No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Classification of Dispersed Patterns of Radiographic Images with COVID-19 by Core-Periphery Network Modeling
Abstract
In real world data classification tasks, we always face the situations where the data samples of the normal cases present a well defined pattern and the features of abnormal data samples vary from one to another, i.e., do not show a regular pattern. Up to now, the general data classification hypothesis requires the data features within each class to present a certain level of similarity. Therefore, such real situations violate the classic classification condition and make it a hard task. In this paper, we present a novel solution for this kind of problems through a network approach. Specifically, we construct a core-periphery network from the training data set in such way that core node set is formed by the normal data samples and peripheral node set contains the abnormal samples of the training data set. The classification is made by checking the coreness of the testing data samples. The proposed method is applied to classify radiographic image for COVID-19 diagnosis. Computer simulations show promising results of the method. The main contribution is to introduce a general scheme to characterize pattern formation of the data “without pattern”.
Traditional classification techniques usually classify data samples according to the physical organization, such as similarity, distance, and distribution, of the data features, which lack a general and explicit mechanism to represent data classes with semantic data patterns. Therefore, the incorporation of data pattern formation in classification is still a challenge problem. Meanwhile, data classification techniques can only work well when data features present high level of similarity in the feature space within each class. Such a hypothesis is not always satisfied, since, in real-world applications, we frequently encounter the following situation: On one hand, the data samples of some classes (usually representing the normal cases) present well defined patterns; on the other hand, the data features of other classes (usually representing abnormal classes) present large variance, i.e., low similarity within each class. Such a situation makes data classification a difficult task. In this paper, we present a novel solution to deal with the above mentioned problems based on the mesostructure of a complex network, built from the original data set. Specifically, we construct a core–periphery network from the training data set in such way that the normal class is represented by the core sub-network and the abnormal class is characterized by the peripheral sub-network. The testing data sample is classified to the core class if it gets a high coreness value; otherwise, it is classified to the periphery class. The proposed method is tested on an artificial data set and then applied to classify x-ray images for COVID-19 diagnosis, which presents high classification precision. In this way, we introduce a novel method to describe data pattern of the data “without pattern” through a network approach, contributing to the general solution of classification.
Chest X-ray is the first imaging technique that plays an important role in the diagnosis of COVID-19 disease. Due to the high availability of large-scale annotated image datasets, great success has been achieved using convolutional neural networks (CNN s) for image recognition and classification. However, due to the limited availability of annotated medical images, the classification of medical images remains the biggest challenge in medical diagnosis. Thanks to transfer learning, an effective mechanism that can provide a promising solution by transferring knowledge from generic object recognition tasks to domain-specific tasks. In this paper, we validate and a deep CNN, called Decompose, Transfer, and Compose (DeTraC), for the classification of COVID-19 chest X-ray images. DeTraC can deal with any irregularities in the image dataset by investigating its class boundaries using a class decomposition mechanism. The experimental results showed the capability of DeTraC in the detection of COVID-19 cases from a comprehensive image dataset collected from several hospitals around the world. High accuracy of 93.1% (with a sensitivity of 100%) was achieved by DeTraC in the detection of COVID-19 X-ray images from normal, and severe acute respiratory syndrome cases.
The coronavirus (COVID-19) pandemic is putting healthcare systems across the world under unprecedented and increasing pressure according to the World Health Organization (WHO). With the advances in computer algorithms and especially Artificial Intelligence, the detection of this type of virus in the early stages will help in fast recovery and help in releasing the pressure off healthcare systems. In this paper, a GAN with deep transfer learning for coronavirus detection in chest X-ray images is presented. The lack of datasets for COVID-19 especially in chest X-rays images is the main motivation of this scientific study. The main idea is to collect all the possible images for COVID-19 that exists until the writing of this research and use the GAN network to generate more images to help in the detection of this virus from the available X-rays images with the highest accuracy possible. The dataset used in this research was collected from different sources and it is available for researchers to download and use it. The number of images in the collected dataset is 307 images for four different types of classes. The classes are the COVID-19, normal, pneumonia bacterial, and pneumonia virus. Three deep transfer models are selected in this research for investigation. The models are the Alexnet, Googlenet, and Restnet18. Those models are selected for investigation through this research as it contains a small number of layers on their architectures, this will result in reducing the complexity, the consumed memory and the execution time for the proposed model. Three case scenarios are tested through the paper, the first scenario includes four classes from the dataset, while the second scenario includes 3 classes and the third scenario includes two classes. All the scenarios include the COVID-19 class as it is the main target of this research to be detected. In the first scenario, the Googlenet is selected to be the main deep transfer model as it achieves 80.6% in testing accuracy. In the second scenario, the Alexnet is selected to be the main deep transfer model as it achieves 85.2% in testing accuracy, while in the third scenario which includes two classes (COVID-19, and normal), Googlenet is selected to be the main deep transfer model as it achieves 100% in testing accuracy and 99.9% in the validation accuracy. All the performance measurement strengthens the obtained results through the research.
