Robust spots finding in microarray images with distortions

A hierarchical refinement algorithm for fully automatic gridding in spotted DNA microarray image processing

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

BackgroundMicroarray image analysis processes scanned digital images of hybridized arrays to produce the input spot-level data for downstream analysis, so it can have a potentially large impact on those and subsequent analysis. Signal saturation is an optical effect that occurs when some pixel values for highly expressed genes or peptides exceed the upper detection threshold of the scanner software (216 - 1 = 65, 535 for 16-bit images). In practice, spots with a sizable number of saturated pixels are often flagged and discarded. Alternatively, the saturated values are used without adjustments for estimating spot intensities. The resulting expression data tend to be biased downwards and can distort high-level analysis that relies on these data. Hence, it is crucial to effectively correct for signal saturation.ResultsWe developed a flexible mixture model-based segmentation and spot intensity estimation procedure that accounts for saturated pixels by incorporating a censored component in the mixture model. As demonstrated with biological data and simulation, our method extends the dynamic range of expression data beyond the saturation threshold and is effective in correcting saturation-induced bias when the lost information is not tremendous. We further illustrate the impact of image processing on downstream classification, showing that the proposed method can increase diagnostic accuracy using data from a lymphoma cancer diagnosis study.ConclusionsThe presented method adjusts for signal saturation at the segmentation stage that identifies a pixel as part of the foreground, background or other. The cluster membership of a pixel can be altered versus treating saturated values as truly observed. Thus, the resulting spot intensity estimates may be more accurate than those obtained from existing methods that correct for saturation based on already segmented data. As a model-based segmentation method, our procedure is able to identify inner holes, fuzzy edges and blank spots that are common in microarray images. The approach is independent of microarray platform and applicable to both single- and dual-channel microarrays.

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.

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.

In this paper a novel procedure based on texture spatial characterization techniques is proposed aimed at automatically addressing spots in microarray images. The algorithm relies on the regular and pseudo-periodic patterns of spots, which can be considered as texture primitives. A fully automatic procedure is proposed to segment the autocorrelation functions of subgrid images and accurately determine the locations of the peaks. These candidate peaks, i.e., vectors, are next used to compute the displacement vectors that fully characterize the spatial arrangement of spots, describing the spot spacing and angle of rotation of the pattern. A refinement procedure is then applied to improve the accuracy of the norms and angles of the displacement vectors. An ideal template is generated using the computed spanning vectors, which is deformed and adjusted via Markov Random Fields (MRF) modelling. Experiments based on artificial and real images are promising, showing improvements regarding robustness against image rotations, and accuracy, over results provided by state-ofthe-art methods.

Lots of error sources affect the microarray image quality, especially the noise. An image may contain different type noises which will produce distinct influence on image processing, so it doesnpsilat need to remove all. This paper analyzed the affection of different noises to automatic gridding and proposed grid line number for quantitive evaluation. A new algorithm for noise reduction was developed, which included two parts: edge noise reduction and highly fluorescence noise reduction. Edge detection was executed on the vertical and horizontal projections of microarray image. Highly fluorescent noise was removed by linear replace, which is an easy and fast means. The algorithm was implemented and compared to other common noise reduction methods. Experiment results show the feasibility of the proposed approach.

Many different programs are available to analyze microarray images. Most programs are commercial packages, some are free. In the latter group only few propose automatic grid alignment and batch mode. More often than not a program implements only one quantification algorithm. AGScan is an open source program that works on all major platforms. It is based on the ImageJ library [Rasband (1997-2006)] and offers a plug-in extension system to add new functions to manipulate images, align grid and quantify spots. It is appropriate for daily laboratory use and also as a framework for new algorithms. The program is freely distributed under X11 Licence. The install instructions can be found in the user manual. The software can be downloaded from http://mulcyber.toulouse.inra.fr/projects/agscan/. The questions and plug-ins can be sent to the contact listed below.

cDNA microarrays are a useful tool for studying the expression levels of genes. Nevertheless, microarray image gridding remains a challenging and complex task. Most of the microarray image analysis tools require human intervention, leading to variations of the gene expression results. Automatic methods have also been proposed, but present high computational complexity. In this work, the performance enhancement via GPU computing techniques of a fully automatic gridding method, previously proposed by the authors' research group, is presented. The NVIDIA CUDA architecture was utilized in order to achieve parallel computation of complex steps of the algorithm. Experimental results showed that the proposed approach provides enhanced performance in terms of computational time, while achieving higher utilization of the available computational resources.

A new block-based multi-metric fusion (BMMF) approach is proposed for perceptual image quality assessment. The proposed BMMF scheme automatically detects image content and distortion types in a block via machine learning, which is motivated by the observation that the performance of an image quality metric is highly influenced by these factors. Locally, image block content is classified into three types; namely, smooth, edge and texture. Image distortion is detected and grouped into five types. An appropriate image quality metric is adopted for each block by considering its content and distortion types, and then all block-based quality metrics are fused to result in one final score. Furthermore, a corrected version of BMMF is derived for a specific group of distortions based on image complexity analysis. The proposed BMMF scheme is tested on TID database with its Spearman Correlation equal to 0.9471, which outperforms today's state-of-the-art image quality metrics.

Many approaches have been proposed in the literature to enhance the robustness of Convolutional Neural Network (CNN)-based architectures against image distortions. Attempts to combat various types of distortions can be made by combining multiple expert networks, each trained by a certain type of distorted images, which however lead to a large model with high complexity. In this paper, we propose a CNN-based architecture with a pre-processing unit in which only undistorted data are used for training. The pre-processing unit employs discrete cosine transform (DCT) and discrete wavelets transform (DWT) to remove high-frequency components while capturing prominent high-frequency features in the undistorted data by means of random selection. We further utilize the singular value decomposition (SVD) to extract features before feeding the preprocessed data into the CNN for training. During testing, distorted images directly enter the CNN for classification without having to go through the hybrid module. Five different types of distortions are produced in the SVHN dataset and the CIFAR-10/100 datasets. Experimental results show that the proposed DCT-DWT-SVD module built upon the CNN architecture provides a classifier robust to input image distortions, outperforming the state-of-the-art approaches in terms of accuracy under different types of distortions.

Digital watermarking for camera-captured images based on just noticeable distortion and Wiener filtering

The problem of axial rotations in reading was investigated by the use of the Lamb Chop Test. Comparisons of reading readiness scores, levels of reading achievement, and scores on the Lamb Chop Test for first and third grade Ss indicate significant association between these factors and incidence of rotational errors. Frequency of rotational errors was not found to be greater among left-handed than among right-handed Ss. Analysis of types of rotational errors showed a decrease in both vertical and depth rotations when data for first and third grade samples were compared. The persistence of horizontal rotations among poorer readers in the third grade suggests that (1) the hitherto predominant emphasis upon vertical (Left-Right) rotations may have been misplaced and (2) consideration of all types of axial rotations, rather than any single one, is necessary in the diagnosis of reading disability.

Resistance to optical distortions in three-dimensional interferometric temporal focusing microscopy