scholarly journals Impartially Validated Multiple Deep-Chain Models to Detect COVID-19 in Chest X-ray Using Latent Space Radiomics

2021 ◽  
Vol 10 (14) ◽  
pp. 3100
Author(s):  
Bardia Yousefi ◽  
Satoru Kawakita ◽  
Arya Amini ◽  
Hamed Akbari ◽  
Shailesh M. Advani ◽  
...  
Keyword(s):  
Principal Component ◽  
Study Cohort ◽  
X Ray ◽  
Latent Space ◽  
Convolutional Autoencoder ◽  
Chest X Ray ◽  
Rapid Pace ◽  
Low Dimensional ◽  
Limited Testing ◽  
Lung Lobes

The COVID-19 pandemic continues to spread globally at a rapid pace, and its rapid detection remains a challenge due to its rapid infectivity and limited testing availability. One of the simply available imaging modalities in clinical routine involves chest X-ray (CXR), which is often used for diagnostic purposes. Here, we proposed a computer-aided detection of COVID-19 in CXR imaging using deep and conventional radiomic features. First, we used a 2D U-Net model to segment the lung lobes. Then, we extracted deep latent space radiomics by applying deep convolutional autoencoder (ConvAE) with internal dense layers to extract low-dimensional deep radiomics. We used Johnson–Lindenstrauss (JL) lemma, Laplacian scoring (LS), and principal component analysis (PCA) to reduce dimensionality in conventional radiomics. The generated low-dimensional deep and conventional radiomics were integrated to classify COVID-19 from pneumonia and healthy patients. We used 704 CXR images for training the entire model (i.e., U-Net, ConvAE, and feature selection in conventional radiomics). Afterward, we independently validated the whole system using a study cohort of 1597 cases. We trained and tested a random forest model for detecting COVID-19 cases through multivariate binary-class and multiclass classification. The maximal (full multivariate) model using a combination of the two radiomic groups yields performance in classification cross-validated accuracy of 72.6% (69.4–74.4%) for multiclass and 89.6% (88.4–90.7%) for binary-class classification.

scholarly journals Clinical features of endobronchial tuberculosis

2014 ◽  
Vol 71 (2) ◽  
pp. 156-160 ◽  
Author(s):  
Natalija Samardzic ◽  
Dragana Jovanovic ◽  
Ljiljana Markovic-Denic ◽  
Marina Roksandic-Milenkovic ◽  
Spasoje Popevic ◽  
...  
Keyword(s):  
Clinical Features ◽  
Lung Diseases ◽  
Tracheobronchial Tree ◽  
Laboratory Findings ◽  
X Ray ◽  
Diagnostic Aspects ◽  
Clinical Center ◽  
Chest X Ray ◽  
Endobronchial Tuberculosis ◽  
Lung Lobes

Background/Aim. Endobronchial tuberculosis (EBTB) is a specific type of pulmonary tuberculosis which often affect the tracheobronchial tree, and can be microbiologically and/or pathohistologically confirmed. The aim of the study was to determine the clinical features and diagnostic aspects of EBTB. Methods. This retrospective study was conducted at the Clinic for Lung Diseases, Clinical Center of Serbia, Belgrade, from January 1997 to December 2007. All patients with EBTB confirmed by bronchoscopy with biopsy during a study period were analysed. Data included the patient?s medical history, a physical exam, chest X-ray, mycobacterial analysis of sputum samples, endoscopic types and patohistological confirmation. Results. In the study, 57.6% of the patients were males. The most frequent symptoms were cough (71.2%), malaise (54.2%), fever (49.2%), weight loss (40.7%), and hemoptysis (13.6%). Most of the patients were diagnosed within 30 days of symptoms onset. Sputum examination showed acid-fast bacilli in 31.4% of the patients, while sputum culture for tuberculosis bacilli were positive in 55.9% of the patients. The most common radiographic localization was in the upper lung lobes (63.5%). Cavities were present in 60.4% of the patients. The most common endoscopic subtype determined by bronchoscopy were nonspecific bronchitis (39.9%) and edematous-hyperemic subtype (36.4%). Conclusion. EBTB was more frequent among men, and among people in their fifties in our country. Detailed bronchoscopic examination, correlated with clinical and laboratory findings, will improve diagnostic rate and provide timely therapy.

scholarly journals A Self-Attention Mechanism for COVID-19 Detection using Chest X-Ray Images

2021 ◽  
Author(s):  
Usman Muhammad ◽  
Md Ziaul Hoque ◽  
Mourad Oussalah ◽  
Anja Keskinarkaus ◽  
Tapio Seppänen ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Feature Space ◽  
Viral Disease ◽  
Attention Mechanism ◽  
Current Evidence ◽  
Great Promise ◽  
X Ray ◽  
Benchmark Datasets ◽  
Chest X Ray ◽  
Low Dimensional

