BACKGROUND: Comparing phenotypes of heterogeneous cell populations from multiple biological conditions is at the heart of scientific discovery based on flow cytometry (FC). When the biological signal is measured by the average expression of a biomarker, standard statistical methods require that variance be approximately stabilized in populations to be compared. Since the mean and variance of a cell population are often correlated in fluorescence-based FC measurements, a preprocessing step is needed to stabilize the within-population variances. RESULTS: We present a variance-stabilization algorithm, called flowVS, that removes the mean-variance correlations from cell populations identified in each fluorescence channel. flowVS transforms each channel from all samples of a data set by the inverse hyperbolic sine (asinh) transformation. For each channel, the parameters of the transformation are optimally selected by Bartlett's likelihood-ratio test so that the populations attain homogeneous variances. The optimum parameters are then used to transform the corresponding channels in every sample. flowVS is therefore an explicit variance-stabilization method that stabilizes within-population variances in each channel by evaluating the homoskedasticity of clusters with a likelihood-ratio test. With two publicly available datasets, we show that flowVS removes the mean-variance dependence from raw FC data and makes the within-population variance relatively homogeneous. We demonstrate that alternative transformation techniques such as flowTrans, flowScape, logicle, and FCSTrans might not stabilize variance. Besides flow cytometry, flowVS can also be applied to stabilize variance in microarray data. With a publicly available data set we demonstrate that flowVS performs as well as the VSN software, a state-of-the-art approach developed for microarrays. CONCLUSIONS: The homogeneity of variance in cell populations across FC samples is desirable when extracting features uniformly and comparing cell populations with different levels of marker expressions. The newly developed flowVS algorithm solves the variance-stabilization problem in FC and microarrays by optimally transforming data with the help of Bartlett's likelihood-ratio test. On two publicly available FC datasets, flowVS stabilizes within-population variances more evenly than the available transformation and normalization techniques. flowVS-based variance stabilization can help in performing comparison and alignment of phenotypically identical cell populations across different samples. flowVS and the datasets used in this paper are publicly available in Bioconductor.

We study a bio-detection application as a case study to demonstrate that Kmeans -- based unsupervised feature learning can be a simple yet effective alternative to deep learning techniques for small data sets with limited intra-as well as inter-class diversity. We investigate the effect on the classifier performance of data augmentation as well as feature extraction with multiple patch sizes and at different image scales. Our data set includes 1833 images from four different classes of bacteria, each bacterial culture captured at three different wavelengths and overall data collected during a three-day period. The limited number and diversity of images present, potential random effects across multiple days, and the multi-mode nature of class distributions pose a challenging setting for representation learning. Using images collected on the first day for training, on the second day for validation, and on the third day for testing Kmeans -- based representation learning achieves 97% classification accuracy on the test data. This compares very favorably to 56% accuracy achieved by deep learning and 74% accuracy achieved by handcrafted features. Our results suggest that data augmentation or dropping connections between units offers little help for deep-learning algorithms, whereas significant boost can be achieved by Kmeans -- based representation learning by augmenting data and by concatenating features obtained at multiple patch sizes or image scales.

Biofilm is a formation of microbial material on tooth substrata. Several methods to quantify dental biofilm coverage have recently been reported in the literature, but at best they provide a semiautomated approach to quantification with significant input from a human grader that comes with the grader's bias of what is foreground, background, biofilm, and tooth. Additionally,human assessment indices limit the resolution of the quantification scale; most commercial scales use five levels of quantification for biofilm coverage (0%, 25%, 50%, 75%, and 100%). On the other hand, current state-of-the-art techniques in automatic plaque quantification fail to make their way into practical applications owing to their inability to incorporate human input to handle misclassifications. This paper proposes a new interactive method for biofilm quantification in Quantitative light-induced fluorescence(QLF) images of canine teeth that is independent of the perceptual bias of the grader. The method partitions a QLF image into segments of uniform texture and intensity called superpixels; every superpixel is statistically modeled as a realization of a single 2-D Gaussian Markov random field (GMRF) whose parameters are estimated; the superpixel is then assigned to one of three classes (background, biofilm, tooth substratum) based on the training set of data. The quantification results show a high degree of consistency and precision. At the same time, the proposed method gives pathologists full control to postprocess the automatic quantification by flipping misclassified superpixels to a different state (background,tooth, biofilm) with a single click, providing greater usability than simply marking the boundaries of biofilm and tooth as done by current state-of-the-art methods.

