Analysis Of Microarray Images Research Articles

Incorporating Deep Features in the Analysis of Tissue Microarray Images.

Tissue microarray (TMA) images have been used increasingly often in cancer studies and the validation of biomarkers. TACOMA-a cutting-edge automatic scoring algorithm for TMA images-is comparable to pathologists in terms of accuracy and repeatability. Here we consider how this algorithm may be further improved. Inspired by the recent success of deep learning, we propose to incorporate representations learnable through computation. We explore representations of a group nature through unsupervised learning, e.g., hierarchical clustering and recursive space partition. Information carried by clustering or spatial partitioning may be more concrete than the labels when the data are heterogeneous, or could help when the labels are noisy. The use of such information could be viewed as regularization in model fitting. It is motivated by major challenges in TMA image scoring-heterogeneity and label noise, and the cluster assumption in semi-supervised learning. Using this information on TMA images of breast cancer, we have reduced the error rate of TACOMA by about 6%. Further simulations on synthetic data provide insights on when such representations would likely help. Although we focus on TMAs, learnable representations of this type are expected to be applicable in other settings.

Fast and inexpensive self-made tissue microarray for immunohistochemical and in situ hybridization studies: examples with bladder cancer

Background: The tissue microarray (TMA), first described by Battifora and first implemented in 1998 by Kononen et al, is a powerful research tool, allowing simultaneous analysis of specimens from a large number of cases on one slide by routine slides. Unfortunately, commercial aray instruments are very expensive and thus not suitable for laboratories with limited funds. We describe simple and cost-effective method for constructing of manual TMA that can be performed by any anatomic pathology laboratory, requiring minimum skill and time.Methods: Skin punch biopsy needle of 2-mm diameter was used for extracting cores from 15 positive control breast cancer cases, 15 normal bladder tissue and 30 muscle-invasive bladder cancer and for injecting into recipient block.Result: : We constructed TMA block using skin punch biopsy needle of 2-mm, and succesfulfully performed HER 2 immunodetection and Chromogen in situ hybridization studies, without substantial tissue loss. 10% of our tumor cases exhibited Her-2 neu overexpression. An open source software programme “ТМА-Ј“ was applied to facilitate management, viewing, analysis of tissue microarray images and associated clinico-pathology data.Conclusion: : This method could be done by any pathology laboratory and represents good and reliable alternative for commercially available, expensive devices and software solutions.DOI: 10.21276/apalm.2017.1166

MIGS-GPU: Microarray Image Gridding and Segmentation on the GPU.

Complementary DNA (cDNA) microarray is a powerful tool for simultaneously studying the expression level of thousands of genes. Nevertheless, the analysis of microarray images remains an arduous and challenging task due to the poor quality of the images that often suffer from noise, artifacts, and uneven background. In this study, the MIGS-GPU [Microarray Image Gridding and Segmentation on Graphics Processing Unit (GPU)] software for gridding and segmenting microarray images is presented. MIGS-GPU's computations are performed on the GPU by means of the compute unified device architecture (CUDA) in order to achieve fast performance and increase the utilization of available system resources. Evaluation on both real and synthetic cDNA microarray images showed that MIGS-GPU provides better performance than state-of-the-art alternatives, while the proposed GPU implementation achieves significantly lower computational times compared to the respective CPU approaches. Consequently, MIGS-GPU can be an advantageous and useful tool for biomedical laboratories, offering a user-friendly interface that requires minimum input in order to run.

Unsupervised image segmentation for microarray spots with irregular contours and inner holes

