Improved and Robust Detection of Cell Nuclei from Four Dimensional Fluorescence Images

Segmentation-free direct methods are quite efficient for automated nuclei extraction from high dimensional images. A few such methods do exist but most of them do not ensure algorithmic robustness to parameter and noise variations. In this research, we propose a method based on multiscale adaptive filtering for efficient and robust detection of nuclei centroids from four dimensional (4D) fluorescence images. A temporal feedback mechanism is employed between the enhancement and the initial detection steps of a typical direct method. We estimate the minimum and maximum nuclei diameters from the previous frame and feed back them as filter lengths for multiscale enhancement of the current frame. A radial intensity-gradient function is optimized at positions of initial centroids to estimate all nuclei diameters. This procedure continues for processing subsequent images in the sequence. Above mechanism thus ensures proper enhancement by automated estimation of major parameters. This brings robustness and safeguards the system against additive noises and effects from wrong parameters. Later, the method and its single-scale variant are simplified for further reduction of parameters. The proposed method is then extended for nuclei volume segmentation. The same optimization technique is applied to final centroid positions of the enhanced image and the estimated diameters are projected onto the binary candidate regions to segment nuclei volumes.Our method is finally integrated with a simple sequential tracking approach to establish nuclear trajectories in the 4D space. Experimental evaluations with five image-sequences (each having 271 3D sequential images) corresponding to five different mouse embryos show promising performances of our methods in terms of nuclear detection, segmentation, and tracking. A detail analysis with a sub-sequence of 101 3D images from an embryo reveals that the proposed method can improve the nuclei detection accuracy by 9 over the previous methods, which used inappropriate large valued parameters. Results also confirm that the proposed method and its variants achieve high detection accuracies ( 98 mean F-measure) irrespective of the large variations of filter parameters and noise levels.     

A cascaded approach to normalising gene mentions in biomedical literature

Linking gene and protein names mentioned in the literature to unique identifiers in referent genomic databases is an essential step in accessing and integrating knowledge in the biomedical domain. However, it remains a challenging task due to lexical and terminological variation, and ambiguity of gene name mentions in documents. We present a generic and effective rule-based approach to link gene mentions in the literature to referent genomic databases, where pre-processing of both gene synonyms in the databases and gene mentions in text are first applied. The mapping method employs a cascaded approach, which combines exact, exact-like and token-based approximate matching by using flexible representations of a gene synonym dictionary and gene mentions generated during the pre-processing phase. We also consider multi-gene name mentions and permutation of components in gene names. A systematic evaluation of the suggested methods has identified steps that are beneficial for improving either precision or recall in gene name identification. The results of the experiments on the BioCreAtIvE2 data sets (identification of human gene names) demonstrated that our methods achieved highly encouraging results with F-measure of up to 81.20%.     

Automatic image segmentation of nuclear stained breast tissue sections using color active contour model and an improved watershed method

Automatic image segmentation of immunohistologically stained breast tissue sections helps pathologists to discover the cancer disease earlier. The detection of the real number of cancer nuclei in the image is a very tedious and time consuming task. Segmentation of cancer nuclei, especially touching nuclei, presents many difficulties to separate them by traditional segmentation algorithms. This paper presents a new automatic scheme to perform both classification of breast stained nuclei and segmentation of touching nuclei in order to get the total number of cancer nuclei in each class. Firstly, a modified geometric active contour model is used for multiple contour detection of positive and negative nuclear staining in the microscopic image. Secondly, a touching nuclei method based on watershed algorithm and concave vertex graph is proposed to perform accurate quantification of the different stains. Finally, benign nuclei are identified by their morphological features and they are removed automatically from the segmented image for positive cancer nuclei assessment. The proposed classification and segmentation schemes are tested on two datasets of breast cancer cell images containing different level of malignancy. The experimental results show the superiority of the proposed methods when compared with other existing classification and segmentation methods. On the complete image database, the segmentation accuracy in term of cancer nuclei number is over than 97%, reaching an improvement of 3–4% over earlier methods.     

