarrays require complicated and costly bead fabrication and/or sophisticated bead decoding hardware to achieve high multiplexing. Recently, the development of spatial bead encoding techniques have opened up the possibility of using pattern matching and image processing to develop highly multiplexed, high-throughput bead-based arrays. In this thesis, we improve the existing spatial bead encoding scheme, and develop a pipeline of computational methods, which allows for automated spatial bead encoding. Six novel computational methods, that automate the proposed bead encoding scheme, are developed in this thesis. The proposed scheme improves the previously reported spatial encoding schemes by making them better suited for use in real world scenarios. In the spatial bead encoding scheme, a sequential bead deposition method is used to capture the identities of the beads in bright or dark field images of the array. While, a second fluorescence image of the array is used to quantify the target analyte concentrations associated with the beads. By aligning the two images using the patterns formed by the beads, both the bead identities (i.e. the target analyte associate with the bead) and the analyte concentrations are decoded. The six computational methods developed in this thesis, are grouped into three categories: bright and dark field image processing, fluorescence image processing, and bead pattern matching. These methods are developed such that they require minimal parameter tuning, and are able to deal with noisy images acquired in uncontrolled environments As part of the bright and dark field image processing we have developed two novel methods: a fully automatic method for detecting the underlying micro-well grid structure in the images, and an unsupervised learning based method to classify the micro-wells as either empty or containing a bead. We show the ability of the proposed methods to deal with extreme amounts of noise and distortions using multiple datasets. While, microarray image gridding is a well-studied problem in the context of fluorescence images of planar microarrays, to the best of our knowledge no methods have yet been developed for processing either bright or dark field images of bead-based microarrays. Unlike in bright field images, where all the beads are visible, in fluorescence images only those beads that are expressed in the sample are visible. Therefore, in fluorescence image analysis the first step is to detect the beads in the image. To this end, we have developed an unsupervised, simultaneous bead detection and segmentation method which uses the coherence in shape and size of the beads to circumvent the need for parameter optimization. The main challenge in this segmentation is the large dynamic range across which the beads are expressed. We have also developed a probabilistic non-linear gridding method that attempts to establish the micro-well grid structure from the detected beads. While similar gridding techniques have been developed in the past, we make two contributions in this regard: first, we put the gridding method in a probabilistic framework, and second, we show that in certain cases it is impossible to ascertain if the correct grid has been detected without using additional information about the physical properties of the array. The final step in the proposed bead encoding scheme is to establishing one-to-one correspondences between the beads detected in the bright field and fluorescence images. We have developed two methods for this matching. When the micro-well grid structure in the fluorescence image is successfully established, the grid information can be used to reduce the matching problem to a binary grid alignment problem. A grid matching method that is very fast and can handle a large number of beads (>50,000) has been developed for this purpose. Finally, to perform matching when the fluorescence image grid is not available, a novel point pattern matching method that is affine invariant and robust to small non-linear distortions has been developed. The point pattern matching method addresses the problem of matching large point sets in the presence of large amounts of outliers and occlusion. The proposed method is evaluated using several real and simulated datasets.

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

Genetic microarray image processing has become an important field of research to produce tools aiming to reliable gene expression estimation. Current instrumentation to analyze microarray images lacks flexibility and accuracy. In the present paper an FPGA-based hand-held device for the analysis of microarrays is described, which may implement basic scanning and reticle algorithms to estimate spots and expression levels in cDNA microarrays. The algorithms are based on global and local spot correlation, background removal and rectangular mask fitting. These algorithms can be recursively applied and are intrinsically parallelizable for practical implementation purposes. Results using specific microarray images are shown.

Interpreting ocean remote sensing images is still a challenge is worth studying because they can carry valuable information for various important applications. Due to the absence of labeled datasets, unsupervised object-based image analysis (OBIA) methods provide an effective solution to understand remote sensing images with its advantage of grouping local similar pixels into a homogeneous area. However, ocean remote sensing images usually have the characteristics of large size, large background, and coexisting of large and small objects, which result in previous OBIA methods easily falling into the difficulty of accurately segmenting the large and small objects at the same time, and the dilemma of time-consuming computation. To solve this problem, a novel multi-scale and multi-subgraph (MSMSG)-based image segmentation method is presented in this paper. First, a coarse-to-fine superpixel generation method is designed to generate optimal superpixels, which can not only solve the problem of coexisting large objects and small objects but also the problem of manually setting the initial segmentation number. Second, the proposed background removal strategy helps to eliminate the trouble of large background areas in ocean remote sensing images. Third, a multi-subgraph is constructed with the help of background removal. Finally, the multi-scale and multi-subgraph merging strategy is addressed to group all similar superpixels into a same cluster, which not only reduces the useless computation of nonadjacent superpixels but also avoids segmentation errors with the same scale. Experiments conducted on three different datasets show that the proposed segmentation method is high-performance and high-efficiency.