We present a clustering algorithm for discovering rare yet significant recurring classes across a batch of samples in the presence of random effects. We model each sample data by an infinite mixture of Dirichlet-process Gaussian-mixture models (DPMs) with each DPM representing the noisy realization of its corresponding class distribution in a given sample. We introduce dependencies across multiple samples by placing a global Dirichlet process prior over individual DPMs. This hierarchical prior introduces a sharing mechanism across samples and allows for identifying local realizations of classes across samples. We use collapsed Gibbs sampler for inference to recover local DPMs and identify their class associations. We demonstrate the utility of the proposed algorithm, processing a flow cytometry data set containing two extremely rare cell populations, and report results that significantly outperform competing techniques. The source code of the proposed algorithm is available on the web via the link: http://cs.iupui.edu/~dundar/aspire.htm.

BACKGROUND: Flow cytometry (FC)-based computer-aided diagnostics is an emerging technique utilizing modern multiparametric cytometry systems.The major difficulty in using machine-learning approaches for classification of FC data arises from limited access to a wide variety of anomalous samples for training. In consequence, any learning with an abundance of normal cases and a limited set of specific anomalous cases is biased towards the types of anomalies represented in the training set. Such models do not accurately identify anomalies, whether previously known or unknown, that may exist in future samples tested. Although one-class classifiers trained using only normal cases would avoid such a bias, robust sample characterization is critical for a generalizable model. Owing to sample heterogeneity and instrumental variability, arbitrary characterization of samples usually introduces feature noise that may lead to poor predictive performance. Herein, we present a non-parametric Bayesian algorithm called ASPIRE (anomalous sample phenotype identification with random effects) that identifies phenotypic differences across a batch of samples in the presence of random effects. Our approach involves simultaneous clustering of cellular measurements in individual samples and matching of discovered clusters across all samples in order to recover global clusters using probabilistic sampling techniques in a systematic way. RESULTS: We demonstrate the performance of the proposed method in identifying anomalous samples in two different FC data sets, one of which represents a set of samples including acute myeloid leukemia (AML) cases, and the other a generic 5-parameter peripheral-blood immunophenotyping. Results are evaluated in terms of the area under the receiver operating characteristics curve (AUC). ASPIRE achieved AUCs of 0.99 and 1.0 on the AML and generic blood immunophenotyping data sets, respectively. CONCLUSIONS: These results demonstrate that anomalous samples can be identified by ASPIRE with almost perfect accuracy without a priori access to samples of anomalous subtypes in the training set. The ASPIRE approach is unique in its ability to form generalizations regarding normal and anomalous states given only very weak assumptions regarding sample characteristics and origin. Thus, ASPIRE could become highly instrumental in providing unique insights about observed biological phenomena in the absence of full information about the investigated samples.

Disease outbreaks due to contaminated food are a major concern not only for the food-processing industry but also for the public at large. Techniques for automated detection and classification of microorganisms can be a great help in preventing outbreaks and maintaining the safety of the nations food supply. Identification and classification of foodborne pathogens using colony scatter patterns is a promising new label-free technique that utilizes image-analysis and machine-learning tools. However, the feature-extraction tools employed for this approach are computationally complex, and choosing the right combination of scatter-related features requires extensive testing with different feature combinations. In the presented work we used computer clusters to speed up the feature-extraction process, which enables us to analyze the contribution of different scatter-based features to the overall classification accuracy. A set of 1000 scatter patterns representing ten different bacterial strains was used. Zernike and Chebyshev moments as well as Haralick texture features were computed from the available light-scatter patterns. The most promising features were first selected using Fishers discriminant analysis, and subsequently a support-vector-machine (SVM) classifier with a linear kernel was used. With extensive testing we were able to identify a small subset of features that produced the desired results in terms of classification accuracy and execution speed. The use of distributed computing for scatter-pattern analysis, feature extraction, and selection provides a feasible mechanism for large-scale deployment of a light scatter-based approach to bacterial classification.