BackgroundMicroarray analysis represents a powerful way to test scientific hypotheses on the functionality of cells. The measurements consider the whole genome, and the large number of generated data requires sophisticated analysis. To date, no gold-standard for the analysis of microarray images has been established. Due to the lack of a standard approach there is a strong need to identify new processing algorithms.MethodsWe propose a novel approach based on hyperbolic partial differential equations (PDEs) for unsupervised spot segmentation. Prior to segmentation, morphological operations were applied for the identification of co-localized groups of spots. A grid alignment was performed to determine the borderlines between rows and columns of spots. PDEs were applied to detect the inflection points within each column and row; vertical and horizontal luminance profiles were evolved respectively. The inflection points of the profiles determined borderlines that confined a spot within adapted rectangular areas. A subsequent k-means clustering determined the pixels of each individual spot and its local background.ResultsWe evaluated the approach for a data set of microarray images taken from the Stanford Microarray Database (SMD). The data set is based on two studies on global gene expression profiles of Arabidopsis Thaliana. We computed values for spot intensity, regression ratio, and coefficient of determination. For spots with irregular contours and inner holes, we found intensity values that were significantly different from those determined by the GenePix Pro microarray analysis software. We determined the set of differentially expressed genes from our intensities and identified more activated genes than were predicted by the GenePix software.ConclusionsOur method represents a worthwhile alternative and complement to standard approaches used in industry and academy. We highlight the importance of our spot segmentation approach, which identified supplementary important genes, to better explains the molecular mechanisms that are activated in a defense responses to virus and pathogen infection.

Abstract 303: Cell Slider: Using crowd sourcing for the scoring of molecular pathology

Abstract The advent of tumour microarrays has increased the throughput of pathology sample preparation but has led to a new bottleneck at the analysis stage as many thousands of samples need to be scored by an expert pathologist. We launched Cell Slider (www.clicktocure.net), the world's first Citizen Science project in cancer research, in Autumn 2012. Cell SliderTM aims to speed up the analysis of tumour microarray images through crowd sourcing. Citizen Scientists have now generated over 1.7 million scores of tumour images from the Breast Cancer Association Consortium image database. In order to evaluate the validity of Citizen Scientist scoring we compared the scores of Citizen Scientists with those of an experienced pathologist for 2,575 tissue cores from the SEARCH study that have been stained for expression of the estrogen receptor. Each image of a 0.6mm tissue core stained for ER was divided into 12 sub-images, each of which was scored by five citizen scientists. A weighted average of the 60 (12x5) scores was used to generate a single citizen scientist score for each tissue core. The average number of cancer cells observed by Citizen Scientists was used to indicate whether or not the core contained cancer. The sensitivity and specificity then depends on the threshold used for positivity. Of 2,575 cores on the TMA the pathologist identified 1,792 as having cancer tissue. The kappa statistic for agreement between pathologist and Citizen Scientist was 0.72. Using a threshold to give a sensitivity of 95 per cent, the specificity was 72 per cent. We estimated the accuracy of assignment of tumour ER status using the 1,703 cores where both pathologist and Citizen Scientists identified cancer in the TMA core. A pseudo-Allred score on a continuous scale was calculated from the individual Citizen Scientist scores for the proportion of positively stained cells and the intensity of positively stained cells. The sensitivity and specificity of ER status depends on the threshold pseudo-Allred score used to determine ER positivity. The kappa statistic for agreement between pathologist and Citizen Scientist was 0.84. Using a threshold to give a sensitivity of 95 per cent, the specificity was 90 per cent. We have shown that crowd sourcing can be used to score breast cancer TMAs stained by immunohistochemistry with a reasonable degree of accuracy. Further analysis are underway to determine whether accuracy can be improved using difference weighting schemes and to evaluate the accuracy of scoring of typical cytoplasmic and membrane molecular markers. Citation Format: Paul D. Pharoah. Cell Slider: Using crowd sourcing for the scoring of molecular pathology. [abstract]. In: Proceedings of the 105th Annual Meeting of the American Association for Cancer Research; 2014 Apr 5-9; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2014;74(19 Suppl):Abstract nr 303. doi:10.1158/1538-7445.AM2014-303

Noise Removal using Empirical Mode Decomposition and Wavelet Transform in Microarray Images

A Deoxyribonucleic Acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as glass, plastic or silicon chip forming an array. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. The DNA microarray image analysis includes three tasks: gridding, segmentation and intensity extraction. In this paper, a method for noise removal in microarray image using Bidimensional Empirical Mode Decomposition (BEMD) is presented. The BEMD decomposes the image into IMFs and residual components. Then, the selected high frequency IMFs are de-noised with wavelet model and finally the BEMD reconstruction gives the de-noised image. The experimental results show the proposed algorithm can perform significantly better in terms of noise suppression and detail preservation in microarray images.