Augmented transitive relationships with high impact protein distillation in protein interaction prediction

Predicting new protein-protein interactions is important for discovering novel functions of various biological pathways. Predicting these interactions is a crucial and challenging task. Moreover, discovering new protein-protein interactions through biological experiments is still difficult. Therefore, it is increasingly important to discover new protein interactions. Many studies have predicted protein-protein interactions, using biological features such as Gene Ontology (GO) functional annotations and structural domains of two proteins. In this paper, we propose an augmented transitive relationships predictor (ATRP), a new method of predicting potential protein interactions using transitive relationships and annotations of protein interactions. In addition, a distillation of virtual direct protein-protein interactions is proposed to deal with unbalanced distribution of different types of interactions in the existing protein-protein interaction databases. Our results demonstrate that ATRP can effectively predict protein-protein interactions. ATRP achieves an 81% precision, a 74% recall and a 77% F-measure in average rate in the prediction of direct protein-protein interactions. Using the generated benchmark datasets from KUPS to evaluate of all types of the protein-protein interaction, ATRP achieved a 93% precision, a 49% recall and a 64% F-measure in average rate. This article is part of a Special Issue entitled: Computational Methods for Protein Interaction and Structural Prediction.     

Application of singular spectrum-based change-point analysis to EMG-onset detection

While many approaches have been proposed to identify the signal onset in EMG recordings, there is no standardized method for performing this task. Here, we propose to use a change-point detection procedure based on singular spectrum analysis to determine the onset of EMG signals. This method is suitable for automated real-time implementation, can be applied directly to the raw signal, and does not require any prior knowledge of the EMG signal’s properties. The algorithm proposed by Moskvina and Zhigljavsky (2003) was applied to EMG segments recorded from wrist and trunk muscles. Wrist EMG data was collected from 9 Parkinson’s disease patients with and without tremor, while trunk EMG data was collected from 13 healthy able-bodied individuals. Along with the change-point detection analysis, two threshold-based onset detection methods were applied, as well as visual estimates of the EMG onset by trained practitioners. In the case of wrist EMG data without tremor, the change-point analysis showed comparable or superior frequency and quality of detection results, as compared to other automatic detection methods. In the case of wrist EMG data with tremor and trunk EMG data, performance suffered because other changes occurring in these signals caused larger changes in the detection statistic than the changes caused by the initial muscle activation, suggesting that additional criteria are needed to identify the onset from the detection statistic other than its magnitude alone. Once this issue is resolved, change-point detection should provide an effective EMG-onset detection method suitable for automated real-time implementation.     

Unified Saliency Detection Model Using Color and Texture Features

Saliency detection attracted attention of many researchers and had become a very active area of research. Recently, many saliency detection models have been proposed and achieved excellent performance in various fields. However, most of these models only consider low-level features. This paper proposes a novel saliency detection model using both color and texture features and incorporating higher-level priors. The SLIC superpixel algorithm is applied to form an over-segmentation of the image. Color saliency map and texture saliency map are calculated based on the region contrast method and adaptive weight. Higher-level priors including location prior and color prior are incorporated into the model to achieve a better performance and full resolution saliency map is obtained by using the up-sampling method. Experimental results on three datasets demonstrate that the proposed saliency detection model outperforms the state-of-the-art models.     

