Search

Gene regulatory networks (GRN) have been studied by computational scientists and biologists over 20 years to gain a fine map of gene functions. With large-scale genomic and epigenetic data generated under diverse cells, tissues, and diseases, the integrative analysis of multi-omics data plays a key role in identifying casual genes in human disease development. Bayesian inference (or integration) has been successfully applied to inferring GRNs. Learning a posterior distribution than making a single-value prediction of model parameter makes Bayesian inference a more robust approach to identify GRN from noisy biomedical observations. Moreover, given multi-omics data as input and a large number of model parameters to estimate, the automatic preference of Bayesian inference for simple models that sufficiently explain data without unnecessary complexity ensures fast convergence to reliable results. In this chapter, we introduced GRN modeling using hierarchical Bayesian network and then used Gibbs sampling to identify network variables. We applied this model to breast cancer data and identified genes relevant to breast cancer recurrence. In the end, we discussed the potential of Bayesian inference as well as Bayesian deep learning for large-scale and complex GRN inference.

To construct biologically interpretable gene sets for muscular dystrophy (MD) sub-type classification, we propose a novel computational scheme to integrate protein-protein interaction (PPI) network, functional gene set information, and mRNA profiling data. The workflow of the proposed scheme includes the following three major steps: firstly, we apply an affinity propagation clustering (APC) approach to identify gene sub-networks associated with each MD sub-type, in which a new distance metric is proposed for APC to combine PPI network information and gene-gene co-expression relationship; secondly, we further incorporate functional gene set knowledge, which complements the physical PPI information, into our scheme for biomarker identification; finally, based on the constructed sub-networks and gene set features, we apply multi-class support vector machines (MSVMs) for MD sub-type classification, with which to highlight the biomarkers contributing to sub-type prediction. The experimental results show that our scheme can help identify sub-networks and gene sets that are more relevant to MD than those constructed by other conventional approaches. Moreover, our integrative strategy improves the prediction accuracy substantially, especially for those 'hard-to-classify' sub-types.

Conventionally, pathway-based analysis assumes that genes in a pathway equally contribute to a biological function, thus assigning uniform weight to genes. However, this assumption has been proved incorrect, and applying uniform weight in the pathway analysis may not be an appropriate approach for the tasks like molecular classification of diseases, as genes in a functional group may have different predicting power. Hence, we propose to use different weights to genes in pathway-based analysis and devise four weighting schemes. We applied them in two existing pathway analysis methods using both real and simulated gene expression data for pathways. Among all schemes, random weighting scheme, which generates random weights and selects optimal weights minimizing an objective function, performs best in terms ofPvalue or error rate reduction. Weighting changes pathway scoring and brings up some new significant pathways, leading to the detection of disease-related genes that are missed under uniform weight.

Purpose: A learning-based approach integrating the use of pixel-level statistical modeling and spiculation detection is presented for the segmentation of mammographic masses with ill-defined margins and spiculations. Methods: The algorithm involves a multiphase pixel-level classification, using a comprehensive group of features computed from regional intensity, shape, and textures, to generate a mass-conditional probability map (PM). Then, the mass candidate, along with the background clutters consisting of breast fibroglandular and other nonmass tissues, is extracted from the PM by integrating the prior knowledge of shape and location of masses. A multiscale steerable ridge detection algorithm is employed to detect spiculations. Finally, all the object-level findings, including mass candidate, detected spiculations, and clutters, along with the PM, are integrated by graph cuts to generate the final segmentation mask. Results: The method was tested on 54 masses (51 malignant and 3 benign), all with ill-defined margins and irregular shape or spiculations. The ground truth delineations were provided by five experienced radiologists. Area overlapping ratio of 0.689 (±0.160) and 0.540 (±0.164) were obtained for segmenting entire mass and margin portion only, respectively. Williams index of area and contour based measurements indicated that the segmentation results of the algorithm agreed well with the radiologists’ delineation. Conclusions: The proposed approach could closely delineate the mass body. Most importantly, it is capable of including mass margin and its spicule extensions which are considered as key features for breast lesion analyses.

Summary: VISDA (Visual Statistical Data Analyzer) is a caBIG™ analytical tool for cluster modeling, visualization and discovery that has met silver-level compatibility under the caBIG initiative. Being statistically principled and visually interfaced, VISDA exploits both hierarchical statistics modeling and human gift for pattern recognition to allow a progressive yet interactive discovery of hidden clusters within high dimensional and complex biomedical datasets. The distinctive features of VISDA are particularly useful for users across the cancer research and broader research communities to analyze complex biological data.Availability: http://gforge.nci.nih.gov/projects/visda/Contact: yuewang@vt.eduSupplementary information: Supplementary data are available at Bioinformatics online.

