Bayesian Image Analysis Research Articles

Implementation a Different Segmentation Method as a Joint Prior Model to Reconstruction the Bayesian Image analysis

The basic concepts in the application of Bayesian approaches to image analysis have been introduced as advanced method. The Bayesian approach contains benefits in respect to image analysis and interpretation because it permits the use of prior knowledge concerning the situation under study. This paper use to investigate the application of some of the well-known procedures (determines number labels of image under several conditions like noise of image, resolution of image) for the Bayesian image analysis with segmentation as a joint prior model in order to estimate the Maximum Likelihood (ML). Markov random field with segmentation which resulted by mean of posterior (MP). This paper contains several sections. Firstly, includes introduction about the image analysis with, Bayes frame work and statistical background to Markov's random field and its relationship through Markov Chain Monte Carlo. Secondly, section, which directly addresses solutions by using a principle of segmentation, which is a representation in threshold, is simply type introduced. Thirdly, presents the description of Experiment of Segmentation by depend on histogram also study of the factor (one prior) and the same model by adding segmentation (joint prior) based on techniques presented in the previously section are discussed . Fourthly, this section contains on the second prior implementation and simulation by using phantom data (Castle from south East Asia) also steps of estimation. Finally, result of experiment as well as estimation and summary.

Hierarchical Bayesian image analysis: From low-level modeling to robust supervised learning

Within a supervised classification framework, labeled data are used to learn classifier parameters. Prior to that, it is generally required to perform dimensionality reduction via feature extraction. These preprocessing steps have motivated numerous research works aiming at recovering latent variables in an unsupervised context. This paper proposes a unified framework to perform classification and low-level modeling jointly. The main objective is to use the estimated latent variables as features for classification and to incorporate simultaneously supervised information to help latent variable extraction. The proposed hierarchical Bayesian model is divided into three stages: a first low-level modeling stage to estimate latent variables, a second stage clustering these features into statistically homogeneous groups and a last classification stage exploiting the (possibly badly) labeled data. Performance of the model is assessed in the specific context of hyperspectral image interpretation, unifying two standard analysis techniques, namely unmixing and classification.

Implementation A Different Segmentation Method As A Joint Prior Model To Reconstruction The Bayesian Image Analysis

Implementation A Different Segmentation Method As A Joint Prior Model To Reconstruction The Bayesian Image Analysis

Autonomous rock classification using Bayesian image analysis for Rover-based planetary exploration

A robust classification system is proposed to support autonomous geological mapping of rocky outcrops using grayscale digital images acquired by a planetary exploration rover. The classifier uses 13 Haralick textural parameters to describe the surface of rock samples, automatically catalogues this information into a 5-bin data structure, computes Bayesian probabilities, and outputs an identification.The system has been demonstrated using a library of 30 digital images of igneous, sedimentary and metamorphic rocks. The images are 3.5×3.5cm2 in size and composed of 256×256 pixels with 256 grayscale levels. They are first converted to gray level co-occurrence matrices which quantify the number of times adjacent pixels of similar intensity are present. The Haralick parameters are computed from these matrices. When all 13 parameters are used, classification accuracy, defined using an empirical scoring system, is 65% due to a large number of false positives. When the number of parameters and the choice of parameter is optimized, classification accuracy increases to 80%. The best results were achieved with 3 parameters that can be interpreted visually (angular second moment, contrast, correlation) together with two statistical parameters (sum of squares variance and difference variance) and a parameter derived from information theory (information measure of correlation II).The system has been kept simple not to draw excessive computational power from the rover. It could, however, be easily extended to handle additional parameters such as images acquired at different wavelengths.

Endothelial nuclear lamina is not required for glucocorticoid receptor nuclear import but does affect receptor-mediated transcription activation

The lamina serves to maintain the nuclear structure and stiffness while acting as a scaffold for heterochromatin and many transcriptional proteins. Its role in endothelial mechanotransduction, specifically how nuclear mechanics impact gene regulation under shear stress, is not fully understood. In this study, we successfully silenced lamin A/C in bovine aortic endothelial cells to determine its role in both glucocorticoid receptor (GR) nuclear translocation and glucocorticoid response element (GRE) transcriptional activation in response to dexamethasone and shear stress. Nuclear translocation of GR, an anti-inflammatory nuclear receptor, in response to dexamethasone or shear stress (5, 10, and 25 dyn/cm(2)) was observed via time-lapse cell imaging and quantified using a Bayesian image analysis algorithm. Transcriptional activity of the GRE promoter was assessed using a dual-luciferase reporter plasmid. We found no dependence on nuclear lamina for GR translocation from the cytoplasm into the nucleus. However, the absence of lamin A/C led to significantly increased expression of luciferase under dexamethasone and shear stress induction as well as changes in histone protein function. PCR results for NF-κB inhibitor alpha (NF-κBIA) and dual specificity phosphatase 1 (DUSP1) genes further supported our luciferase data with increased expression in the absence of lamin. Our results suggest that absence of lamin A/C does not hinder passage of GR into the nucleus, but nuclear lamina is important to properly regulate GRE transcription. Nuclear lamina, rather than histone deacetylase (HDAC), is a more significant mediator of shear stress-induced transcriptional activity, while dexamethasone-initiated transcription is more HDAC dependent. Our findings provide more insights into the molecular pathways involved in nuclear mechanotransduction.

