Gibbs Random Field Model Research Articles

An AI-based novel system for predicting respiratory support in COVID-19 patients through CT imaging analysis

The proposed AI-based diagnostic system aims to predict the respiratory support required for COVID-19 patients by analyzing the correlation between COVID-19 lesions and the level of respiratory support provided to the patients. Computed tomography (CT) imaging will be used to analyze the three levels of respiratory support received by the patient: Level 0 (minimum support), Level 1 (non-invasive support such as soft oxygen), and Level 2 (invasive support such as mechanical ventilation). The system will begin by segmenting the COVID-19 lesions from the CT images and creating an appearance model for each lesion using a 2D, rotation-invariant, Markov–Gibbs random field (MGRF) model. Three MGRF-based models will be created, one for each level of respiratory support. This suggests that the system will be able to differentiate between different levels of severity in COVID-19 patients. The system will decide for each patient using a neural network-based fusion system, which combines the estimates of the Gibbs energy from the three MGRF-based models. The proposed system were assessed using 307 COVID-19-infected patients, achieving an accuracy of 97.72%pm 1.57, a sensitivity of 97.76%pm 4.08, and a specificity of 98.87%pm 2.09, indicating a high level of prediction accuracy.

A Novel Computer-Aided Diagnostic System for Early Detection of Diabetic Retinopathy Using 3D-OCT Higher-Order Spatial Appearance Model.

Early diagnosis of diabetic retinopathy (DR) is of critical importance to suppress severe damage to the retina and/or vision loss. In this study, an optical coherence tomography (OCT)-based computer-aided diagnosis (CAD) method is proposed to detect DR early using structural 3D retinal scans. This system uses prior shape knowledge to automatically segment all retinal layers of the 3D-OCT scans using an adaptive, appearance-based method. After the segmentation step, novel texture features are extracted from the segmented layers of the OCT B-scans volume for DR diagnosis. For every layer, Markov–Gibbs random field (MGRF) model is used to extract the 2nd-order reflectivity. In order to represent the extracted image-derived features, we employ cumulative distribution function (CDF) descriptors. For layer-wise classification in 3D volume, using the extracted Gibbs energy feature, an artificial neural network (ANN) is fed the extracted feature for every layer. Finally, the classification outputs for all twelve layers are fused using a majority voting schema for global subject diagnosis. A cohort of 188 3D-OCT subjects are used for system evaluation using different k-fold validation techniques and different validation metrics. Accuracy of , , and are achieved using 4-, 5-, and 10-fold cross-validation, respectively. Additional comparison with deep learning networks, which represent the state-of-the-art, documented the promise of our system’s ability to diagnose the DR early.

Modeling Economic Activities and Random Catastrophic Failures of Financial Networks via Gibbs Random Fields

The complicated economic behavior of entities in a population can be modeled as a Gibbs random field (GRF). Even with simple GRF models, which restrict direct statistical interactions with a small number of neighbors of an entity, real life economic and financial activities may be effectively described. A computer simulator is developed to run empirical experiments to assess different coupling structures and parameters of the presented model; it is possible to test many economic and financial models and policies in terms of their transient and steady-state consequences.

Novel stochastic framework for automatic segmentation of human thigh MRI volumes and its applications in spinal cord injured individuals.

Severe spinal cord injury (SCI) leads to skeletal muscle atrophy and adipose tissue infiltration in the skeletal muscle, which can result in compromised muscle mechanical output and lead to health-related complications. In this study, we developed a novel automatic 3-D approach for volumetric segmentation and quantitative assessment of thigh Magnetic Resonance Imaging (MRI) volumes in individuals with chronic SCI as well as non-disabled individuals. In this framework, subcutaneous adipose tissue, inter-muscular adipose tissue and total muscle tissue are segmented using linear combination of discrete Gaussians algorithm. Also, three thigh muscle groups were segmented utilizing the proposed 3-D Joint Markov Gibbs Random Field model that integrates first order appearance model, spatial information, and shape model to localize the muscle groups. The accuracy of the automatic segmentation method was tested both on SCI (N = 16) and on non-disabled (N = 14) individuals, showing an overall 0.93±0.06 accuracy for adipose tissue and muscle compartments segmentation based on Dice Similarity Coefficient. The proposed framework for muscle compartment segmentation showed an overall higher accuracy compared to ANTs and STAPLE, two previously validated atlas-based segmentation methods. Also, the framework proposed in this study showed similar Dice accuracy and better Hausdorff distance measure to that obtained using DeepMedic Convolutional Neural Network structure, a well-known deep learning network for 3-D medical image segmentation. The automatic segmentation method proposed in this study can provide fast and accurate quantification of adipose and muscle tissues, which have important health and functional implications in the SCI population.

