A wavelet-based modification of the Markov random field (WMRF) model is proposed for segmenting complementary DNA (cDNA) microarray images. For evaluation purposes, five simulated and a set of five real microarray images were used. The one-level stationary wavelet transform (SWT) of each microarray image was used to form two images, a denoised image, using hard thresholding filter, and a magnitude image, from the amplitudes of the horizontal and vertical components of SWT. Elements from these two images were suitably combined to form the WMRF model for segmenting spots from their background. The WMRF was compared against the conventional MRF and the Fuzzy C means (FCM) algorithms on simulated and real microarray images and their performances were evaluated by means of the segmentation matching factor (SMF) and the coefficient of determination (r2). Additionally, the WMRF was compared against the SPOT and SCANALYZE, and performances were evaluated by the mean absolute error (MAE) and the coefficient of variation (CV). The WMRF performed more accurately than the MRF and FCM (SMF: 92.66, 92.15, and 89.22, r2 : 0.92, 0.90, and 0.84, respectively) and achieved higher reproducibility than the MRF, SPOT, and SCANALYZE (MAE: 497, 1215, 1180, and 503, CV: 0.88, 1.15, 0.93, and 0.90, respectively).

The objective of this paper was to investigate the segmentation ability of the fuzzy Gaussian mixture model (FGMM) clustering algorithm, applied on complementary DNA (cDNA) images. Following a standard established procedure, a simulated microarray image of 1600 cells, each containing one spot, was produced. For further evaluation of the algorithm, three real microarray images were also used, each containing 6400 spots. For the task of locating spot borders and surrounding background (BG) in each cell, an automatic gridding process was developed and applied on microarray images. The FGMM and the Gaussian mixture model (GMM) algorithms were applied to each cell with the purpose of discriminating foreground (FG) from BG. The segmentation abilities of both algorithms were evaluated by means of the segmentation matching factor, coefficient of determination, and concordance correlation, in respect to the actual classes (FG-BG pixels) of the simulated spots. Pairwise correlation and mean absolute error of the real images among replicates were also calculated. The FGMM was found to perform better and with equal processing time, as compared to the GMM, rendering the FGMM algorithm an efficient alternative for segmenting cDNA microarray images.

BACKGROUND: The integration of biomedical information is essential for tackling medical problems. We describe a data model in the domain of flow cytometry (FC) allowing for massive management, analysis and integration with other laboratory and clinical information. The paper is concerned with the proper translation of the Flow Cytometry Standard (FCS) into a relational database schema, in a way that facilitates end users at either doing research on FC or studying specific cases of patients undergone FC analysis RESULTS: The proposed database schema provides integration of data originating from diverse acquisition settings, organized in a way that allows syntactically simple queries that provide results significantly faster than the conventional implementations of the FCS standard. The proposed schema can potentially achieve up to 8 orders of magnitude reduction in query complexity and up to 2 orders of magnitude reduction in response time for data originating from flow cytometers that record 256 colours. This is mainly achieved by managing to maintain an almost constant number of data-mining procedures regardless of the size and complexity of the stored information. CONCLUSION: It is evident that using single-file data storage standards for the design of databases without any structural transformations significantly limits the flexibility of databases. Analysis of the requirements of a specific domain for integration and massive data processing can provide the necessary schema modifications that will unlock the additional functionality of a relational database.

Proteomic analysis using mass spectrometry data is a powerful tool for biomarker discovery. However, proteomic data suffers from two crucial problems i/ are inherently very noisy and ii/ the number of features that finally characterize each spectrum is usually very large. In the present study, a well-established framework of data preprocessing steps was developed to deal with the problem of noise, incorporating smoothing, normalization, peak detection, and peak alignment algorithms. In addition, to alleviate the problem of feature dimensionality, a novel iterative peak selection method was developed for choosing peaks (features) from the pre- processed spectra, based on sequential global thresholding followed by particle swarm optimization. These features were fed into a probabilistic neural network algorithm, in order to discriminate healthy from prostate cancer cases and, thus, to determine, through the algorithm's optimal design, biomarkers related to prostate cancer.