Bayesian Image Analysis of Dexamethasone and Shear Stress-Induced Glucocorticoid Receptor Intracellular Movement

Endothelial cells are continuously exposed to hemodynamic shear stress, which has been shown to induce an array of physiological responses at the cellular and molecular levels. Uniform high shear stress is protective against vascular diseases such as atherosclerosis which preferentially occur at regions of disturbed flow and low shear. The glucocorticoid receptor (GR), a member of the steroid nuclear receptors with anti-inflammatory functions, has been shown to be activated by shear stress. Using a unique expectation-maximization (EM) algorithm based on Bayesian statistics, we have developed an image analysis algorithm to quantitatively assess GR nuclear translocation based on time-lapse images of green fluorescence protein-tagged GR (GFP-GR) under continuous exposure to a shear stress of 10 or 25 dynes/cm(2) as well as to Dexamethasone, a GR agonist. Average fluorescence brightness is generated for nucleus and cytoplasm. Real-time imaging of sheared cells revealed a steady and significant nuclear GFP-GR increase of approximately 20% within 2 h, compared to a rapid 60% increase in Dexamethasone-treated cells within 30 min. Furthermore, we found that that GFP-GR nuclear translocation under shear is not dependent on an intact cytoskeleton. Our image analysis algorithm provides a novel quantitative method to further study shear-sensitive mechanotransduction pathways in endothelial cells.

Three-dimensional Bayesian image analysis and confocal microscopy

We report methods for tackling a challenging three-dimensional (3D) deconvolution problem arising in confocal microscopy. We fit a marked point process model for the set of cells in the sample using Bayesian methods; this produces automatic or semi-automatic segmentations showing the shape, size, orientation and spatial arrangement of objects in a sample. Importantly, the methods also provide measures of uncertainty about size and shape attributes. The 3D problem is considerably more demanding computationally than the two-dimensional analogue considered in Al-Awadhi et al. [2] due to the much larger data set and higher-dimensional descriptors for objects in the image. In using Markov chain Monte Carlo simulation to draw samples from the posterior distribution, substantial computing effort can be consumed simply in reaching the main area of support of the posterior distribution. For more effective use of computation time, we use morphological techniques to help construct an initial typical image under the posterior distribution.

A Bayesian image analysis of radiation induced changes in tumor vascular permeability

This work is motivated by a quantitative Magnetic Resonance Imaging study of the relative change in tumor vascular permeability during the course of radiation therapy. The differences in tumor and healthy brain tissue physiology and pathology constitute a notable feature of the image data-spatial heterogeneity with respect to its contrast uptake profile (a surrogate for permeability) and radiation induced changes in this profile. To account for these spatial aspects of the data, we employ a Gaussian hidden Markov random field (MRF) model. The model incorporates a latent set of discrete labels from the MRF governed by a spatial regularization parameter. We estimate the MRF regularization parameter and treat the number of MRF states as a random variable and estimate it via a reversible jump Markov chain Monte Carlo algorithm. We conduct simulation studies to examine the performance of the model and compare it with a recently proposed method using the Expectation-Maximization (EM) algorithm. Simulation results show that the Bayesian algorithm performs as well, if not slightly better than the EM based algorithm. Results on real data suggest that the tumor "core" vascular permeability increases relative to healthy tissue three weeks after starting radiotherapy, which may be an opportune time to initiate chemotherapy and warrants further investigation.

Learning in Gibbsian fields: how accurate and how fast can it be?

Gibbsian fields or Markov random fields are widely used in Bayesian image analysis, but learning Gibbs models is computationally expensive. The computational complexity is pronounced by the recent minimax entropy (FRAME) models which use large neighborhoods and hundreds of parameters. In this paper, we present a common framework for learning Gibbs models. We identify two key factors that determine the accuracy and speed of learning Gibbs models: The efficiency of likelihood functions and the variance in approximating partition functions using Monte Carlo integration. We propose three new algorithms. In particular, we are interested in a maximum satellite likelihood estimator, which makes use of a set of precomputed Gibbs models called "satellites" to approximate likelihood functions. This algorithm can approximately estimate the minimax entropy model for textures in seconds in a HP workstation. The performances of various learning algorithms are compared in our experiments.