We present a new method for the automatic segmentation and components classification of brain Optic Pathway Gliomas (OPGs) from multi-spectral MRI datasets. Our method accurately identifies the sharp OPG boundaries and consistently delineates the missing contours by effectively incorporating prior location, shape, and intensity information. It then classifies the segmented OPG volume into its three main components--solid, enhancing, and cyst--with a probabilistic tumor tissue model generated from training datasets that accounts for the datasets grey-level differences. Experimental results on 25 datasets yield a mean OPG boundary surface distance error of 0.73mm and mean volume overlap difference of 30.6% as compared to manual segmentation by an expert radiologist. A follow-up patient study shows high correlation between the clinical tumor progression evaluation and the component classification results. To the best of our knowledge, ours is the first method for automatic OPG segmentation and component classification that may support quantitative disease progression and treatment efficacy evaluation.

A method for corneal nerves automatic segmentation and morphometric analysis

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

Regular gridding and segmentation for microarray images

Separation of complex mixtures of proteins by 2-DE is a fundamental component of current proteomic technology. Quantitative analysis of the images generated by digitization of such gels is critical for identifying alterations in protein expression within a given biological system. Software packages are designed for this purpose. The accurate definition of protein spot boundaries, using a suitable method of image segmentation, is a key requirement for image analysis. It is often necessary for operators to intervene manually to correct mistakes in spot segmentation; therefore operator subjectivity and differences in ability can weaken the analysis. We estimated the error in spot quantification after manual spot segmentation, which was performed by different operators, using two different software packages. Our results clearly show that this operation was associated with significant inter- and intra-variability and an overestimation of subsequent spot intensity, especially when spots were weak. For comparative studies, we suggest separately analysing spots which have been manually segmented by imposing a requirement for at least a threefold difference in spot intensity in addition to use of statistical tests.

A microarray-image model is used that takes into account many factors, including spot morphology, signal strength, background fluorescent noise, and shape and surface degradation. The model yields synthetic images whose appearance and quality reflect that of real microarray images. The model is used to link noise factors to the fidelity of signal extraction with respect to a standard image-extraction algorithm. Of particular interest is the identification of the noise factors and their interactions that significantly degrade the ability to accurately detect the true gene-expression signal. This study uses statistical criteria in conjunction with the simulation of various noise conditions to better understand the noise influence on signal extraction for cDNA microarray images. It proposes a paradigm that is implemented in software. It specifically considers certain kinds of noise in the noise model and sets these at certain levels; however, one can choose other types of noise or use different noise levels. In sum, it develops a statistical package that can work in conjunction with the existing image simulation toolbox.

Automatic segmentation of the retinal vasculature is a first step in computer-assisted diagnosis and treatment planning. The extraction of retinal vessels in pediatric retinal images is challenging because of comparatively wide arterioles with a light streak running longitudinally along the vessel's center, the central vessel reflex. A new method for automatic segmentation was developed and tested. A supervised method for retinal vessel segmentation in the images of multi-ethnic school children was developed based on ensemble classifier of bootstrapped decision trees. A collection of dual Gaussian, second derivative of Gaussian and Gabor filters, along with the generalized multiscale line strength measure and morphological transformation is used to generate the feature vector. The feature vector encodes information to handle the normal vessels as well as the vessels with the central reflex. The methodology is evaluated on CHASE_DB1, a relatively new public retinal image database of multi-ethnic school children, which is a subset of retinal images from the Child Heart and Health Study in England (CHASE) dataset. The segmented retinal images from the CHASE_DB1 database produced best case accuracy, sensitivity and specificity of 0.96, 0.74 and 0.98, respectively, and worst case measures of 0.94, 0.67 and 0.98, respectively. A new retinal blood vessel segmentation algorithm was developed and tested with a shared database. The observed accuracy, speed, robustness and simplicity suggest that the algorithm may be a suitable tool for automated retinal image analysis in large population-based studies.