Motivation: Multilayer perceptrons (MLP) represent one of the widely used and effective machine learning methods currently applied to diagnostic classification based on high-dimensional genomic data. Since the dimensionalities of the existing genomic data often exceed the available sample sizes by orders of magnitude, the MLP performance may degrade owing to the curse of dimensionality and over-fitting, and may not provide acceptable prediction accuracy. Results: Based on Fisher linear discriminant analysis, we designed and implemented an MLP optimization scheme for a two-layer MLP that effectively optimizes the initialization of MLP parameters and MLP architecture. The optimized MLP consistently demonstrated its ability in easing the curse of dimensionality in large microarray datasets. In comparison with a conventional MLP using random initialization, we obtained significant improvements in major performance measures including Bayes classification accuracy, convergence properties and area under the receiver operating characteristic curve (Az). Supplementary information: The Supplementary information is available on Contact: yuewang@vt.edu

This paper describes a neural computation based nonrigid registration methodology using multiple rigid transforms, in a piece-wise fashion, to model the registration process between images in a sequence. The registration methodology is a hybrid approach that combines registration without exact point correspondence via multi-object principal axes, and registration with point correspondence via polynomial transform. Neural computation is used to combine the derived individual principal axes solutions for each object in a committee machine formulation and to obtain the polynomial transform based on extracted control points using a multi layer perceptrons (MLP). Three examples are presented to demonstrate the techniques involved in the process. The first example uses four Gaussian clusters and focuses on the combination of the multiple transforms into a composite transform using finite mixture modeling techniques. The next examples present the complete process for prostate cancer registration and breast sequence analysis respectively. To verify performance, the results are compared to non-neural based implementations and other existing registration methods.

The authors developed an image-guided biopsy simulation system that uses advanced image analysis and computer graphics techniques. First, they reconstruct three-dimensional (3-D) computerized prostate models with accurate 3-D representation of all internal anatomical structures of the prostate. The prostate needle biopsy simulation system is then implemented by an interactive 3-D visualization system with various realistic imaging probes and needles for examination and path planning. They show two specific ways such a simulation system can be used: (a) as a virtual simulation system where a surgeon can sit in front of the computer to plan better needle paths and can practice the actual biopsy procedure before he or she actually performs on a patient and (b) for validating the effectiveness of various biopsy techniques in prostate cancer detection and tumor volume estimation.

Quantitative analysis of magnetic resonance (MR) images is a powerful tool for image-guided diagnosis, monitoring, and intervention. The major tasks involve tissue quantification and image segmentation where both the pixel and context images are considered. To extract clinically useful information from images that might be lacking in prior knowledge, the authors introduce an unsupervised tissue characterization algorithm that is both statistically principled and patient specific. The method uses adaptive standard finite normal mixture and inhomogeneous Markov random field models, whose parameters are estimated using expectation-maximization and relaxation labeling algorithms under information theoretic criteria. The authors demonstrate the successful applications of the approach with synthetic data sets and then with real MR brain images.

Summary: Phenotypic Up-regulated Gene Support Vector Machine (PUGSVM) is a cancer Biomedical Informatics Grid (caBIG™) analytical tool for multiclass gene selection and classification. PUGSVM addresses the problem of imbalanced class separability, small sample size and high gene space dimensionality, where multiclass gene markers are defined by the union of one-versus-everyone phenotypic upregulated genes, and used by a well-matched one-versus-rest support vector machine. PUGSVM provides a simple yet more accurate strategy to identify statistically reproducible mechanistic marker genes for characterization of heterogeneous diseases. Availability: http://www.cbil.ece.vt.edu/caBIG-PUGSVM.htm. Contact: yuewang@vt.edu Supplementary information: Supplementary data are available at Bioinformatics online.

Identification of condition-specific protein interaction subnetworks has emerged as an attractive research field to reveal molecular mechanisms of diseases and provide reliable network biomarkers for disease diagnosis. Several methods have been proposed, which integrate gene expression and protein-protein interaction (PPI) data to identify subnetworks. However, existing methods treat differential expression of genes and network topology independently, which is an oversimplified assumption to model real biological systems. In this paper, we propose a sampling-based subnetwork identification approach to take into account the dependency between gene expression and network topology. Specifically, we apply Markov random field (MRF) theory to model the dependency of genes in PPI network using a Bayesian framework, followed by a Markov Chain Monte Carlo (MCMC) approach to identify significant subnetworks. The MCMC approach estimates the posterior distribution of genes' significant scores and network structure iteratively. Experimental results on both synthetic data and real breast cancer data demonstrated the effectiveness of the proposed method in identifying subnetworks, especially several functionally important, aberrant subnetworks associated with pathways involved in the development and recurrence of breast cancer.

Nanomaterial has demonstrated its advantages in a variety of application fields such as biosensors and next-generation computer chips. It is important yet challenging to precisely capture and recover the morphological characteristics of nanomaterial for nanomanufacturing quality control. We propose a computer vision-assisted approach in this paper to recover the structural details of nanowires and their spatial distribution. First, we develop a geometric model for nanowire length measurement and a model calibration method based on statistical fitting to deal with bias. Second, we devise a morphology-based detection algorithm to identify nanowires from Scanning Electron Microscope (SEM) images in the presence of defects, and design a simple yet novel similarity function for correspondence establishment. The identified nanowires are fed into the geometric model to calculate their lengths. The experimental results show that our proposed method can effectively identify nanowires and establish correspondence with high detection accuracy and low false alarms in estimating lengths of a great number of nanowires on a substrate. Our approach can be readily integrated to assist nanomanufacturing and its quality control.