Spot Edge Detection in Microarray Images Using Bi-Dimensional Empirical Mode Decomposition

A Deoxyribonucleic Acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as glass, plastic or silicon chip forming an array. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. The DNA microarray image analysis includes three tasks: gridding, segmentation and intensity extraction. During the processing of microarray images, the irregularities of spot position and shape could generate significant errors. This paper presents an edge detection method using Bi-dimensional Empirical Mode Decomposition. Application of edge detection technology on separating spots form the background decreases the probability of errors and gives more accurate information about the states of spots. The proposed method identifies the spots with low density, thus increasing the performance of microarray images.

Microarray core detection by geometric restoration.

Whole-slide imaging of tissue microarrays (TMAs) holds the promise of automated image analysis of a large number of histopathological samples from a single slide. This demands high-throughput image processing to enable analysis of these tissue samples for diagnosis of cancer and other conditions. In this paper, we present a completely automated method for the accurate detection and localization of tissue cores that is based on geometric restoration of the core shapes without placing any assumptions on grid geometry. The method relies on hierarchical clustering in conjunction with the Davies-Bouldin index for cluster validation in order to estimate the number of cores in the image wherefrom we estimate the core radius and refine this estimate using morphological granulometry. The final stage of the algorithm reconstructs circular discs from core sections such that these discs cover the entire region of each core regardless of the precise shape of the core. The results show that the proposed method is able to reconstruct core locations without any evidence of localization. Furthermore, the algorithm is more efficient than existing methods based on the Hough transform for circle detection. The algorithm’s simplicity, accuracy, and computational efficiency allow for automated high-throughput analysis of microarray images.

Microarray Core Detection by Geometric Restoration

Whole-slide imaging of tissue microarrays (TMAs) holds the promise of automated image analysis of a large number of histopathological samples from a single slide. This demands high-throughput image processing to enable analysis of these tissue samples for diagnosis of cancer and other conditions. In this paper, we present a completely automated method for the accurate detection and localization of tissue cores that is based on geometric restoration of the core shapes without placing any assumptions on grid geometry. The method relies on hierarchical clustering in conjunction with the Davies-Bouldin index for cluster validation in order to estimate the number of cores in the image wherefrom we estimate the core radius and refine this estimate using morphological granulometry. The final stage of the algorithm reconstructs circular discs from core sections such that these discs cover the entire region of each core regardless of the precise shape of the core. The results show that the proposed method is able to reconstruct core locations without any evidence of localization. Furthermore, the algorithm is more efficient than existing methods based on the Hough transform for circle detection. The algorithm’s simplicity, accuracy, and computational efficiency allow for automated high-throughput analysis of microarray images.

Microarray Analysis at Single-Molecule Resolution

Bioanalytical chip-based assays have been enormously improved in sensitivity in the recent years; detection of trace amounts of substances down to the level of individual fluorescent molecules has become state-of-the-art technology. The impact of such detection methods, however, has yet not fully been exploited, mainly due to a lack of appropriate mathematical tools for robust data analysis. One particular example relates to the analysis of microarray data. While classical microarray analysis works at resolutions of 2-20 microm and quantifies the abundance of target molecules by determining average pixel intensities, a novel high-resolution approach directly visualizes individual bound molecules as diffraction-limited peaks. The now possible quantification via counting is less susceptible to labeling artifacts and background noise. We have developed an approach for the analysis of high-resolution microarray images. First, it consists of a single-molecule detection step, based on undecimated wavelet transforms, and second, a spot identification step via spatial statistics approach (corresponding to the segmentation step in the classical microarray analysis). The detection method was tested on simulated images with a concentration range of 0.001 to 0.5 molecules per square micrometer and signal-to-noise ratio (SNR) between 0.9 and 31.6. For SNR above 15, the false negatives relative error was below 15%. Separation of foreground/background is proved reliable, in case foreground density exceeds background by a factor of 2. The method has also been applied to real data from high-resolution microarray measurements.