Recognizing names in biomedical texts: a machine learning approach

MOTIVATION: With an overwhelming amount of textual information in molecular biology and biomedicine, there is a need for effective and efficient literature mining and knowledge discovery that can help biologists to gather and make use of the knowledge encoded in text documents. In order to make organized and structured information available, automatically recognizing biomedical entity names becomes critical and is important for information retrieval, information extraction and automated knowledge acquisition. RESULTS: In this paper, we present a named entity recognition system in the biomedical domain, called PowerBioNE. In order to deal with the special phenomena of naming conventions in the biomedical domain, we propose various evidential features: (1) word formation pattern; (2) morphological pattern, such as prefix and suffix; (3) part-of-speech; (4) head noun trigger; (5) special verb trigger and (6) name alias feature. All the features are integrated effectively and efficiently through a hidden Markov model (HMM) and a HMM-based named entity recognizer. In addition, a k-Nearest Neighbor (k-NN) algorithm is proposed to resolve the data sparseness problem in our system. Finally, we present a pattern-based post-processing to automatically extract rules from the training data to deal with the cascaded entity name phenomenon. From our best knowledge, PowerBioNE is the first system which deals with the cascaded entity name phenomenon. Evaluation shows that our system achieves the F-measure of 66.6 and 62.2 on the 23 classes of GENIA V3.0 and V1.1, respectively. In particular, our system achieves the F-measure of 75.8 on the "protein" class of GENIA V3.0. For comparison, our system outperforms the best published result by 7.8 on GENIA V1.1, without help of any dictionaries. It also shows that our HMM and the k-NN algorithm outperform other models, such as back-off HMM, linear interpolated HMM, support vector machines, C4.5, C4.5 rules and RIPPER, by effectively capturing the local context dependency and resolving the data sparseness problem. Moreover, evaluation on GENIA V3.0 shows that the post-processing for the cascaded entity name phenomenon improves the F-measure by 3.9. Finally, error analysis shows that about half of the errors are caused by the strict annotation scheme and the annotation inconsistency in the GENIA corpus. This suggests that our system achieves an acceptable F-measure of 83.6 on the 23 classes of GENIA V3.0 and in particular 86.2 on the "protein" class, without help of any dictionaries. We think that a F-measure of 90 on the 23 classes of GENIA V3.0 and in particular 92 on the "protein" class, can be achieved through refining of the annotation scheme in the GENIA corpus, such as flexible annotation scheme and annotation consistency, and inclusion of a reasonable biomedical dictionary. AVAILABILITY: A demo system is available at http://textmining.i2r.a-star.edu.sg/NLS/demo.htm. Technology license is available upon the bilateral agreement.     

Regional Principal Color Based Saliency Detection

Saliency detection is widely used in many visual applications like image segmentation, object recognition and classification. In this paper, we will introduce a new method to detect salient objects in natural images. The approach is based on a regional principal color contrast modal, which incorporates low-level and medium-level visual cues. The method allows a simple computation of color features and two categories of spatial relationships to a saliency map, achieving higher F-measure rates. At the same time, we present an interpolation approach to evaluate resulting curves, and analyze parameters selection. Our method enables the effective computation of arbitrary resolution images. Experimental results on a saliency database show that our approach produces high quality saliency maps and performs favorably against ten saliency detection algorithms.     

Different neuroplasticity for task targets and distractors

Adult learning-induced sensory cortex plasticity results in enhanced action potential rates in neurons that have the most relevant information for the task, or those that respond strongly to one sensory stimulus but weakly to its comparison stimulus. Current theories suggest this plasticity is caused when target stimulus evoked activity is enhanced by reward signals from neuromodulatory nuclei. Prior work has found evidence suggestive of nonselective enhancement of neural responses, and suppression of responses to task distractors, but the differences in these effects between detection and discrimination have not been directly tested. Using cortical implants, we defined physiological responses in macaque somatosensory cortex during serial, matched, detection and discrimination tasks. Nonselective increases in neural responsiveness were observed during detection learning. Suppression of responses to task distractors was observed during discrimination learning, and this suppression was specific to cortical locations that sampled responses to the task distractor before learning. Changes in receptive field size were measured as the area of skin that had a significant response to a constant magnitude stimulus, and these areal changes paralleled changes in responsiveness. From before detection learning until after discrimination learning, the enduring changes were selective suppression of cortical locations responsive to task distractors, and nonselective enhancement of responsiveness at cortical locations selective for target and control skin sites. A comparison of observations in prior studies with the observed plasticity effects suggests that the non-selective response enhancement and selective suppression suffice to explain known plasticity phenomena in simple spatial tasks. This work suggests that differential responsiveness to task targets and distractors in primary sensory cortex for a simple spatial detection and discrimination task arise from nonselective increases in response over a broad cortical locus that includes the representation of the task target, and selective suppression of responses to the task distractor within this locus.     