Low-Complexity and Hardware-Friendly H.265/HEVC Encoder for Vehicular Ad-Hoc Networks.

Real-time video streaming over vehicular ad-hoc networks (VANETs) has been considered as a critical challenge for road safety applications. The purpose of this paper is to reduce the computation complexity of high efficiency video coding (HEVC) encoder for VANETs. Based on a novel spatiotemporal neighborhood set, firstly the coding tree unit depth decision algorithm is presented by controlling the depth search range. Secondly, a Bayesian classifier is used for the prediction unit decision for inter-prediction, and prior probability value is calculated by Gibbs Random Field model. Simulation results show that the overall algorithm can significantly reduce encoding time with a reasonably low loss in encoding efficiency. Compared to HEVC reference software HM16.0, the encoding time is reduced by up to 63.96%, while the Bjontegaard delta bit-rate is increased by only 0.76–0.80% on average. Moreover, the proposed HEVC encoder is low-complexity and hardware-friendly for video codecs that reside on mobile vehicles for VANETs.

A Generalized Deep Learning-Based Diagnostic System for Early Diagnosis of Various Types of Pulmonary Nodules.

A novel framework for the classification of lung nodules using computed tomography scans is proposed in this article. To get an accurate diagnosis of the detected lung nodules, the proposed framework integrates the following 2 groups of features: (1) appearance features modeled using the higher order Markov Gibbs random field model that has the ability to describe the spatial inhomogeneities inside the lung nodule and (2) geometric features that describe the shape geometry of the lung nodules. The novelty of this article is to accurately model the appearance of the detected lung nodules using a new developed seventh-order Markov Gibbs random field model that has the ability to model the existing spatial inhomogeneities for both small and large detected lung nodules, in addition to the integration with the extracted geometric features. Finally, a deep autoencoder classifier is fed by the above 2 feature groups to distinguish between the malignant and benign nodules. To evaluate the proposed framework, we used the publicly available data from the Lung Image Database Consortium. We used a total of 727 nodules that were collected from 467 patients. The proposed system demonstrates the promise to be a valuable tool for the detection of lung cancer evidenced by achieving a nodule classification accuracy of 91.20%.

Fuzzy-C-Means Clustering Based Segmentation and CNN-Classification for Accurate Segmentation of Lung Nodules

Objective:Accurate segmentation of abnormal and healthy lungs is very crucial for a steadfast computer-aided disease diagnostics.Methods:For this purpose a stack of chest CT scans are processed. In this paper, novel methods are proposed for segmentation of the multimodal grayscale lung CT scan. In the conventional methods using Markov–Gibbs Random Field (MGRF) model the required regions of interest (ROI) are identified.Result:The results of proposed FCM and CNN based process are compared with the results obtained from the conventional method using MGRF model. The results illustrate that the proposed method can able to segment the various kinds of complex multimodal medical images precisely.Conclusion:However, in this paper, to obtain an exact boundary of the regions, every empirical dispersion of the image is computed by Fuzzy C-Means Clustering segmentation. A classification process based on the Convolutional Neural Network (CNN) classifier is accomplished to distinguish the normal tissue and the abnormal tissue. The experimental evaluation is done using the Interstitial Lung Disease (ILD) database.

A microscopic Gibbs field model for the macroscopic yielding behaviour of a viscoplastic fluid.

We present a Gibbs random field model for the microscopic interactions in a viscoplastic fluid. The model has only two parameters which are sufficient to describe the internal energy of the material in the absence of external stress and a third parameter for a constant externally applied stress. The energy function is derived from the Gibbs potential in terms of the external stress and internal energy. The resulting Gibbs distribution, over a configuration space of microscopic interactions, can mimic experimentally observed macroscopic behavioural phenomena that depend on the externally applied stress. A simulation algorithm that can be used to approximate samples from the Gibbs distribution is given and it is used to gain several insights about the model. Corresponding to weak interactions between the microscopic solid units, our model reveals a smooth solid-fluid transition which is fully reversible upon increasing/decreasing external stresses. If the interaction between neighbouring microscopic constituents exceeds a critical threshold the solid-fluid transition becomes abrupt and a hysteresis of the deformation states is observed even at the asymptotic limit of steady forcing. Quite remarkably, in spite of the limited number of parameters involved, the predictions of our model are in a good qualitative agreement with macro rheological experimental results on the solid-fluid transition in various yield stress materials subjected to an external stress.