Combining belief networks and neural networks for scene segmentation

We are concerned with the problem of image segmentation, in which each pixel is assigned to one of a predefined finite number of labels. In Bayesian image analysis, this requires fusing together local predictions for the class labels with a prior model of label images. Following the work of Bouman and Shapiro (1994), we consider the use of tree-structured belief networks (TSBNs) as prior models. The parameters in the TSBN are trained using a maximum-likelihood objective function with the EM algorithm and the resulting model is evaluated by calculating how efficiently it codes label images. A number of authors have used Gaussian mixture models to connect the label field to the image data. We compare this approach to the scaled-likelihood method of Smyth (1994) and Morgan and Bourlard (1995), where local predictions of pixel classification from neural networks are fused with the TSBN prior. Our results show a higher performance is obtained with the neural networks. We evaluate the classification results obtained and emphasize not only the maximum a posteriori segmentation, but also the uncertainty, as evidenced e.g., by the pixelwise posterior marginal entropies. We also investigate the use of conditional maximum-likelihood training for the TSBN and find that this gives rise to improved classification performance over the ML-trained TSBN.

Approximations for Gibbs Distribution Normalising Constants

A key difficulty in the use of Gibbs prior distributions in Bayesian image analysis is the intractability of the normalisation constant. One approach is to perform off-line simulations which allow a calibration of normalisation constant against prior parameter. In this paper the reverse-logistic regression approach to calibration will be examined for various Gibbs distributions and explicit parametric equations will be proposed. A simple method for combining separate calibrations will be illustrated and the relationship between normalisation constant and image size will be explored with an empirical approximation proposed.

Coloured Voronoi tessellations for Bayesian image analysis and reservoir modelling

Coloured Voronoi tessellations for Bayesian image analysis and reservoir modelling

Coloured Voronoi tessellations for Bayesian image analysis and reservoir modelling

A new flexible prior for Bayesian image analysis and reservoir modelling is defined in terms of interacting coloured Voronoi cells described by a certain nearest-neighbour Markov point process. This prior can be defined in both two and three (as well as higher) dimensions, and simple MCMC algorithms can be used for drawing inference from the posterior distribution. Various 2D and 3D applications are considered.

Estimation of the Head Sensitivity Function in Scanning Magnetoresistance Microscopy

We apply Bayesian image analysis techniques to a problem in a newly developed scanned probe technology that uses commercial magnetoresistive (MR) record and playback heads as probes to sense magnetic fields. This technology can be used for magnetic imaging and for evaluating playback and record processes in magnetic recording. In MR microscopy, an MR head is raster scanned while in physical contact with a magnetic sample (e.g., hard disk media, tape, or fine magnetic particles). By plotting the MR resistance as a function of position, a very high resolution (on the order of .1 × 1.0μm) magnetic image of the sample is constructed. This case study focuses on characterizing the head sensitivity function (HSF), which depends on the physical dimensions and the magnetic properties of the MR head. These sensitivity functions are of great practical interest because they ultimately relate to the head's performance in a high-density data storage environment. Estimating the HSF requires a deconvolution that has features that prevent the problem from being straightforward: both the HSF and the source being scanned are unknown, and there is a substantial amount of correlated noise in the scanned image. We take a Bayesian approach to model and estimate the HSF, while accounting for noise and other nuisance effects such as thermal drift. Besides yielding a point estimate, which is a fairly difficult task here, this approach also quantifies uncertainty so we can assess whether certain features of the estimated head sensitivity function appear to be genuine.

Bayesian Image Analysis and the Disaggregation of Rainfall

Abstract The applicability of meteorological general circulation models (GCMs) is limited by their spatial resolution. In this paper, a method is developed for improving the resolution of GCM-generated rainfall fields, using ideas from Bayesian image analysis to improve the resolution of the binary wet–dry image. This approach incorporates both the spatial and temporal memory of the rainfall field and can be adapted to utilize any available physical information. The method is illustrated using data from a network of weather radar stations in Arkansas, and some informal diagnostic procedures are developed for assessing the adequacy of the underlying model.

Bayesian Morphology: Fast Unsupervised Bayesian Image Analysis

We consider the problems of image segmentation and classification, and image restoration when the true image is made up of a small number of (unordered) colors. Our emphasis is on both performance and speed; speed has become increasingly important for analyzing large images and multispectral images with many bands, processing large image databases, real-time or near realtime image analysis, and the online analysis of video. Bayesian image analysis provides an elegant solution to these problems, but it is computationally expensive, and the solutions it provides may be sensitive to unrealistic global properties of the models on which it is based. The ICM algorithm is faster and based on the local properties of the models underlying Bayesian image analysis; parameter estimation is performed iteratively via pseudolikelihood. Mathematical morphology is faster again and is widely considered to perform well, but lacks a statistical basis; method selection (analogous to parameter estimation) is done in a rather ad hoc manner. We propose Bayesian morphology, a synthesis of these methods that attempts to combine the speed of mathematical morphology with the principled statistical basis of ICM. The key observation is that when the original image is discrete (or if an initial segmentation has been carried out), then, assuming a Potts model for the true scene and channel transmission noise, (1) the ICM algorithm is equivalent to a form of mathematical morphology and (2) the segmentation is insensitive to the precise values of the model parameters. Unlike in standard Bayesian images analysis and ICM, it is feasible to do maximum likelihood estimation of the parameters in this setting. For gray-level or multispectral images, we propose an initial segmentation based on the EM algorithm for a mixture model of the marginal distribution of the pixels. The resulting algorithm is much faster than ICM, with gains that increase for more bands and larger images, and has good performance in experiments and for real examples.