Overview of BioCreative II gene normalization

Background:

The goal of the gene normalization task is to link genes or gene products mentioned in the literature to biological databases. This is a key step in an accurate search of the biological literature. It is a challenging task, even for the human expert; genes are often described rather than referred to by gene symbol and, confusingly, one gene name may refer to different genes (often from different organisms). For BioCreative II, the task was to list the Entrez Gene identifiers for human genes or gene products mentioned in PubMed/MEDLINE abstracts. We selected abstracts associated with articles previously curated for human genes. We provided 281 expert-annotated abstracts containing 684 gene identifiers for training, and a blind test set of 262 documents containing 785 identifiers, with a gold standard created by expert annotators. Inter-annotator agreement was measured at over 90%.

Results:

Twenty groups submitted one to three runs each, for a total of 54 runs. Three systems achieved F-measures (balanced precision and recall) between 0.80 and 0.81. Combining the system outputs using simple voting schemes and classifiers obtained improved results; the best composite system achieved an F-measure of 0.92 with 10-fold cross-validation. A 'maximum recall' system based on the pooled responses of all participants gave a recall of 0.97 (with precision 0.23), identifying 763 out of 785 identifiers.

Conclusion:

Major advances for the BioCreative II gene normalization task include broader participation (20 versus 8 teams) and a pooled system performance comparable to human experts, at over 90% agreement. These results show promise as tools to link the literature with biological databases.

     

A Simple Semi-Automatic Approach for Land Cover Classification from Multispectral Remote Sensing Imagery

Land cover data represent a fundamental data source for various types of scientific research. The classification of land cover based on satellite data is a challenging task, and an efficient classification method is needed. In this study, an automatic scheme is proposed for the classification of land use using multispectral remote sensing images based on change detection and a semi-supervised classifier. The satellite image can be automatically classified using only the prior land cover map and existing images; therefore human involvement is reduced to a minimum, ensuring the operability of the method. The method was tested in the Qingpu District of Shanghai, China. Using Environment Satellite 1(HJ-1) images of 2009 with 30 m spatial resolution, the areas were classified into five main types of land cover based on previous land cover data and spectral features. The results agreed on validation of land cover maps well with a Kappa value of 0.79 and statistical area biases in proportion less than 6%. This study proposed a simple semi-automatic approach for land cover classification by using prior maps with satisfied accuracy, which integrated the accuracy of visual interpretation and performance of automatic classification methods. The method can be used for land cover mapping in areas lacking ground reference information or identifying rapid variation of land cover regions (such as rapid urbanization) with convenience.     

Prediction of Protein–Protein Interaction Sites in Sequences and 3D Structures by Random Forests

Identifying interaction sites in proteins provides important clues to the function of a protein and is becoming increasingly relevant in topics such as systems biology and drug discovery. Although there are numerous papers on the prediction of interaction sites using information derived from structure, there are only a few case reports on the prediction of interaction residues based solely on protein sequence. Here, a sliding window approach is combined with the Random Forests method to predict protein interaction sites using (i) a combination of sequence- and structure-derived parameters and (ii) sequence information alone. For sequence-based prediction we achieved a precision of 84% with a 26% recall and an F-measure of 40%. When combined with structural information, the prediction performance increases to a precision of 76% and a recall of 38% with an F-measure of 51%. We also present an attempt to rationalize the sliding window size and demonstrate that a nine-residue window is the most suitable for predictor construction. Finally, we demonstrate the applicability of our prediction methods by modeling the Ras–Raf complex using predicted interaction sites as target binding interfaces. Our results suggest that it is possible to predict protein interaction sites with quite a high accuracy using only sequence information.     

Liquid chromatography method for detecting native fluorescent bioamines in urine using post-column derivatization and intramolecular FRET detection

Liquid chromatography (LC) with fluorescence detection is described for simultaneous determination of native fluorescent bioamines (indoleamines and catecholamines). This is based on intramolecular fluorescence resonance energy transfer (FRET) in an LC system following post-column derivatization of native fluorescent bioamines' amino groups with o-phthalaldehyde (OPA). OPA fluorescence was achieved through an intramolecular FRET process when the molecules were excited at maximum excitation wavelength of the native fluorescent bioamines. Bioamines separated by reversed-phase LC on ODS column were derivatized with OPA and 2-mercaptoethanol. This method provides sufficient selectivity and sensitivity for the determination of normetanephrine, dopamine, tyrosine, 5-hydroxytryptamine, tryptamine, and tryptophan in healthy human urine without prior sample purification.     