COVID-19 is a worldwide epidemic, as announced by the World Health Organization (WHO) in March 2020. Machine learning (ML) methods can play vital roles in identifying COVID-19 patients by visually analyzing their chest x-ray images. In this paper, a new ML-method proposed to classify the chest x-ray images into two classes, COVID-19 patient or non-COVID-19 person. The features extracted from the chest x-ray images using new Fractional Multichannel Exponent Moments (FrMEMs). A parallel multi-core computational framework utilized to accelerate the computational process. Then, a modified Manta-Ray Foraging Optimization based on differential evolution used to select the most significant features. The proposed method evaluated using two COVID-19 x-ray datasets. The proposed method achieved accuracy rates of 96.09% and 98.09% for the first and second datasets, respectively.
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
We analyse the complex network architectures based on the k-core notion, where the k-core is the maximal subgraph in a network, whose vertices all have internal degree at least k. We explain the nature of the unusual “hybrid” phase transition of the emergence of a giant k-core in a network, which combines a jump in the order parameter and a critical singularity, and relate this transition to critical phenomena in other systems. Finally, we indicate generic features and differences between the k-core problem and bootstrap percolation.
Recent studies uncovered important core/periphery network structures
characterizing complex sets of cooperative and competitive interactions between
network nodes, be they proteins, cells, species or humans. Better
characterization of the structure, dynamics and function of core/periphery
networks is a key step of our understanding cellular functions, species
adaptation, social and market changes. Here we summarize the current knowledge
of the structure and dynamics of "traditional" core/periphery networks,
rich-clubs, nested, bow-tie and onion networks. Comparing core/periphery
structures with network modules, we discriminate between global and local
cores. The core/periphery network organization lies in the middle of several
extreme properties, such as random/condensed structures, clique/star
configurations, network symmetry/asymmetry, network
assortativity/disassortativity, as well as network hierarchy/anti-hierarchy.
These properties of high complexity together with the large degeneracy of core
pathways ensuring cooperation and providing multiple options of network flow
re-channelling greatly contribute to the high robustness of complex systems.
Core processes enable a coordinated response to various stimuli, decrease
noise, and evolve slowly. The integrative function of network cores is an
important step in the development of a large variety of complex organisms and
organizations. In addition to these important features and several decades of
research interest, studies on core/periphery networks still have a number of
unexplored areas.
A common but informal notion in social network analysis and other fields is the concept of a core/periphery structure. The intuitive conception entails a dense, cohesive core and a sparse, unconnected periphery. This paper seeks to formalize the intuitive notion of a core/periphery structure and suggests algorithms for detecting this structure, along with statistical tests for testing a priori hypotheses. Different models are presented for different kinds of graphs (directed and undirected, valued and nonvalued). In addition, the close relation of the continuous models developed to certain centrality measures is discussed.
Outlier detection has been used for centuries to detect and, where appropriate, remove anomalous observations from data. Outliers arise due to mechanical faults, changes in system behaviour, fraudulent behaviour, human error, instrument error or simply through natural deviations in populations. Their detection can identify system faults and fraud before they escalate with potentially catastrophic consequences. It can identify errors and remove their contaminating effect on the data set and as such to purify the data for processing. The original outlier detection methods were arbitrary but now, principled and systematic techniques are used, drawn from the full gamut of Computer Science and Statistics. In this paper, we introduce a survey of contemporary techniques for outlier detection. We identify their respective motivations and distinguish their advantages and disadvantages in a comparative review.
to difierentiate between normal and anomalous behavior. When applying a given technique to a particular domain, these assumptions can be used as guidelines to assess the efiectiveness of the technique in that domain. For each category, we provide a basic anomaly detection technique, and then show how the difierent existing techniques in that category are variants of the basic tech- nique. This template provides an easier and succinct understanding of the techniques belonging to each category. Further, for each category, we identify the advantages and disadvantages of the techniques in that category. We also provide a discussion on the computational complexity of the techniques since it is an important issue in real application domains. We hope that this survey will provide a better understanding of the difierent directions in which research has been done on this topic, and how techniques developed in one area can be applied in domains for which they were not intended to begin with.
The quad tree is a data structure appropriate for storing information to be retrieved on composite keys. We discuss the specific case of two-dimensional retrieval, although the structure is easily generalised to arbitrary dimensions. Algorithms are given both for staightforward insertion and for a type of balanced insertion into quad trees. Empirical analyses show that the average time for insertion is logarithmic with the tree size. An algorithm for retrieval within regions is presented along with data from empirical studies which imply that searching is reasonably efficient. We define an optimized tree and present an algorithm to accomplish optimization in n log n time. Searching is guaranteed to be fast in optimized trees. Remaining problems include those of deletion from quad trees and merging of quad trees, which seem to be inherently difficult operations.