Motivation: The identification of gene regulatory modules is an important yet challenging problem in computational biology. While many computational methods have been proposed to identify regulatory modules, their initial success is largely compromised by a high rate of false positives, especially when applied to human cancer studies. New strategies are needed for reliable regulatory module identification.Results: We present a new approach, namely multilevel support vector regression (ml-SVR), to systematically identify condition-specific regulatory modules. The approach is built upon a multilevel analysis strategy designed for suppressing false positive predictions. With this strategy, a regulatory module becomes ever more significant as more relevant gene sets are formed at finer levels. At each level, a two-stage support vector regression (SVR) method is utilized to help reduce false positive predictions by integrating binding motif information and gene expression data; a significant analysis procedure is followed to assess the significance of each regulatory module. To evaluate the effectiveness of the proposed strategy, we first compared the ml-SVR approach with other existing methods on simulation data and yeast cell cycle data. The resulting performance shows that the ml-SVR approach outperforms other methods in the identification of both regulators and their target genes. We then applied our method to breast cancer cell line data to identify condition-specific regulatory modules associated with estrogen treatment. Experimental results show that our method can identify biologically meaningful regulatory modules related to estrogen signaling and action in breast cancer.Availability and implementation: The ml-SVR MATLAB package can be downloaded at http://www.cbil.ece.vt.edu/software.htmContact: xuan@vt.eduSupplementary information: Supplementary data are available at Bioinformatics online.

A learning-based approach integrating the use of pixel level statistical modeling and spiculation detection is presented for the segmentation of mammographic masses with ill-defined margins and spiculations. The algorithm involves a multi-phase pixel-level classification, using a comprehensive group of regional features, to generate a pixel level mass-conditional probability map (PM). Then, mass candidate along with background clutters are extracted from the PM by integrating the prior knowledge of shape and location of masses. A multi-scale steerable ridge detection algorithm is employed to detect spiculations. Finally, all the object level findings, including mass candidate, detected spiculations, and clutters, along with the PM are integrated by graph cuts to generate the final segmentation mask. The method was tested on 54 masses (51 malignant and 3 benign), all with ill-defined margins and irregular shape or spiculations. The ground truth delineations were provided by five experienced radiologists. Area overlap ratio of 0.766 (±0.144) and 0.642 (±0.173) were obtained for segmenting the whole mass and only the margin portion, respectively. Williams index of area and contour based measurements indicated that segmentation results of the algorithm well agreed with the radiologists' delineation. Most importantly, the proposed approach is capable of including mass margin and its extension which are considered as key features for breast lesion analyses.

In this paper, we propose a learning-based algorithm for automatic medical image annotation based on sparse aggregation of learned local appearance cues, achieving high accuracy and robustness against severe diseases, imaging artifacts, occlusion, or missing data. The algorithm starts with a number of landmark detectors to collect local appearance cues throughout the image, which are subsequently verified by a group of learned sparse spatial configuration models. In most cases, a decision could already be made at this stage by simply aggregating the verified detections. For the remaining cases, an additional global appearance filtering step is employed to provide complementary information to make the final decision. This approach is evaluated on a large-scale chest radiograph view identification task, demonstrating an almost perfect performance of 99.98% for a posteroanterior/anteroposterior (PA-AP) and lateral view position identification task, compared with the recently reported large-scale result of only 98.2% [1]. Our approach also achieved the best accuracies for a three-class and a multi-class radiograph annotation task, when compared with other state of the art algorithms. Our algorithm has been integrated into an advanced image visualization workstation, enabling content-sensitive hanging-protocols and auto-invocation of a computer aided detection algorithm for PA-AP chest images.

Identifying breast cancer susceptibility genes is one of the key challenges in breast cancer research. Conventional gene-based approaches can identify patterns of gene activity that sub-classify tumors, by which genes with known breast cancer mutations are typically not detected. In this study, we present a novel network motif-based approach that integrates biological network topology and high-throughput gene expression data to identify markers not as individual genes but as network motifs. We observed that the network motifs are more reproducible than individual marker genes selected without biological network information, and that they achieve higher accuracy in the classification of metastatic versus non-metastatic tumors.

Early detection of Ground Glass Nodule (GGN) in lung Computed Tomography (CT) images is important for lung cancer prognosis. Due to its indistinct boundaries, manual detection and segmentation of GGN is labor-intensive and problematic. In this paper, we propose a novel multi-level learning-based framework for automatic detection and segmentation of GGN in lung CT images. Our main contributions are: firstly, a multi-level statistical learning-based approach that seamlessly integrates segmentation and detection to improve the overall accuracy for GGN detection (in a subvolume). The classification is done at two levels, both voxel-level and object-level. The algorithm starts with a three-phase voxel-level classification step, using volumetric features computed per voxel to generate a GGN class-conditional probability map. GGN candidates are then extracted from this probability map by integrating prior knowledge of shape and location, and the GGN object-level classifier is used to determine the occurrence of the GGN. Secondly, an extensive set of volumetric features are used to capture the GGN appearance. Finally, to our best knowledge, the GGN dataset used for experiments is an order of magnitude larger than previous work. The effectiveness of our method is demonstrated on a dataset of 1100 subvolumes (100 containing GGNs) extracted from about 200 subjects.

Motivation: Significant efforts have been made to acquire data under different conditions and to construct static networks that can explain various gene regulation mechanisms. However, gene regulatory networks are dynamic and condition-specific; under different conditions, networks exhibit different regulation patterns accompanied by different transcriptional network topologies. Thus, an investigation on the topological changes in transcriptional networks can facilitate the understanding of cell development or provide novel insights into the pathophysiology of certain diseases, and help identify the key genetic players that could serve as biomarkers or drug targets. Results: Here, we report a differential dependency network (DDN) analysis to detect statistically significant topological changes in the transcriptional networks between two biological conditions. We propose a local dependency model to represent the local structures of a network by a set of conditional probabilities. We develop an efficient learning algorithm to learn the local dependency model using the Lasso technique. A permutation test is subsequently performed to estimate the statistical significance of each learned local structure. In testing on a simulation dataset, the proposed algorithm accurately detected all the genes with network topological changes. The method was then applied to the estrogen-dependent T-47D estrogen receptor-positive (ER+) breast cancer cell line datasets and human and mouse embryonic stem cell datasets. In both experiments using real microarray datasets, the proposed method produced biologically meaningful results. We expect DDN to emerge as an important bioinformatics tool in transcriptional network analyses. While we focus specifically on transcriptional networks, the DDN method we introduce here is generally applicable to other biological networks with similar characteristics. Availability: The DDN MATLAB toolbox and experiment data are available at http://www.cbil.ece.vt.edu/software.htm. Contact: yuewang@vt.edu Supplementary information: Supplementary data are available at Bioinformatics online.