Double digest RADseq: an inexpensive method for de novo SNP discovery and genotyping in model and non-model species

The ability to efficiently and accurately determine genotypes is a keystone technology in modern genetics, crucial to studies ranging from clinical diagnostics, to genotype-phenotype association, to reconstruction of ancestry and the detection of selection. To date, high capacity, low cost genotyping has been largely achieved via "SNP chip" microarray-based platforms which require substantial prior knowledge of both genome sequence and variability, and once designed are suitable only for those targeted variable nucleotide sites. This method introduces substantial ascertainment bias and inherently precludes detection of rare or population-specific variants, a major source of information for both population history and genotype-phenotype association. Recent developments in reduced-representation genome sequencing experiments on massively parallel sequencers (commonly referred to as RAD-tag or RADseq) have brought direct sequencing to the problem of population genotyping, but increased cost and procedural and analytical complexity have limited their widespread adoption. Here, we describe a complete laboratory protocol, including a custom combinatorial indexing method, and accompanying software tools to facilitate genotyping across large numbers (hundreds or more) of individuals for a range of markers (hundreds to hundreds of thousands). Our method requires no prior genomic knowledge and achieves per-site and per-individual costs below that of current SNP chip technology, while requiring similar hands-on time investment, comparable amounts of input DNA, and downstream analysis times on the order of hours. Finally, we provide empirical results from the application of this method to both genotyping in a laboratory cross and in wild populations. Because of its flexibility, this modified RADseq approach promises to be applicable to a diversity of biological questions in a wide range of organisms.     

Prediction of Protein–Protein Interaction Sites in Sequences and 3D Structures by Random Forests

Identifying interaction sites in proteins provides important clues to the function of a protein and is becoming increasingly relevant in topics such as systems biology and drug discovery. Although there are numerous papers on the prediction of interaction sites using information derived from structure, there are only a few case reports on the prediction of interaction residues based solely on protein sequence. Here, a sliding window approach is combined with the Random Forests method to predict protein interaction sites using (i) a combination of sequence- and structure-derived parameters and (ii) sequence information alone. For sequence-based prediction we achieved a precision of 84% with a 26% recall and an F-measure of 40%. When combined with structural information, the prediction performance increases to a precision of 76% and a recall of 38% with an F-measure of 51%. We also present an attempt to rationalize the sliding window size and demonstrate that a nine-residue window is the most suitable for predictor construction. Finally, we demonstrate the applicability of our prediction methods by modeling the Ras–Raf complex using predicted interaction sites as target binding interfaces. Our results suggest that it is possible to predict protein interaction sites with quite a high accuracy using only sequence information.     

Improved parameter estimation for systems with an experimentally located Hopf bifurcation

When performing system identification, we have two sources of information: experimental data and prior knowledge. Many cell-biological systems are oscillating, and sometimes we know an input where the system reaches a Hopf bifurcation. This is the case, for example, for glycolysis in yeast cells and for the Belousov-Zhabotinsky reaction, and for both of these systems there exist significant numbers of quenching data, ideal for system identification. We present a method that includes prior knowledge of the location of a Hopf bifurcation in estimation based on time-series. The main contribution is a reformulation of the prior knowledge into the standard formulation of a constrained optimisation problem. This formulation allows for any of the standard methods to be applied, including all the theories regarding the method's properties. The reformulation is carried out through an over-parametrisation of the original problem. The over-parametrisation allows for extra constraints to be formed, and the net effect is a reduction of the search space. A method that can solve the new formulation of the problem is presented, and the advantage of adding the prior knowledge is demonstrated on the Brusselator.     