<p>COVID-19 is a rapidly spreading viral disease and has affected over 100 countries worldwide. The numbers of casualties and infected cases have been escalated particularly in vulnerable states with weakened healthcare systems. Recently, reverse transcription-polymerase chain reaction (RT-PCR) is the test of choice for diagnosing COVID-19. However, current evidence suggests that COVID-19 infected patients are mostly stimulated from a lung infection after coming in contact with this virus. Therefore, chest X-ray (i.e., radiography) and chest CT can be a surrogate in some countries where PCR is not readily available. This has forced the scientific community to detect COVID-19 infection from X-ray images and recently proposed machine learning methods offer great promise for fast and accurate detection. Deep learning with convolutional neural networks (CNNs) has been successfully applied to radiological imaging for improving the accuracy of diagnosis. However, the performance remains limited due to the lack of representative X-ray images available in public benchmark datasets. To alleviate this issue, we propose an attention mechanism for data augmentation in the feature space rather than in the data space using reconstruction independent component analysis (RICA). Specifically, a unified architecture is proposed which contains a deep convolutional neural network (CNN), an attention mechanism, and a bidirectional LSTM (BiLSTM). The CNN provides the high-level features extracted at the pooling layer where the attention mechanism chooses the most relevant features and generates low-dimensional augmented features. Finally, BiLSTM is used to classify the processed sequential information. We conducted experiments on two publicly available databases to show that the proposed approach achieves the state-of-the-art results with an accuracy of 97% and 84% while being able to generate explanations. Explainability analysis has been carried out using feature visualization through PCA projection and t-SNE plots.<br></p>

scholarly journals AI-based Diagnosis of COVID-19 Patients Using X-ray Scans with Stochastic Ensemble of CNNs

2020 ◽  
Author(s):  
Ridhi Arora ◽  
Vipul Bansal ◽  
Himanshu Buckchash ◽  
Rahul Kumar ◽  
Vinodh J Sahayasheela ◽  
...  
Keyword(s):  
Comprehensive Evaluation ◽  
State Of The Art ◽  
Empirical Evaluation ◽  
Main Idea ◽  
Feature Space ◽  
Disease Diagnosis ◽  
X Ray ◽  
Main Challenge ◽  
Latent Space ◽  
Chest X Ray

<div>According to WHO, COVID-19 is an infectious disease and has a significant social and economic impact. The main challenge in ?fighting against this disease is its scale. Due to the imminent outbreak, the medical facilities are over exhausted and unable to accommodate the piling cases. A quick diagnosis system is required to address these challenges. To this end, a stochastic deep learning model is proposed. The main idea is to constrain the deep representations over a gaussian prior to reinforce the discriminability in feature space. The model can work on chest X-ray or CT-scan images. It provides</div><div>a fast diagnosis of COVID-19 and can scale seamlessly. This work presents a comprehensive evaluation of previously proposed approaches for X-ray based</div><div>disease diagnosis. Our approach works by learning a latent space over X-ray image distribution from the ensemble of state-of-the-art convolutional-nets,</div><div>and then linearly regressing the predictions from an ensemble of classifi?ers which take the latent vector as input. We experimented with publicly available datasets having three classes { COVID-19, normal, Pneumonia. Moreover, for robust evaluation, experiments were performed on a large chest X-ray dataset with fi?ve different very similar diseases. Extensive empirical evaluation shows</div><div>how the proposed approach advances the state-of-the-art.</div>

scholarly journals Weather scenarios from AROME-EPS forecasts using autoencoder and clustering methods

2021 ◽  
Author(s):  
Arnaud Mounier ◽  
Laure Raynaud ◽  
Lucie Rottner ◽  
Matthieu Plu
Keyword(s):  
Principal Component ◽  
Ensemble Prediction ◽  
Mathematical Representation ◽  
Space Representation ◽  
Clustering Methods ◽  
Latent Space ◽  
Accumulated Rainfall ◽  
Object Oriented Approach ◽  
Prediction Systems ◽  
Low Dimensional