Bayesian Morphology: Fast Unsupervised Bayesian Image Analysis

Abstract We consider the problems of image segmentation and classification, and image restoration when the true image is made up of a small number of (unordered) colors. Our emphasis is on both performance and speed; speed has become increasingly important for analyzing large images and multispectral images with many bands, processing large image databases, real-time or near realtime image analysis, and the online analysis of video. Bayesian image analysis provides an elegant solution to these problems, but it is computationally expensive, and the solutions it provides may be sensitive to unrealistic global properties of the models on which it is based. The ICM algorithm is faster and based on the local properties of the models underlying Bayesian image analysis; parameter estimation is performed iteratively via pseudolikelihood. Mathematical morphology is faster again and is widely considered to perform well, but lacks a statistical basis; method selection (analogous to parameter estimation) is done in a rather ad hoc manner. We propose Bayesian morphology, a synthesis of these methods that attempts to combine the speed of mathematical morphology with the principled statistical basis of ICM. The key observation is that when the original image is discrete (or if an initial segmentation has been carried out), then, assuming a Potts model for the true scene and channel transmission noise, (1) the ICM algorithm is equivalent to a form of mathematical morphology and (2) the segmentation is insensitive to the precise values of the model parameters. Unlike in standard Bayesian images analysis and ICM, it is feasible to do maximum likelihood estimation of the parameters in this setting. For gray-level or multispectral images, we propose an initial segmentation based on the EM algorithm for a mixture model of the marginal distribution of the pixels. The resulting algorithm is much faster than ICM, with gains that increase for more bands and larger images, and has good performance in experiments and for real examples.

Bayesian Image Analysis With Markov Chain Monte Carlo and Coloured Continuum Triangulation Models

Summary It is now possible to carry out Bayesian image segmentation from a continuum parametric model with an unknown number of regions. However, few suitable parametric models exist. We set out to model processes which have realizations that are naturally described by coloured planar triangulations. Triangulations are already used, to represent image structure in machine vision, and in finite element analysis, for domain decomposition. However, no normalizable parametric model, with realizations that are coloured triangulations, has been specified to date. We show how this must be done, and in particular we prove that a normalizable measure on the space of triangulations in the interior of a fixed simple polygon derives from a Poisson point process of vertices. We show how such models may be analysed by using Markov chain Monte Carlo methods and we present two case-studies, including convergence analysis.

Non‐parametric Bayesian Estimation of a Spatial Poisson Intensity

A method introduced by Arjas & Gasbarra (1994) and later modified by Arjas & Heikkinen (1997) for the non‐parametric Bayesian estimation of an intensity on the real line is generalized to cover spatial processes. The method is based on a model approximation where the approximating intensities have the structure of a piecewise constant function. Random step functions on the plane are generated using Voronoi tessellations of random point patterns. Smoothing between nearby intensity values is applied by means of a Markov random field prior in the spirit of Bayesian image analysis. The performance of the method is illustrated in examples with both real and simulated data.

Markov Random Fields with Higher‐order Interactions

Discrete‐state Markov random fields on regular arrays have played a significant role in spatial statistics and image analysis. For example, they are used to represent objects against background in computer vision and pixel‐based classification of a region into different crop types in remote sensing. Convenience has generally favoured formulations that involve only pairwise interactions. Such models are in themselves unrealistic and, although they often perform surprisingly well in tasks such as the restoration of degraded images, they are unsatisfactory for many other purposes. In this paper, we consider particular forms of Markov random fields that involve higher‐order interactions and therefore are better able to represent the large‐scale properties of typical spatial scenes. Interpretations of the parameters are given and realizations from a variety of models are produced via Markov chain Monte Carlo. Potential applications are illustrated in two examples. The first concerns Bayesian image analysis and confirms that pairwise‐interaction priors may perform very poorly for image functionals such as number of objects, even when restoration apparently works well. The second example describes a model for a geological dataset and obtains maximum‐likelihood parameter estimates using Markov chain Monte Carlo. Despite the complexity of the formulation, realizations of the estimated model suggest that the representation is quite realistic.