In studying the relationship between risk factors and breast cancer, the growth patterns of fat pads and glandular tissues are considered as important biomarkers. The aim of this study is to measure the growth pattern statistics of rat mammary pads and glandular tissues with magnetic resonance (MR) time sequence images. In this paper, we proposed methods containing sequential steps to extract and analyze imaging biomarkers of rat mammary pad and glandular tissues. Firstly, to accurately segment out pads in MR images with noisy bias filed, we proposed a level set method combining local binary fitting (LBF) and geodesic active contour (GAC). The salient glandular tissue regions within the fat pads are further extracted by a scale-space analysis procedure. Then, the volume data of a single rat at different time points are aligned through profile correlation analysis. Finally, the growth rates are calculated and compared to show the changing patterns of fat pads and glandular tissues within separate groups. The experimental results showed the great utility of this approach in providing accurate measurements for novel risk factors of breast cancer.

Adaptive radiation therapy (ART) requires an on-line modification of the treatment plan to compensate for the motion of organs. In this paper, an improved multi-leaf collimator (MLC) deformation approach is proposed to accurately compensate for the organ motion between the planning and treatment scans for ART. Instead of using slice-by-slice 2-D deformation field as in the original MLC deformation method, 3-D deformation field is first recovered by a volumetric deformable registration method to guide the MLC modification. In order to minimize the toxicity on organ-at-risk (OAR), the deformation fields of the OAR and planning target volume (PTV) are jointly used to adjust the MLC sequence of the original plan. The proposed approach has been applied to the radiotherapy for prostate cancer. Preliminary experimental results have demonstrated that the proposed method outperformed the original MLC approach with much reduced toxicity on OAR while maintaining great radiation efficacy on PTV.

To accommodate the inter- and intra-fractional motion of internal organs in prostate cancer treatment, a large margin (5mm-25mm) has often to be considered during radiation therapy planning. Normally, the inter-fractional motion is more substantial than the intra-fractional counterpart. Therefore, the study of inter-fractional motion pattern is of special interest for adaptive radiation therapy. Existing methods on organ motion analysis mainly focus on the deviation of an organ's shape from its mean shape. The deviation information is helpful in choosing a statistically proper margin, but is of limited use for plan adaptation. In this paper, we propose a new deformation analysis method that can be directly used for plan adaptation. First, deformation estimation is accomplished by a fast deformable registration method, which utilizes a contour based multi-grid strategy to register treatment cone-beam CT (CBCT) images with planning CT images. Second, dominant deformation modes are extracted by a novel deformation analysis approach. To be specific, a cooperative principal component analysis (PCA) method is developed to analyze the deformation field in a coarse-to-fine strategy. The deformation modes are initialized by applying PCA on the organs as a whole and refined by analyzing the individual organs subsequently. The experimental results show that the organ motion can be well characterized by a few dominant deformation modes. Based on the dominant modes, a corresponding set of dominant modal plans could be generated for further optimization. Ultimately, an adaptive plan for each treatment can be obtained on-line while the margin can be effectively reduced to minimize the unnecessary radiation dosage.

In this study, we present a clinically guided technical method for content-based categorization of mammographic masses. Our work is motivated by the continuing effort in content-based image annotation and retrieval to extract and model the semantic content of images. Specifically, we classified the shape and margin of mammographic mass into different categories, which are designated by radiologists according to descriptors from Breast Imaging Reporting and Data System Atlas (BI-RADS). Experiments were conducted within subsets selected from datasets consisting of 346 masses. In the experiments that categorize lesion shape, we obtained a precision of 70% with three classes and 87.4% with two classes. In the experiments that categorize margin, we obtained precisions of 69.4% and 74.7% for the use of four and three classes, respectively. In this study, we intend to demonstrate that this classification based method is applicable in extracting the semantic characteristics of mass appearances, and thus has the potential to be used for automatic categorization and retrieval tasks in clinical applications.

One of the major goals in microarray data analysis is to identify biomarkers and build a classification model for future prediction. Many traditional statistical models, based on microarray data alone, often fail in identifying biologically meaningful genes, which should have synergistic effect on determine the clinical outcomes through some interactions rather than work individually. In this paper, we proposed a network-constrained support vector machine (nSVM) for classification by incorporating prior knowledge, which could be protein-protein interactions, protein-gene regulation relationships or pathways information. Specifically, we use Laplacian matrix to represent gene-gene interaction network to regularize the objective function of SVM, which imposes the smoothness of coefficients over the network. The experimental results on simulation and real microarray datasets demonstrate that our method could not only improve classification performance compared to conventional SVM, but more importantly, it could identify significant sub-networks belonging to several pathways which might be related to underlying mechanism associated with clinical outcomes.