TEXTURAL FRACTOGRAPHY

The reconstitution of the history of a fatigue process is based on the knowledge of any correspondences between the morphology of the crack surface and the velocity of the crack growth (crack growth rate - CGR). The textural fractography is oriented to mezoscopic SEM magnifications (30 to 500x). Images contain complicated textures without distinct borders. The aim is to find any characteristics of this texture, which correlate with CGR. Pre-processing of images is necessary to obtain a homogeneous texture. Three methods of textural analysis have been developed and realized as computational programs: the method based on the spectral structure of the image, the method based on a Gibbs random field (GRF) model, and the method based on the idealization of light objects into a fibre process. In order to extract and analyze the fibre process, special methods - tracing fibres and a database-oriented analysis of a fibre process - have been developed.

Automatic analysis of 3D low dose CT images for early diagnosis of lung cancer

Our long term research goal is to develop a fully automated, image-based diagnostic system for early diagnosis of pulmonary nodules that may lead to lung cancer. This paper focuses on monitoring the development of lung nodules detected in successive chest low dose (LD) CT scans of a patient. We propose a new methodology for 3D LDCT data registration which is non-rigid and involves two steps: (i) global target-to-prototype alignment of one scan to another using the learned prior appearance model followed by (ii) local alignment in order to correct for intricate relative deformations. After equalizing signals for two subsequent chest scans, visual appearance of these chest images is described using a Markov–Gibbs random field (MGRF) model with multiple pairwise interaction. An affine transformation that globally registers a target to a prototype is estimated by the gradient ascent-based maximization of a special Gibbs energy function. To get an accurate visual appearance model, we developed a new approach to automatic selection of most characteristic second-order cliques that describe pairwise interactions in the LDCT data. To handle local deformations, we displace each voxel of the target over evolving closed equi-spaced surfaces (iso-surfaces) to closely match the prototype. The evolution of the iso-surfaces is guided by a speed function in the directions that minimize distances between the corresponding voxel pairs on the iso-surfaces in both the data sets. Preliminary results on the 135 LDCT data sets from 27 patients show that the proposed accurate registration could lead to precise diagnosis and identification of the development of the detected pulmonary nodules.

Erratum: Spartan Gibbs Random Field Models for Geostatistical Applications

Typographical errors in certain mathematical formulas that appear in the article Spartan Gibbs Random Field Models for Geostatistical Applications [SIAM J. Sci. Comput., 24 (2003), pp. 2125--2162] are corrected.

Stereo video coding based on frame estimation and interpolation

The paper proposes a stereo video coding system. To ensure compatibility with monoscopic transmission, one of the view sequences is coded and transmitted conforming to the MPEG standard, referred to as the reference stream, and the other view stream is referred to as target stream. Only a few frames of the latter are coded and transmitted, while the rest are skipped and reconstructed at the decoder using a novel stereoscopic frame compensation and interpolation technique, termed SFEI BLCF. In disparity estimation, smooth and accurate disparity fields are obtained by using hierarchical Markov random field (MRF) and Gibbs random field (GRF) models. A fast search method is used to improve the precision and computation speed. Coding and decoding results show that, with only 8/spl sim/30% additional bandwidth over a single view bit stream, one can transmit, store, and reconstruct stereoscopic video sequences with reasonably good performance.

Gibbs random field models: a toolbox for spatial information extraction

In this paper, we present Gibbs random field models in the form of a powerful toolbox for spatial information extraction from remote sensing images. These models are defined via parametrised energy functions that characterise local interactions between neighbouring pixels. After shortly revisiting the information theoretical concept and defining a family of Gibbs models, we give a tour through examples of different kinds of spatial information extraction. These examples range from parameter estimation and analysis, via selection of the model that best describes the image data, up to the segmentation of the whole image into regions with uniform properties of the model. Finally, the concept of across-image segmentation of spatial information leads to an application for content-based queries from remote sensing image archives.

A new texture analysis approach

A new texture analysis approach by using Gibbs random field model is discussed. A parameter vector is defined in order to compute potentials of textures. It is found that texture features can be provided by its corresponding parameter vector, and the vector can be estimated in terms of maximum potential. Conclusions can be inferred that this new method based on the maximum potential is valid.

Permutational model of image texture

Very often computer simulation is practically the only method of image processing studies. To organize a simulation experiment one ought to have efficient simulation algorithms of random image components. Textures form a very important class of such components. They have a specific structure which can be described by their marginal probability distributions and correlations. The coloured spectrum and non-gaussian nature make the simulation of image textures rather difficult. This paper presents a simple Gibbs random field (GRF) model and a relevant simulation algorithm. It is assumed that the modelled texture is a permutation of white noise auxiliary image elements which minimizes the appropriately defined energy function of the GRF model. The modelled texture marginal probability distribution as well as the horizontal and vertical correlation coefficients are supposed to be known. They enable to define clique potentials and an energy function for the four-neighbours neighbourhood system. Four types of causality (lexicographic, meander-like, Hilbertian and Peanonian) are considered and the simulation algorithm for four different simulation paths are proposed. Numerous simulation experiments were performed and their results analysed.

