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.

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.

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.

High-throughput biological imaging uses automated imaging devices to collect a large number of microscopic images for analysis of biological systems and validation of scientific hypotheses. Efficient manipulation of these datasets for knowledge discovery requires high-performance computational resources, efficient storage, and automated tools for extracting and sharing such knowledge among different research sites. Newly emerging grid technologies provide powerful means for exploiting the full potential of these imaging techniques. Efficient utilization of grid resources requires the development of knowledge-based tools and services that combine domain knowledge with analysis algorithms. In this paper, we first investigate how grid infrastructure can facilitate high-throughput biological imaging research, and present an architecture for providing knowledge-based grid services for this field. We identify two levels of knowledge-based services. The first level provides tools for extracting spatiotemporal knowledge from image sets and the second level provides high-level knowledge management and reasoning services. We then present cellular imaging markup language, an extensible markup language-based language for modeling of biological images and representation of spatiotemporal knowledge. This scheme can be used for spatiotemporal event composition, matching, and automated knowledge extraction and representation for large biological imaging datasets. We demonstrate the expressive power of this formalism by means of different examples and extensive experimental results.

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.

Study of spatial relations between biological objects is crucial for understanding biological processes. Monitoring drug or particle delivery inside cells and studying the dynamics of subcellular proteins are some of the examples. Biological applications have varying demands in terms of speed and accuracy. While accuracy may be the most important factor for small-scale biology, speed is also a concern for high-content/high-throughput screening applications. In this paper we present a variety of algorithms for inter-object spatial relations in two-and three-dimensional space. These algorithms provide trade-off between speed and accuracy, depending on the requirements of the application. Results for speed and accuracy are reported for real as well as synthetic data sets.

High-content and high-throughput screening (HCS/HTS) technologies provide powerful imaging tools for analyses of biological processes. These technologies combine sophisticated optics with automation techniques for imaging large populations of cells under different experimental perturbations and produce enormous amount of imaging data, including 2D images, 3D confocal data sets, time-lapse video sequences, and multispectral images. Manual analysis of such data is extremely time consuming, and intelligent image interpretation tools have only recently started to emerge. There is a direct need for powerful automated image understanding and spatio-temporal knowledge extraction techniques for gaining useful semantic information in biological domain consisting of multimodality multimedia data. In this tutorial we highlight key multimedia processing challenges in this domain and present a knowledge extraction and representation framework that is currently underway at Purdue University's Cytometery Laboratories and Distributed Multimedia System Laboratory. The proposed framework is being implemented using XML in order to allow extensibility and standardization.