Systems as diverse as genetic networks or the world wide web are best
described as networks with complex topology. A common property of many large
networks is that the vertex connectivities follow a scale-free power-law
distribution. This feature is found to be a consequence of the two generic
mechanisms that networks expand continuously by the addition of new vertices,
and new vertices attach preferentially to already well connected sites. A model
based on these two ingredients reproduces the observed stationary scale-free
distributions, indicating that the development of large networks is governed by
robust self-organizing phenomena that go beyond the particulars of the
individual systems.
We analytically describe the architecture of randomly damaged uncorrelated networks as a set of successively enclosed substructures--k-cores. The k-core is the largest subgraph where vertices have at least k interconnections. We find the structure of k-cores, their sizes, and their birthpoints--the bootstrap percolation thresholds. We show that in networks with a finite mean number zeta2 of the second-nearest neighbors, the emergence of a k-core is a hybrid phase transition. In contrast, if zeta2 diverges, the networks contain an infinite sequence of k-cores which are ultrarobust against random damage.
We study a map of the Internet (at the autonomous systems level), by introducing and using the method of k-shell decomposition and the methods of percolation theory and fractal geometry, to find a model for the structure of the Internet. In particular, our analysis uses information on the connectivity of the network shells to separate, in a unique (no parameters) way, the Internet into three subcomponents: (i) a nucleus that is a small (≈100 nodes), very well connected globally distributed subgraph; (ii) a fractal subcomponent that is able to connect the bulk of the Internet without congesting the nucleus, with self-similar properties and critical exponents predicted from percolation theory; and (iii) dendrite-like structures, usually isolated nodes that are connected to the rest of the network through the nucleus only. We show that our method of decomposition is robust and provides insight into the underlying structure of the Internet and its functional consequences. Our approach of decomposing the network is general and also useful when studying other complex networks.
• fractals
• networks
• percolation
We show that the Internet topology at the autonomous system (AS) level has a rich-club phenomenon. The rich nodes, which are a small number of nodes with large numbers of links, are very well connected to each other. The rich-club is a core tier that we measured using the rich-club connectivity and the node-node link distribution. We obtained this core tier without any heuristic assumption between the ASs. The rich-club phenomenon is a simple qualitative way to differentiate between power law topologies and provides a criterion for new network models. To show this, we compared the measured rich-club of the AS graph with networks obtained using the Baraba´si-Albert (BA) scale-free network model, the Fitness BA model and the Inet-3.0 model.
The COVID-19 pandemic, caused by the severe acute respiratory syndrome coronavirus 2, emerged into a world being rapidly transformed by artificial intelligence (AI) based on big data, computational power and neural networks. The gaze of these networks has in recent years turned increasingly towards applications in healthcare. It was perhaps inevitable that COVID-19, a global disease propagating health and economic devastation, should capture the attention and resources of the world's computer scientists in academia and industry. The potential for AI to support the response to the pandemic has been proposed across a wide range of clinical and societal challenges, including disease forecasting, surveillance and antiviral drug discovery. This is likely to continue as the impact of the pandemic unfolds on the world's people, industries and economy but a surprising observation on the current pandemic has been the limited impact AI has had to date in the management of COVID-19. This correspondence focuses on exploring potential reasons behind the lack of successful adoption of AI models developed for COVID-19 diagnosis and prognosis, in front-line healthcare services. We highlight the moving clinical needs that models have had to address at different stages of the epidemic, and explain the importance of translating models to reflect local healthcare environments. We argue that both basic and applied research are essential to accelerate the potential of AI models, and this is particularly so during a rapidly evolving pandemic. This perspective on the response to COVID-19, may provide a glimpse into how the global scientific community should react to combat future disease outbreaks more effectively.
Background and Objective:The COVID-19 can cause severe pneumonia and is estimated to have a high impact on the healthcare system. Early diagnosis is crucial for correct treatment in order to possibly reduce the stress in the healthcare system. The standard image diagnosis tests for pneumonia are chest X-ray (CXR) and computed tomography (CT) scan. Although CT scan is the gold standard, CXR are still useful because it is cheaper, faster and more widespread. This study aims to identify pneumonia caused by COVID-19 from other types and also healthy lungs using only CXR images.
Methods:In order to achieve the objectives, we have proposed a classification schema considering the following perspectives: i) a multi-class classification; ii) hierarchical classification, since pneumonia can be structured as a hierarchy. Given the natural data imbalance in this domain, we also proposed the use of resampling algorithms in the schema in order to re-balance the classes distribution. We observed that, texture is one of the main visual attributes of CXR images, our classification schema extract features using some well-known texture descriptors and also using a pre-trained CNN model. We also explored early and late fusion techniques in the schema in order to leverage the strength of multiple texture descriptors and base classifiers at once.