A Gibbs random field‐based active electromagnetic method for noninvasive diagnostics in biomedical applications

A new approach to the reconstruction of dielectric properties of unknown biological bodies is proposed, which is developed starting from an integral equation formulation of the electromagnetic inverse scattering problem. A Gibbs Random Field model is used to develop a stochastic approach based on the Bayes theorem. An iterative solution is obtained by the simulated annealing technique. The method integrates the important features of the spatial domain method with the possibility of taking into account a priori information on the scatterers under test. No large ill‐conditioned matrix inversions are required. A two‐dimensional formulation is considered, involving cylindrical scatterers illuminated by transverse magnetic‐wave incident fields. A multi‐illumination multiview reconstruction process is also performed. Some results on the reconstruction of strong scatterers are reported.

Gibbs random fields, cooccurrences, and texture modeling

Gibbs random field (GRF) models and features from cooccurrence matrices are typically considered as separate but useful tools for texture discrimination. The authors show an explicit relationship between cooccurrences and a large class of GRF's. This result comes from a new framework based on a set-theoretic concept called the and on measures of this set, measures. This framework is also shown to be useful for relating different texture analysis tools. The authors show how the aura set can be constructed with morphological dilation, how its measure yields cooccurrences, and how it can be applied to characterizing the behavior of the Gibbs model for texture. In particular, they show how the aura measure generalizes, to any number of gray levels and neighborhood order, some properties previously known for just the binary, nearest-neighbor GRF. Finally, the authors illustrate how these properties can guide one's intuition about the types of GRF patterns which are most likely to form. >

Gibbs random field model based weight selection for the 2-D adaptive weighted median filter

A generalized filtering method based on the minimization of the energy of the Gibbs model is described. The well-known linear and median filters are all special cases of this method. It is shown that, with that selection of appropriate energy functions, the method can be successfully used to adapt the weights of the adaptive weighted median filter to preserve different textures within the image white eliminating the noise. The newly developed adaptive weighted median filter is based on a 3/spl times/3 square neighborhood structure. The weights of the pixels are adapted according to the clique energies within this neighborhood structure. The assigned energies to 2- or 3-pixel cliques are based on the local statistics within a larger estimation window. It is shown that the proposed filter performance is better compared to some well-known similar filters like the standard, separable, weighted and some adaptive weighted median filters. >

Structure of aura and co-occurrence matrices for the Gibbs texture model

The aura matrix of an image indicates how much of each gray level is present in the neighborhood of each other gray level and generalizes the popular texture-analysis tool, the co-occurrence matrix. In this paper we show that interesting structure appears in both the aura and co-occurrence matrices for textures that are synthesized from Gibbs random-field models. We derive this structure by characterizing configurations of the distribution that are most likely to be synthesized when the Gibbs energy is minimized. This minimization is an important part of applications that use the Gibbs model within a Bayesian estimation framework for maximum a posteriori (MAP) estimation. In particular, we show that the aura matrix will become tridiagonal for an attractive autobinomial field when suitable constraints exist on the histogram, neighborhood, and image sizes. Under the same constraints, but where the field is repulsive instead of attractive, the matrix will become antitridiagonal. The interpretation of this structure is especially significant for modeling textures with minimum-energy configurations: zeros in the matrix prohibit certain colors from occurring next to each other, thus prohibiting large classes of textures from being formed.

An adaptive clustering algorithm for image segmentation

The problem of segmenting images of objects with smooth surfaces is considered. The algorithm that is presented is a generalization of the K-means clustering algorithm to include spatial constraints and to account for local intensity variations in the image. Spatial constraints are included by the use of a Gibbs random field model. Local intensity variations are accounted for in an iterative procedure involving averaging over a sliding window whose size decreases as the algorithm progresses. Results with an 8-neighbor Gibbs random field model applied to pictures of industrial objects, buildings, aerial photographs, optical characters, and faces show that the algorithm performs better than the K-means algorithm and its nonadaptive extensions that incorporate spatial constraints by the use of Gibbs random fields. A hierarchical implementation is also presented that results in better performance and faster speed of execution. The segmented images are caricatures of the originals which preserve the most significant features, while removing unimportant details. They can be used in image recognition and as crude representations of the image. >