A soft multi-core architecture for edge detection and data analysis of microarray images

As configurable processing advances, elements from the traditional approaches of both hardware and software development can be combined by incorporating customized, application-specific computational resources into the processor's architecture, especially in the case of field-programmable-gate-array-based systems with soft-processors, so as to enhance the performance of embedded applications. This paper explores the use of several different microarchitectural alternatives to increase the performance of edge detection algorithms, which are of fundamental importance for the analysis of DNA microarray images. Optimized application-specific hardware modules are combined with efficient parallelized software in an embedded soft-core-based multi-processor. It is demonstrated that the performance of one common edge detection algorithm, namely Sobel, can be boosted remarkably. By exploiting the architectural extensions offered by the soft-processor, in conjunction with the execution of carefully selected application-specific instruction-set extensions on a custom-made accelerating co-processor connected to the processor core, we introduce a new approach that makes this methodology noticeably more efficient across various applications from the same domain, which are often similar in structure. With flexibility to update the processing algorithms, an improvement reaching one order of magnitude over all-software solutions could be obtained. In support of this flexibility, an effective adaptation of this approach is demonstrated which performs real-time analysis of extracted microarray data; the proposed reconfigurable multi-core prototype has been exploited with minor changes to achieve almost 5x speedup.

A Novel Dual-Core Architecture for the Analysis of DNA Microarray Images

A deoxyribonucleic acid (DNA) microarray is a collection of microscopic DNA spots attached to a solid surface, such as a glass, plastic, or silicon chip forming an array. DNA microarray technologies are an essential part of modern biomedical research. DNA microarray allows compressing hundreds of thousands of different DNA nucleotide sequences in a little microscope glass and permits having all this information on a single image. The analysis of DNA microarray images allows the identification of gene expressions to draw biological conclusions for applications ranging from genetic profiling to diagnosis of cancer. Unfortunately, DNA microarray technology has a high variation of data quality. Therefore, to obtain reliable results, complex and extensive image analysis algorithms should be applied before the actual DNA microarray information can be used for biomedical purposes. In this paper, we present a novel hardware architecture that is specifically designed to analyze DNA microarray images. The architecture is based on a dual-core system that implements several units working in a single-instruction/multiple-data fashion. A field-programmable-gate-array (FPGA)-based prototypal implementation of the proposed architecture is presented. The effectiveness of the novel dual-core architecture is demonstrated by several analyses performed on original DNA microarray images, showing that the capability of detecting DNA spots increases by more than the 30% with respect to that of previously developed software techniques.

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

Microarrays are widely used to quantify gene expression levels. Microarray image analysis is one of the tools, which are necessary when dealing with vast amounts of biological data. In this work we propose a new method for the automated analysis of microarray images. The proposed method consists of two stages: gridding and segmentation. Initially, the microarray images are preprocessed using template matching, and block and spot finding takes place. Then, the non-expressed spots are detected and a grid is fit on the image using a Voronoi diagram. In the segmentation stage, K-means and Fuzzy C means (FCM) clustering are employed. The proposed method was evaluated using images from the Stanford Microarray Database (SMD). The results that are presented in the segmentation stage show the efficiency of our Fuzzy C means-based work compared to the two already developed K-means-based methods. The proposed method can handle images with artefacts and it is fully automated.

Hadamard matrix methods in identifying differentially expressed genes from microarray experiments

Identifying differentially expressed genes is a basic objective in microarray experiments. Many statistical methods for detecting differentially expressed genes in multiple-slide experiments have been proposed. However, sometimes with limited experimental resources, only a single cDNA array or two Oligonuleotide arrays could be made or only insufficient replicated arrays could be conducted. Many current statistical models cannot be used because of the non-availability of replicated data. Simply using fold changes is also unreliable and inefficient [Chen et al. 1997. Ratio-based decisions and the quantitative analysis of cDNA microarray images. J. Biomed. Optics 2, 364–374; Newton et al. 2001. On differential variability of expression ratios: improving statistical inference about gene expression changes from microarray data. J. Comput. Biol. 8, 37–52; Pan et al. 2002. How many replicates of arrays are required to detect gene expression changes in microarray experiments? a mixture model approach. Genome Biol. 3, research0022.1-0022.10]. We propose a new method. If the log-transformed ratios for the expressed genes as well as unexpressed genes have equal variance, we use a Hadamard matrix to construct a t-test from a single array data. Basically, we test whether each doubtful gene has significantly differential expression compared to the unexpressed genes. We form some new random variables corresponding to the rows of a Hadamard matrix using the algebraic sum of gene expressions. A one-sample t-test is constructed and the p-value is calculated for each doubtful gene based on these random variables. By using any method for multiple testing, adjusted p-values could be obtained from original p-values and significance of doubtful genes can be determined. When the variance of expressed genes differs from the variance of unexpressed genes, we construct a z-statistic based on the result from application of Hadamard matrix and find the confidence interval to retain the null hypothesis. Using the interval, we determine differentially expressed genes. This method is also useful for multiple microarrays, especially when sufficient replicated data are not available for a traditional t-test. We apply our methodology to ApoAI data. The results appear to be promising. They not only confirm the early known differentially expressed genes, but also indicate more genes to be differentially expressed.