Ontological concept descriptions of scene objects and aggregates play an essential role in model-based scene interpretation. An aggregate specifies a set of objects with certain properties and relations which together constitute a meaningful scene entity. In this paper we show how ontological concept descriptions for spatially related objects and aggregates can be learnt from positive and negative examples. Our approach features a rich representation language encompassing quantitative and qualitative attributes and relations. Using examples from the buildings domain, we show that learnt aggregate concepts for window arrays, balconies and other structures can be successfully employed in the conceptual knowledge base of a scene interpretation system. Furthermore we argue that our approach can be extended to cover ontological concepts of any kind, with very few restrictions.

Many statistical methods often fail to identify biologically meaningful biomarkers related to a specific disease under study from expression data alone. In this paper, we develop a novel strategy, namely knowledge-driven multi-level independent component analysis (ICA), to infer regulatory signals and identify biologically relevant biomarkers from microarray data. Specifically, based on multi-level clustering results and partial prior knowledge, we apply ICA to find stable disease specific linear regulatory modes and then extract associated biomarker genes. A statistical test is designed to evaluate the significance of transcription factor enrichment for extracted gene set based on motif information. The experimental results on an Rsf-1 induced microarray data set show that our knowledge-driven method can extract more biologically meaningful biomarkers with significant enrichment of transcription factors related to ovarian cancer compared to other gene selection methods with/without prior knowledge.

This paper gives an overview of statistical and machine learning-based feature selection and pattern classification algorithms and their application in molecular cancer classification or phenotype prediction. In particular, the paper focuses on the use of these computational methods for gene and peak selection from microarray and mass spectrometry data, respectively. The selected features are presented to a classifier for phenotype prediction.

The polarization state of the light transmitting through a specimen can provide useful information concerning the optical property of the sample. We present a polarization imaging device that measures the Stokes components of the trans-illuminant light. Particularly, we develop an image analysis algorithm using texture analysis and support vector machine for tissue classification. The experiment has been conducted using rat breast tissue in health and with cancer. It is demonstrated that the Stokes images can improve the classification performance of the algorithm. With the incorporation of the multi-polarization images, it is shown that the diagnosis accuracy can be further improved over that using intensity image only.

In studying the relationship between risk factors and breast cancer, growth patterns of the fat pads and glandular tissues are important features. In other words, these features can be regarded as breast cancer related biomarkers. Accordingly, the goal of this rodent model study is to measure the size of mammary pads over the time and to quantify the development of glandular structures. To achieve this goal, we propose a hierarchical approach to segmenting out rat body, mammary fat pads and glandular tissues in Tl weighted magnetic resonance (T1W-MR) images. Particularly, we have developed an approach combining watershed transform and region competition for improved fat pad segmentation, and a method for glandular tissue segmentation through scale-space analysis. For segmenting fat pads, an efficient strategy, termed as competition propagation, is developed to propagate the region competition result from one slice to next slice, resulting in a fast convergence in region competition algorithm otherwise computationally costly. The glandular tissues, as the fine structures within the fat pads, are then located using scale-space analysis and segmented out by analyzing their local iso-shape patterns. These methods have been applied to 18 volumetric sets of T1W-MR images acquired from this study. The experimental results showed the great utility of the proposed approaches as they can provide accurate measurements to assess novel risk factors for breast cancer.

In studying the relationship between risk factors and breast cancer, growth patterns of the fat pads and glandular tissues are important features. The goal of this small animal study is to measure the size of mammary pads over the time. To achieve this goal, we propose a hierarchical approach to segmenting out rat body, mammary fat pads and evaluating their development in Tl weighted magnetic resonance (TlW-MR) images. Particularly, we have developed a new approach combining watershed transform and region competition for improved fat pad segmentation. An efficient strategy, termed as competition propagation, is developed to propagate the region competition result from one slice to next slice, resulting in a fast convergence in region competition algorithm otherwise computationally costly. To evaluate the development of the fat pads, the volume data of the scans for a single rat to compare are aligned and the common valid range is acquired through correlation analysis. The method has been applied to 18 volumetric sets of Tl W-MR images acquired from this study. The experimental results showed the great utility of this approach as it can provide accurate measurements to assess novel risk factors for breast cancer.

The purpose of this study is to develop a Content-Based Image Retrieval (CBIR) system for mammographic computer-aided diagnosis. We have investigated the potential of using shape, texture, and intensity features to categorize masses that may lead to sorting similar image patterns in order to facilitate clinical viewing of mammographic masses. Experiments were conducted within a database that contains 243 masses (122 benign and 121 malignant). The retrieval performances using the individual feature was evaluated, and the best precision was determined to be 79.9% when using the curvature scale space descriptor (CSSD). By combining several selected shape features for retrieval, the precision was found to improve to 81.4%. By combining the shape, texture, and intensity features together, the precision was found to improve to 82.3%.

In recent years, there has been an increasing interest in studying the propagation of polarized light in biological cells and tissues. This paper presents a novel approach to cell or tissue imaging using a full Stokes imaging system with advanced polarization image analysis algorithms for improved diagnostics. The key component of the Stokes imaging system is the electrically tunable retarder, enabling high-speed operation of the system to acquire four intensity images sequentially. From the acquired intensity images, four Stokes vector images can be computed to obtain complete polarization information. Polarization image analysis algorithms are then developed to analyze Stokes polarization images for cell or tissue classification. Specifically, wavelet transforms are first applied to the Stokes components for initial feature analysis and extraction. Artificial neural networks (ANNs) are then used to extract diagnostic features for improved classification and prediction. In this study, phantom experiments have been conducted using a prototyped Stokes polarization imaging device. In particular, several types of phantoms, consisting of polystyrene latex spheres in various diameters, were prepared to simulate different conditions of epidermal layer of skin. The experimental results from phantom studies and a plant cell study show that the classification performance using Stokes images is significantly improved over that using the intensity image only.