We present a new direction for semi-supervised learning where self-adjusting generative models replace fixed ones and unlabeled data can potentially improve learning even when labeled data is only partially-observed. We model each class data by a mixture model and use a hierarchical Dirichlet process (HDP) to model observed as well as unobserved classes. We extend the standard HDP model to accommodate unlabeled samples and introduce a new sharing strategy, within the context of Gaussian mixture models, that restricts sharing with covariance matrices while leaving the mean vectors free. Our research is mainly driven by real-world applications with evolving data-generating mechanisms where obtaining a fully-observed labeled data set is impractical. We demonstrate the feasibility of the proposed approach for semi-supervised learning in two such applications.

For a training dataset with a nonexhaustive list of classes, i.e. some classes are not yet known and hence are not represented, the resulting learning problem is ill-defined. In this case a sample from a missing class is incorrectly classified to one of the existing classes. For some applications the cost of misclassifying a sample could be negligible. However, the significance of this problem can better be acknowledged when the potentially undesirable consequences of incorrectly classifying a food pathogen as a nonpathogen are considered. Our research is directed towards the real-time detection of food pathogens using optical-scattering technology. Bacterial colonies consisting of the progeny of a single parent cell scatter light at 635 nm to produce unique forward-scatter signatures. These spectral signatures contain descriptive characteristics of bacterial colonies, which can be used to identify bacteria cultures in real time. One bottleneck that remains to be addressed is the nonexhaustive nature of the training library. It is very difficult if not impractical to collect samples from all possible bacteria colonies and construct a digital library with an exhaustive set of scatter signatures. This study deals with the real-time detection of samples from a missing class and the associated problem of learning with a nonexhaustive training dataset. Our proposed method assumes a common prior for the set of all classes, known and missing. The parameters of the prior are estimated from the samples of the known classes. This prior is then used to generate a large number of samples to simulate the space of missing classes. Finally a Bayesian maximum likelihood classifier is implemented using samples from real as well as simulated classes. Experiments performed with samples collected for 28 bacteria subclasses favor the proposed approach over the state of the art.

Rapid advances in optical instrumentation, high-speed cameras, and fluorescent probes have spurred tremendous growth in the volume of biomolecular imaging data. Various optical imaging modalities are used for probing biological systems in vivo and in vitro. These include traditional two-dimensional imaging, three-dimensional confocal imaging, time-lapse imaging, and multispectral imaging. Many applications require a combination of these imaging modalities, which gives rise to huge data sets. However, lack of powerful information extraction and quantitative analysis tools poses a major hindrance to exploiting the full potential of the information content of these data. In particular, automated extraction of semantic information from multimodality imaging data, crucial for understanding biological processes, poses unique challenges. Information extraction from large sets of biomolecular imaging data requires modeling at multiple levels of detail to allow not only quantitative analysis but also interpretation and extraction of high-level semantic information. In this paper, we survey the state of the art in the area of information extraction and automated analysis tools for in vivo and in vitro biomolecular imaging. The modeling and knowledge extraction for these data require sophisticated image processing and machine learning techniques, as well as formalisms for information extraction and knowledge management. Development of such tools has the potential to significantly improve biological discovery and drug development processes.

Bacterial contamination of food products is a serious public health problem that creates high costs for the food-processing industry. Rapid detection of bacterial pathogens is the key to avoiding disease outbreaks and costly product recalls associated with food-borne pathogens. Automated identification of pathogens using scatter patterns of bacterial colonies is a promising technique that uses image processing and machine learning approaches to extract features from forward-scatter patterns produced by irradiating bacterial colonies with red laser light. The feature vector used for this approach can consist of hundreds of features, and a sufficiently large number of training images is required for accurate classification. As most feature extraction algorithms have high computational cost, the feature extraction step becomes the bottleneck in the whole processing pipeline. Computational grid technologies provide a promising and economical solution to this problem. In this work we report the implementation of the laser-scatter-analysis technique on a computational grid. A set of more than 2000 images was used for training of classifiers. The invariant form of Zernike moments up to order 20, radial Chebyshev moments, and Haralick features were extracted. Linear discriminant analysis and support vector machine classifiers were used for classification. We report speed-ups achieved and the scalability of this approach for large sets of images and for higher-order moments. Laser-scatter-analysis technique combined with computational grid technology offers a feasible and economic solution for rapid and accurate detection and classification of bacterial contamination.