To evaluate the approach, we composed a database, named RYDLS-20, containing CXR images of pneumonia caused by different pathogens as well as CXR images of healthy lungs. The classes distribution follows a real-world scenario in which some pathogens are more common than others.
Results:The proposed approach tested in RYDLS-20 achieved a macro-avg F1-Score of 0.65 using a multi-class approach and a F1-Score of 0.89 for the COVID-19 identification in the hierarchical classification scenario.
Conclusions:As far as we know, the top identification rate obtained in this paper is the best nominal rate obtained for COVID-19 identification in an unbalanced environment with more than three classes. We must also highlight the novel proposed hierarchical classification approach for this task, which considers the types of pneumonia caused by the different pathogens and lead us to the best COVID-19 recognition rate obtained here.
Data classification is a common task, which can be performed by both computers and human beings. However, a fundamental difference between them can be observed: computer-based classification considers only physical features (e.g., similarity, distance, or distribution) of input data; by contrast, brain-based classification takes into account not only physical features, but also the organizational structure of data. In this paper, we figure out the data organizational structure for classification using complex networks constructed from training data. Specifically, an unlabeled instance is classified by the
importance
concept characterized by Google’s PageRank measure of the underlying data networks. Before a test data instance is classified, a network is constructed from vector-based data set and the test instance is inserted into the network in a proper manner. To this end, we also propose a measure, called
spatio-structural differential efficiency
, to combine the physical and topological features of the input data. Such a method allows for the classification technique to capture a variety of data patterns using the unique
importance
measure. Extensive experiments demonstrate that the proposed technique has promising predictive performance on the detection of heart abnormalities.
Traditional supervised data classification considers only physical features (e.g., distance or similarity) of the input data. Here, this type of learning is called low level classification. On the other hand, the human (animal) brain performs both low and high orders of learning and it has facility in identifying patterns according to the semantic meaning of the input data. Data classification that considers not only physical attributes but also the pattern formation is, here, referred to as high level classification. In this paper, we propose a hybrid classification technique that combines both types of learning. The low level term can be implemented by any classification technique, while the high level term is realized by the extraction of features of the underlying network constructed from the input data. Thus, the former classifies the test instances by their physical features or class topologies, while the latter measures the compliance of the test instances to the pattern formation of the data. Our study shows that the proposed technique not only can realize classification according to the pattern formation, but also is able to improve the performance of traditional classification techniques. Furthermore, as the class configuration's complexity increases, such as the mixture among different classes, a larger portion of the high level term is required to get correct classification. This feature confirms that the high level classification has a special importance in complex situations of classification. Finally, we show how the proposed technique can be employed in a real-world application, where it is capable of identifying variations and distortions of handwritten digit images. As a result, it supplies an improvement in the overall pattern recognition rate.
Networks of coupled dynamical systems have been used to model biological oscillators, Josephson junction arrays, excitable media, neural networks, spatial games, genetic control networks and many other self-organizing systems. Ordinarily, the connection topology is assumed to be either completely regular or completely random. But many biological, technological and social networks lie somewhere between these two extremes. Here we explore simple models of networks that can be tuned through this middle ground: regular networks 'rewired' to introduce increasing amounts of disorder. We find that these systems can be highly clustered, like regular lattices, yet have small characteristic path lengths, like random graphs. We call them 'small-world' networks, by analogy with the small-world phenomenon (popularly known as six degrees of separation. The neural network of the worm Caenorhabditis elegans, the power grid of the western United States, and the collaboration graph of film actors are shown to be small-world networks. Models of dynamical systems with small-world coupling display enhanced signal-propagation speed, computational power, and synchronizability. In particular, infectious diseases spread more easily in small-world networks than in regular lattices.
Networks may, or may not, be wired to have a core that is both itself densely connected and central in terms of graph distance. In this study we propose a coefficient to measure if the network has such a clear-cut core-periphery dichotomy. We measure this coefficient for a number of real-world and model networks and find that different classes of networks have their characteristic values. Among other things we conclude that geographically embedded transportation networks have a strong core-periphery structure. We proceed to study radial statistics of the core, i.e., properties of the neighborhoods of the core vertices for increasing n. We find that almost all networks have unexpectedly many edges within n neighborhoods at a certain distance from the core suggesting an effective radius for nontrivial network processes.
Geographical curves are so involved in their detail that their lengths are often infinite or, rather, undefinable. However,
many are statistically "selfsimilar," meaning that each portion can be considered a reduced-scale image of the whole. In that
case, the degree of complication can be described by a quantity D that has many properties of a "dimension," though it is
fractional; that is, it exceeds the value unity associated with the ordinary, rectifiable, curves.