Though supervised and unsupervised analyses of genomic data have been intensively studied in recent years, little effort has been made to discover the structural information contained in the data. In this work, we propose a stability analysis guided supervised clustering and visualization method aiming to discover the hierarchical structure in gene expression data, which we call the "tree of phenotypes". We applied the method on two multiclass gene expression microarray data sets and presented the biological plausibility of the learned trees. We also tested the multiclass classifiers built on the learned trees and demonstrated their good classification performance.

We present a novel algorithm that combines a recurrent neural network (RNN) and two swarm intelligence (SI) methods to infer a gene regulatory network (GRN) from time course gene expression data. The algorithm uses ant colony optimization (ACO) to identify the optimal architecture of an RNN, while the weights of the RNN are optimized using particle swarm optimization (PSO). Our goal is to construct an RNN whose response mimics gene expression data generated by time course DNA microarray experiments. We observed promising results in applying the proposed hybrid SI-RNN algorithm to infer networks of interaction from simulated and real-world gene expression data.

In this paper, we report a new gene clustering approach - non-negative independent component analysis (nICA) - for microarray data analysis. Due to positive nature of molecular expressions, nICA fits better to the reality of corresponding putative biological processes. In conjunction with nICA model, VIsual Statistical Data Analyzer (VISDA) is applied to group genes into modules in the latent variable space. The experimental results show that significant enrichment of gene annotations within clusters can be obtained. Keywords -non-negative ICA, latent variable model, gene clustering, module discovery, microarray data analysis

We present a novel algorithm combining artificial neural networks and swarm intelligence (SI) methods to infer network interactions. The algorithm uses ant colony optimization (ACO) to identify the optimal architecture of a recurrent neural network (RNN), while the weights of the RNN are optimized using particle swarm optimization (PSO). Our goal is to construct an RNN that mimics the true structure of an unknown network and the time-series data that the network generated. We applied the proposed hybrid SI-RNN algorithm to infer a simulated genetic network. The results indicate that the algorithm has a promising potential to infer complex interactions such as gene regulatory networks from time-series gene expression data. I. INTRODUCTION inference algorithm based on GAs for the optimization of the influence matrix of gene regulatory network. In (13), GAs and ANNs are combined to determine gene interactions in temporal gene expression data. In this paper, we propose to apply a hybrid of ANNs and swarm intelligence (SI) methods (12) to infer network interactions from time-series data. The architecture and the synaptic weights of a recurrent neural network (RNN) are optimized using ant colony optimization (ACO) and particle swarm optimization (PSO) methods, respectively. Unlike previous computational methods, which targeted at one-step- ahead prediction of time-series data (13), our method enables a multi-step-ahead prediction. This is achieved through our RNN, which is self-evolutionary. The RNN starts with a given initial condition, evolves, and eventually reaches final states. The proposed hybrid SI-RNN algorithm selects the architecture of the RNN and weights not only to mimic the response of the unknown network at each time point but also to identify the structure of the network that generated the time-series data. This is a challenging task given that there may be many possible structures with responses that closely match the generated data. The algorithm evaluates various structures through the cross- validation method to avoid the selection of a wrong structure and to make sure that the correct structure is identified despite the presence of noise and complexity of the unknown network. We successfully applied the algorithm to infer simulated network interactions.

Image-based change quantitation has been recognized as a promising tool for accurate assessment of tumor's early response to chemoprevention in cancer research. For example, various changes on breast density and vascularity in glandular tissue are the indicators of early response to treatment. Accurate extraction of glandular tissue from pre- and postcontrast magnetic resonance (MR) images requires a nonrigid registration of sequential MR images embedded with local deformations. This paper reports a newly developed registration method that aligns MR breast images using finite-element deformable sheet-curve models. Specifically, deformable curves are constructed to match the boundaries dynamically, while a deformable sheet of thin-plate splines is designed to model complex local deformations. The experimental results on both digital phantoms and real MR breast images using the new method have been compared to point-based thin-plate-spline (TPS) approach, and have demonstrated a significant and robust improvement in both boundary alignment and local deformation recovery.

Dynamic functional imaging techniques promise powerful tools for the visualization and elucidation of important disease-causing physiologic processes in living tissue. Most applications aim to find temporal-spatial patterns associated with different disease stages. When multiple functional biomarkers are targeted, imagery signals often represent a composite of more than one distinct functional source independent of spatial resolution. Here we introduce a hybrid blind source separation method that is able to factorize underlying source images and time activity curves from dynamically mixed image sequence. The algorithm is based on a compartment latent variable model, whose parameters are estimated using multivariate clustering and/or independent component analysis. We demonstrate the principle of the approach on tumor microvascular characterization using dynamic contrast-enhanced magnetic resonance imaging for monitoring response to anti-angiogenic therapies.

Functional-molecular imaging techniques promise powerful tools for the visualization and elucidation of important disease-causing physiologic-molecular processes in living tissue. Most applications aim to find temporal-spatial patterns associated with different disease stages. When multiple agents are used, imagery signals often represent a composite of more than one distinct source due to functional-molecular biomarker heterogeneity, independent of spatial resolution. We therefore introduce a hybrid decomposition algorithm, which allows for a computed simultaneous imaging of multiple biomarkers. The method is based on a combination of time-activity curve clustering, pixel subset selection, and independent component analysis. We demonstrate the principle of the approach on an image data set, and we then apply the method to the tumor vascular characterization using dynamic contrast-enhanced magnetic resonance imaging and brain neuro-transporter imaging using dynamic positron emission tomography.