Mixture model analysis of DNA microarray images

In this paper, we propose a new methodology for analysis of microarray images. First, a new gridding algorithm is proposed for determining the individual spots and their borders. Then, a Gaussian mixture model (GMM) approach is presented for the analysis of the individual spot images. The main advantages of the proposed methodology are modeling flexibility and adaptability to the data, which are well-known strengths of GMM. The maximum likelihood and maximum a posteriori approaches are used to estimate the GMM parameters via the expectation maximization algorithm. The proposed approach has the ability to detect and compensate for artifacts that might occur in microarray images. This is accomplished by a model-based criterion that selects the number of the mixture components. We present numerical experiments with artificial and real data where we compare the proposed approach with previous ones and existing software tools for microarray image analysis and demonstrate its advantages.

A dynamical model with adaptive pixel moving for microarray images segmentation

Gene expression analysis is one of the main research issues in computational biology. Such analysis can provide very relevant information related to cell activity. Several techniques have been employed for this analysis. One of them is the analysis of microarray images. This paper proposes a new data clustering method based on dynamical system modelling for the segmentation of microarray images. The proposed approach employs a network consisting of interacting elements, where each element represents an input data as an attribute vector. Each element of the network receives attractions from other elements within a certain region. Those attractions, determined by a predefined similarity measure, drive the elements to converge to their corresponding cluster centre. With this model, neither the number of pixel clusters nor the initial guessing of cluster centres is required. Moreover, the proposed model allows the omission of the gridding process. The results obtained so far have been very promising.

Microarray BASICA: Background Adjustment, Segmentation, Image Compression and Analysis of Microarray Images

This paper presents microarray BASICA: an integrated image processing tool for background adjustment, segmentation, image compression, and analysis of cDNA microarray images. BASICA uses a fast Mann-Whitney test-based algorithm to segment cDNA microarray images and performs postprocessing to eliminate the segmentation irregularities. The segmentation results, along with the foreground and background intensities obtained with the background adjustment, are then used for independent compression of the foreground and background. We introduce a new distortion measurement for cDNA microarray image compression and devise a coding scheme by modifying the embedded block coding with optimized truncation (EBCOT) algorithm (Taubman, 2000) to achieve optimal rate-distortion performance in lossy coding while still maintaining outstanding lossless compression performance. Experimental results show that the bit rate required to ensure sufficiently accurate gene expression measurement varies and depends on the quality of cDNA microarray images. For homogeneously hybridized cDNA microarray images, BASICA is able to provide from a bit rate as low as 5 bpp the gene expression data that are 99% in agreement with those of the original 32 bpp images.

Ratio-based decisions and the quantitative analysis of cDNA microarray images

Gene expression can be quantitatively analyzed by hybridizing fluor-tagged mRNA to targets on a cDNA microarray. Comparison of gene expression levels arising from cohybridized samples is achieved by taking ratios of average expression levels for individual genes. A novel method of image segmentation is provided to identify cDNA target sites and a hypothesis test and confidence interval is developed to quantify the significance of observed differences in expression ratios. In particular, the probability density of the ratio and the maximum-likelihood estimator for the distribution are derived, and an iterative procedure for signal calibration is developed.

Ratio-based decisions and the quantitative analysis of cDNA microarray images

Ratio-based decisions and the quantitative analysis of cDNA microarray images