MOTIVATION: One of the major factors that complicate the task of microarray image analysis is that microarray images are distorted by various types of noise. In this study a robust framework is proposed, designed to take into account the effect of noise in microarray images in order to assist the demanding task of microarray image analysis. The proposed framework, incorporates in the microarray image processing pipeline a novel combination of spot adjustable image analysis and processing techniques and consists of the following stages: (1) gridding for facilitating spot identification, (2) clustering (unsupervised discrimination between spot and background pixels) applied to spot image for automatic local noise assessment, (3) modeling of local image restoration process for spot image conditioning (adjustable wiener restoration using an empirically determined degradation function), (4) automatic spot segmentation employing seeded-region-growing, (5) intensity extraction and (6) assessment of the reproducibility (real data) and the validity (simulated data) of the extracted gene expression levels. RESULTS: Both simulated and real microarray images were employed in order to assess the performance of the proposed framework against well-established methods implemented in publicly available software packages (Scanalyze and SPOT). Regarding simulated images, the novel combination of techniques, introduced in the proposed framework, rendered the detection of spot areas and the extraction of spot intensities more accurate. Furthermore, on real images the proposed framework proved of better stability across replicates. Results indicate that the proposed framework improves spots' segmentation and, consequently, quantification of gene expression levels. AVAILABILITY: All algorithms were implemented in Matlab (The Mathworks, Inc., Natick, MA, USA) environment. The codes that implement microarray gridding, adaptive spot restoration and segmentation/intensity extraction are available upon request. Supplementary results and the simulated microarray images used in this study are available for download from: ftp://users:[email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Collaboration is a key requirement in several contemporary interventional radiology procedures (IRPs). This work proposes a multicast hybrid satellite system capable of supporting advanced IRP collaboration, and evaluates its feasibility and applicability. Following a detailed IRP requirements study, we have developed a system which supports IRP collaboration through the employment of a hybrid satellite-terrestrial network, a prototype multicast version of wavelet based interactive communication system (WinVicos) application, and a partition aggregation and conditional coding (PACC) wavelet codec. A semistructured questionnaire was also used to receive evaluative feedback from collaborating participants. The departments of interventional radiology of University Hospital of Patras, Greece and of Charite Hospital of Berlin, Germany have been connected on the system. Eight interventional radiologists and a vascular surgeon participated periodically in three satellite-terrestrial "fully collaborative" IRPs (average time 90 min) of high complexity and in four terrestrial educational sessions with great success, evidenced by considerable improving the IRP outcomes (clinical and educational). In case of high complexity, where the simultaneous presence of remote interventional expert and/or surgeon is required, advanced collaboration among staff of geographically dispersed international centers is feasible via integration of existing networking and other technologies.

In this paper, we will introduce a novel system where identical miniaturized robotic agents with limited capabilities will collaborate to form a team that is capable of localizing and repairing scale formations in tanks and pipes within inaccessible fluidic environments. Each robotic agent is an autonomous entity that is based on the biologically inspired spiking neural networks (SNNs) that communicate using pulses or spikes. The weights of the SNN are evolved using adaptive genetic algorithm (GA) that uses adaptive crossover and mutation to converge relatively fast to solutions that allow the robots to complete the desired tasks. The robotic agents communicate using indirect communication to move towards the site of scale formation and collaborate to repair damages.

Networks of spiking neurons can perform complex non-linear computations in fast temporal coding just as well as rate coded networks. These networks differ from previous models in that spiking neurons communicate information by the timing, rather than the rate, of spikes. To apply spiking neural networks on particular tasks, a learning process is required. Most existing training algorithms are based on unsupervised Hebbian learning. In this paper, we investigate the performance of the parallel differential evolution algorithm, as a supervised training algorithm for spiking neural networks. The approach was successfully tested on well-known and widely used classification problems.

A computer-aided diagnosis system was developed for assisting brain astrocytomas malignancy grading. Microscopy images from 140 astrocytic biopsies were digitized and cell nuclei were automatically segmented using a Probabilistic Neural Network pixel-based clustering algorithm. A decision tree classification scheme was constructed to discriminate low, intermediate and high-grade tumours by analyzing nuclear features extracted from segmented nuclei with a Support Vector Machine classifier. Nuclei were segmented with an average accuracy of 86.5%. Low, intermediate, and high-grade tumours were identified with 95%, 88.3%, and 91% accuracies respectively. The proposed algorithm could be used as a second opinion tool for the histopathologists.

This work contains the results of an initial study into the FPGA implementation of a spiking neural network. This work was undertaken as a task in a project that aims to design and develop a new kind of tangible collaborative autonomous agent. The project intends to exploit/investigate methods for engineering emergent collective behaviour in large societies of actual miniature agents that can learn and evolve. Such multi-agent systems could be used to detect and collectively repair faults in a variety of applications where it is difficult for humans to gain access, such as fluidic environments found in critical components of material/industrial systems. The initial achievement of implementation of a spiking neural network on a FPGA hardware platform and results of a robotic wall following task are discussed by comparison with software driven robots and simulations.

The performance of three classifiers is evaluated in an attempt to achieve a more objective grading of urinary bladder tumors. 95 cases were classified according to the World Health Organization (WHO) grading system by pathologists in three classes: grade I, grade II, and grade III. Each case was represented by 36 nuclear features. The minimum distance, the least mean square, and the Bayes classifier were implemented in a two stage hierarchical tree. The classification accuracy of each hierarchical tree was also tested in relation to direct tumor grading. The Bayes classifier provided the best overall system accuracy of 74.5%, employing a four-feature vector and the leave one out method. Grade I and grade III tumors were recognized as two distinct entities, whereas tumors of grade II, were poorly discriminated from tumors of grade I and II. Nuclear features could be of value in a more objective grading of urine bladder cancer.