It is clinically important to develop novel approaches to accurately assess early response to chemoprevention. We propose to quantitatively measure changes of breast density and breast vascularity in glandular tissue to assess early response to chemoprevention. In order to accurately extract glandular tissue using pre- and post-contrast magnetic resonance (MR) images, non-rigid registration is the key to align MR images by recovering the local deformations. In this paper, a new registration method has been developed using finite-element deformable sheet-curve models to accurately register MR breast images for extraction of glandular tissue. Finite-element deformable sheet-curve models are coupling dynamic systems to physically model the boundary deformation and image deformation. Specifically, deformable curves are used to obtain a reliable matching of the boundaries using physically constrained deformations. A deformable sheet with the energy functional of thin-plate-splines is used to model complex local deformations between the MR breast images. Finite-element deformable sheet-curve models have been applied to register both digital phantoms and MR breast image. The experimental results have been compared to point-based methods such as the thin-plate-spline (TPS) approach, which demonstrates that our method is of a great improvement over point-based registration methods in both boundary alignment and local deformation recovery.

Presents a task-specific segmentation method that incorporates semantic knowledge into data-driven segmentation process through different region merge scores. Starting from a simple region growing algorithm which results in over-segmented regions, the authors apply a region merging method designed specifically for each task such as road extraction or vegetation area identification. Further, edge information is integrated to verify and correct region boundaries. The experimental results show that this method can reliably extract areas of interest such as roads and vegetation areas in Landsat images.

This paper presents an effective two-step scheme for automatic object detection in computed radiography (CR) images. First, various structure elements of the morphological filters are used to effectively distinguish the foreign object candidates from the complex background structures. Secondly, active contour models are employed to accurately outline the morphological shapes of the suspicious foreign objects to further reduce the rate of false alarms. The proposed methods are tested with a database of 50 hand-wrist computed radiographic images containing various types of foreign objects. Our experimental results demonstrate that the combined use of morphological filters and active contour models can provide an effective automatic detection of foreign objects in CR images and the accurate descriptions of object characteristics.

The diagnosis of localized prostate cancer is carried out by standard core needle biopsies under guidance of transrectal ultrasound imaging of the prostate gland. This paper describes a 3D model supported virtual environment for prostate cancer diagnosis and biopsy design. A 3D deformable reconstruction algorithm is developed to define an object surface from digitally-imaged surgical specimens. A virtual environment with a multimodal visualization capability is integrated to simulate prostate biopsy protocols. The new system permits an accurate graphical modeling of the object of interest, the localization and quantification of tumors, and the definition of the pathways of biopsy needles. The technique allows the medical experts to probe and manipulate the data in 3D view space and to evaluate the performance of simulated biopsies subsequently optimize biopsy techniques. Results and analysis of our experiments demonstrate the effectiveness of the individual modular components of the approach. We conclude with an application of the complete framework to a prostate biopsy simulation and evaluation task.

The discrete wavelet transform provides a new framework of multiresolution space-frequency representation. Its preliminary applications in medical image compression are promising. An accurate modeling of the spatial and frequency characteristics of the wavelet coefficients is a key to designing efficient and accurate quantization for wavelet-based source coding. In this study, we investigate the modeling of a finite mixture distribution of the wavelet coefficients, within the context of information theory and statistical model identification. Using a finite generalized Gaussian mixture to model the overall distribution of the coefficients, an unsupervised learning procedure is developed to quantify the histogram through a tripled adaptive algorithm including detection of the number of local kernels, approximation of the shape of local kernels, and estimation of model parameter values. Our preliminary experimental results indicate that the unsupervised and adaptive histogram quantification can efficiently and accurately fit to the overall mixture distribution of the coefficients for any given frequency subband with unknown characteristics.

The authors present a method that combines region growing and edge detection for magnetic resonance (MR) brain image segmentation. Starting with a simple region growing algorithm which produces an over segmented image, the authors apply a sophisticated region merging method which is capable of handling complex image structures. Edge information is then integrated to verify and, where necessary, to correct region boundaries. The results show that this method is reliable and efficient for MR brain image segmentation.

Non-rigid image registration is a prerequisite for many medical image analysis applications, such as image fusion of multi-modality images and quantitative change analysis of a temporal sequence in computer-aided diagnosis. By establishing the point correspondence of the extracted feature points, it is possible to recover the deformation using nonlinear interpolation methods such as the thin-plate-spline approach. However, it is a difficulty task to establish an exact point correspondence due to the high complexity of the nonlinear deformation existing in medical images. In this paper, a mixture of principal axes registration (mPAR) method is proposed to resolve the correspondence problem through a neural computational approach. The novel feature of mPAR is to align two point sets without needing to establish an explicit point correspondence. Instead, it aligns the two point sets by minimizing the relative entropy between their probability distributions, resulting in a maximum likelihood estimate of the transformation matrix. The registration process consists of: (1) a finite mixture scheme to establish an improved point correspondence and (2) a multilayer perceptron (MLP) neural network to recover the nonlinear deformation. The neural computation for registration used a committee machine to obtain a mixture of piecewise rigid registrations, which gives a reliable point correspondence using multiple extracted objects in a finite mixture scheme. Then the MLP was used to determine the coefficients of a polynomial transform using extracted cross-points of elongated structures as control points. We have applied our mPAR method to a temporal sequence of mammograms from a single patient. The experimental results show that mPAR not only improves the accuracy of the point correspondence but also results in a desirable error-resilience property for control point selection errors.