How Recent History Affects Perception: The Normative Approach and Its Heuristic Approximation

There is accumulating evidence that prior knowledge about expectations plays an important role in perception. The Bayesian framework is the standard computational approach to explain how prior knowledge about the distribution of expected stimuli is incorporated with noisy observations in order to improve performance. However, it is unclear what information about the prior distribution is acquired by the perceptual system over short periods of time and how this information is utilized in the process of perceptual decision making. Here we address this question using a simple two-tone discrimination task. We find that the “contraction bias”, in which small magnitudes are overestimated and large magnitudes are underestimated, dominates the pattern of responses of human participants. This contraction bias is consistent with the Bayesian hypothesis in which the true prior information is available to the decision-maker. However, a trial-by-trial analysis of the pattern of responses reveals that the contribution of most recent trials to performance is overweighted compared with the predictions of a standard Bayesian model. Moreover, we study participants'' performance in a-typical distributions of stimuli and demonstrate substantial deviations from the ideal Bayesian detector, suggesting that the brain utilizes a heuristic approximation of the Bayesian inference. We propose a biologically plausible model, in which decision in the two-tone discrimination task is based on a comparison between the second tone and an exponentially-decaying average of the first tone and past tones. We show that this model accounts for both the contraction bias and the deviations from the ideal Bayesian detector hypothesis. These findings demonstrate the power of Bayesian-like heuristics in the brain, as well as their limitations in their failure to fully adapt to novel environments.     

Breast mass segmentation using region-based and edge-based methods in a 4-stage multiscale system

Mass segmentation in mammograms is a challenging task due to problems such as low contrast, ill-defined, fuzzy or spiculated borders, and the presence of intensity inhomogeneities. These facts complicate the development of computer-aided diagnosis (CAD) systems to assist radiologists. In this paper, a novel mass segmentation algorithm for mammograms based on robust multiscale feature-fusion, and automatic estimation based maximum a posteriori (MAP) method is presented. The proposed segmentation technique consists of mainly four stages: a dynamic contrast improvement scheme applied to a selected region-of-interest (ROI), background-influence correction by template matching, detection of mass candidate points by prior and posterior probabilities based on robust multiscale feature-fusion, and final delineation of the mass region by a MAP scheme. This segmentation method is applied to 480 ROI masses that used ground truth from two radiologists. To compare its effectiveness with the state-of-the-art segmentation methods, three statistical metrics are employed. The experimental results indicate that the developed methods can reliably segment ill-defined or spiculated lesions when compared to other algorithms. Its integration in a CAD system may result in an improved aid to radiologists.     

Automatic Background Knowledge Selection for Matching Biomedical Ontologies

Ontology matching is a growing field of research that is of critical importance for the semantic web initiative. The use of background knowledge for ontology matching is often a key factor for success, particularly in complex and lexically rich domains such as the life sciences. However, in most ontology matching systems, the background knowledge sources are either predefined by the system or have to be provided by the user. In this paper, we present a novel methodology for automatically selecting background knowledge sources for any given ontologies to match. This methodology measures the usefulness of each background knowledge source by assessing the fraction of classes mapped through it over those mapped directly, which we call the mapping gain. We implemented this methodology in the AgreementMakerLight ontology matching framework, and evaluate it using the benchmark biomedical ontology matching tasks from the Ontology Alignment Evaluation Initiative (OAEI) 2013. In each matching problem, our methodology consistently identified the sources of background knowledge that led to the highest improvements over the baseline alignment (i.e., without background knowledge). Furthermore, our proposed mapping gain parameter is strongly correlated with the F-measure of the produced alignments, thus making it a good estimator for ontology matching techniques based on background knowledge.     

A new training method for hybrid models of bioprocesses

Modeling of bioprocesses for engineering applications is a very difficult and time consuming task, due to their complex nonlinear dynamic behavior. In the last years several propositions for hybrid models, and especially serial approaches, were published and discussed, in order to combine analytical prior knowledge with the learning capabilities of Artificial Neural Networks (ANN). These approaches often require synchronous and equidistant sampled training data. However, in practice concentrations are mostly off-line measured, rare, and asynchronous. In this paper a new training method especially suited for very few asynchronously sampled data is presented and applied for modeling animal cell cultures. The achieved model is able to predict the concentrations of the reaction components inside a stirred tank bioreactor.