Non-rigid image registration is a prerequisite for many medical imaging applications such as change analysis in image-based diagnosis and therapy assessment. Nonlinear interpolation methods may be used to recover the deformation if the correspondence of the extracted feature points is available. However, it may be very difficult to establish such correspondence at an initial stage when confronted with large and complex deformation. In this paper, a mixture of principal axes registration (mPAR) is proposed to tackle the correspondence problem using a neural computation method. The feature is to align two point sets without needing to establish the explicit point correspondence. The mPAR aligns two point sets by minimizing the relative entropy between their probability distributions resulting in a maximum likelihood estimate of the transformation mixture. The neural computation for the mPAR is developed using a committee machine to obtain a mixture of piece-wise rigid registrations. The complete registration process consists of two steps: (1) using the mPAR to establish an improved point correspondence and (2) using a multilayer perceptron (MLP) neural network to recover the nonlinear deformation. The mPAR method has been applied to register a contrast-enhanced magnetic resonance (MR) image sequence. The experimental results show that our method not only improves the point correspondence but also results in a desirable error-resilience property for control point selection errors.

This paper presents a three-dimensional (3-D) tissue analysis method and its applications in partial volume correction and change analysis. The method uses a stochastic model-based approach and consists of two steps: (1) unsupervised tissue quantification and (2) 3-D segmentation. Firstly, the MR image volume is modeled by the standard finite normal mixture (SFNM) distribution. It has been shown that the SFNM converges to the true distribution when the pixel images are asymptotically independent. Secondly, the tissue quantification is achieved through (1) model selection by minimum description length (MDL) criterion; (2) parameter initialization by optimal histogram quantization and (3) parameter estimation by a fast EM algorithm using the global 3-D histogram rather than conventionally the raw data. Finally, we develop a 3-D segmentation method using the maximum likelihood (ML) classification and contextual Bayesian relaxation labeling (CBRL). The CBRL is developed to obtain a consistent labeling solution, based on localized SFNM formulation by using neighborhood contextual regularities. The method has been applied to partial volume correction for PET brain images and change analysis for MR breast images.

This paper presents an effective two-step scheme for automatic object detection in computed radiography (CR) images. First, various structure elements of the morphological filters, designed by incorporating available morphological features of the objects of interest including their sizes and rough shape descriptions, are used to effectively distinguish the foreign object candidates from the complex background structures. Second, since the boundaries of the objects are the key features in reflecting object characteristics, active contour models are employed to accurately outline the morphological shapes of the suspicious foreign objects to further reduce the rate of false alarms. The actual detection scheme is accomplished by jointly using these two steps. The proposed methods are tested with a database of 50 hand-wrist computed radiographic images containing various types of foreign objects. Our experimental results demonstrate that the combined use of morphological filters and active contour models can provide an effective automatic detection of foreign objects in CR images achieving good sensitivity and specificity, and the accurate descriptions of the object morphological characteristics.

As a step toward understanding complex spatial distribution patterns of prostate cancers, a 3D master model of the prostate, showing major anatomical structures and probability maps of the location of tumors, has been pilot developed. A virtual environment supported by the 3D master model and in vivo imaging features, will be used to evaluate, simulate, and optimize the image guided needle biopsy and radiation therapy, thus potentially improving the efficacy of prostate cancer diagnosis, staging, and treatment. A deformable graphics algorithm has been developed to reconstruct the graphics models from 200 serially sectioned whole mount radical prostatectomy specimens and to support computerized needle biopsy simulations. For the construction of a generic model, a principal-axes 3D registration technique has been developed. Simulated evaluation and real data experiment have shown the satisfactory performance of the method in constructing initial generic model with localized prostate cancer placement. For the construction of statistical model, a blended model registration technique is advanced to perform a non-linear warping of the individual model to the generic model so that the prostate cancer probability distribution maps can be accurately positioned. The method uses a spine- surface model and a linear elastic model to dynamically deform both the surface and volume where object re-slicing is required. For the interactive visualization of the 3D master model, four modes of data display are developed: (1) transparent rendering of the generic model, (2) overlaid rendering of cancer distributions, (3) stereo rendering, and (4) true volumetric display, and a model-to-image registration technique using synthetic image phantoms is under investigation. Preliminary results have shown that use of this master model allows correct understanding of prostate cancer distribution patterns and rational optimization of prostate biopsy and radiation therapy strategies.

The diagnosis of localized prostate cancer is carried out by standard core needle biopsies under guidance of transrectal ultrasound imaging of the prostate gland. This paper describes a 3-D model supported virtual environment for prostate cancer diagnosis and biopsy design. A 3-D deformable reconstruction algorithm is developed to define object surface from digitally-imaged surgical specimens. A virtual environment with a multimodal visualization capability is integrated to simulate prostate biopsy protocols. The new system permits an accurate graphical modeling of the object of interest, the localization and quantification of tumors, and the definition of the pathways of biopsy needles. The technique allows the medical experts to probe and manipulate the data in 3-D view space and to evaluate the performance of simulated biopsies subsequently optimize biopsy techniques. Results and analysis of our experiments demonstrate the effectiveness of the individual modular components of the approach. We conclude with an application of the complete framework to a prostate biopsy simulation and evaluation task.