&lt;p&gt;The use of ensemble prediction systems (EPS) is challenging because of the huge information it provides. Forecasts from ensemble prediction systems (EPS) are often summarised by statistical quantities (ie quantiles maps). Although such mathematical representation is efficient for capturing the ensemble distribution, it lacks physical consistency, which raises issues for many applications of EPS in an operational context. In order to provide a physically-consistent synthesis of the French convection-permitting AROME-EPS forecasts, we propose to automatically draw a few scenarios that are representative of the different possible outcomes. Each scenario is a reduced set of EPS members.&lt;/p&gt;&lt;p&gt;To design a scenario synthesis, the procedure can be divided into two parts. A first step aims at extracting relevant features in each EPS member in order to reduce the problem dimensionality. Then, a clustering is done based on these features.&lt;/p&gt;&lt;p&gt;The originality of our work is to leverage the capacities of deep learning for the features extraction. For that purpose, we use a convolutional autoencodeur (CAE) to learn an optimal low-dimensional representation (also called latent space representation) of the input forecast field. In this work, the algorithm is developed to work on 1h-accumulated rainfall from AROME-EPS, with a focus on convective cases.&lt;/p&gt;&lt;p&gt;The CAE is trained on around 150 000 forecasts and its performance is evaluated based on the quality of the reconstructed input fields from the latent space. To examine the reconstruction quality, an object-oriented approach is used. CAE is also compared with the commonly-used principal component analysis (PCA). In a second part, different clustering methods (kmeans, HDBSCAN, &amp;#8230;) are applied to EPS members in the latent space and evaluated using subjective and objective diagnostics.&lt;/p&gt;

scholarly journals Feature Extraction of Chest X-ray Images and Analysis using PCA and kPCA

2018 ◽  
Vol 8 (5) ◽  
pp. 3392 ◽  
Author(s):  
Roopa H ◽  
Asha T
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Computer System ◽  
Feature Selection Method ◽  
Principal Component ◽  
Component Analysis ◽  
Data Mining Algorithm ◽  
X Ray ◽  
Chest X Ray ◽  
Disease Analysis

<p class="abstract">Tuberculosis (TB) is an infectious disease caused by mycobacterium which can be diagnosed by its various symptoms like fever, cough, etc. Tuberculosis can also be analyzed by understanding the chest x-ray of the patient which is revealed by an expert physician .The chest x-ray image contains many features which cannot be directly used by any computer system for analyzing the disease. Features of chest x-ray images must be understood and extracted, so that it can be processed to a form to be fed to any computer system for disease analysis. This paper presents feature extraction of chest x-ray image which can be used as an input for any data mining algorithm for TB disease analysis. So texture and shape based features are extracted from x-ray image using image processing concepts. The features extracted are analyzed using principal component analysis (PCA) and kernel principal component analysis (kPCA) techniques. Filter and wrapper feature selection method using linear regression model were applied on these techniques. The performance of PCA and kPCA are analyzed and found that the accuracy of PCA using wrapper approach is 96.07%   when compared to the accuracy of kPCA which is 62.50%. PCA performs well than kPCA with a good accuracy.</p>

scholarly journals Quantitative comparison of principal component analysis and unsupervised deep learning using variational autoencoders for shape analysis of motile cells

2020 ◽  
Author(s):  
Caleb K. Chan ◽  
Amalia Hadjitheodorou ◽  
Tony Y.-C. Tsai ◽  
Julie A. Theriot
Keyword(s):  
Principal Component Analysis ◽  
Deep Learning ◽  
Cell Shape ◽  
Biological Function ◽  
Principal Component ◽  
Black Box ◽  
Biological Data ◽  
Latent Space ◽  
Unsupervised Deep Learning ◽  
Low Dimensional

ABSTRACTCell motility is a crucial biological function for many cell types, including the immune cells in our body that act as first responders to foreign agents. In this work we consider the amoeboid motility of human neutrophils, which show complex and continuous morphological changes during locomotion. We imaged live neutrophils migrating on a 2D plane and extracted unbiased shape representations using cell contours and binary masks. We were able to decompose these complex shapes into low-dimensional encodings with both principal component analysis (PCA) and an unsupervised deep learning technique using variational autoencoders (VAE), enhanced with generative adversarial networks (GANs). We found that the neural network architecture, the VAE-GAN, was able to encode complex cell shapes into a low-dimensional latent space that encodes the same shape variation information as PCA, but much more efficiently. Contrary to the conventional viewpoint that the latent space is a “black box”, we demonstrated that the information learned and encoded within the latent space is consistent with PCA and is reproducible across independent training runs. Furthermore, by including cell speed into the training of the VAE-GAN, we were able to incorporate cell shape and speed into the same latent space. Our work provides a quantitative framework that connects biological form, through cell shape, to a biological function, cell movement. We believe that our quantitative approach to calculating a compact representation of cell shape using the VAE-GAN provides an important avenue that will support further mechanistic dissection of cell motility.AUTHOR SUMMARYDeep convolutional neural networks have recently enjoyed a surge in popularity, and have found useful applications in many fields, including biology. Supervised deep learning, which involves the training of neural networks using existing labeled data, has been especially popular in solving image classification problems. However, biological data is often highly complex and continuous in nature, where prior labeling is impractical, if not impossible. Unsupervised deep learning promises to discover trends in the data by reducing its complexity while retaining the most relevant information. At present, challenges in the extraction of meaningful human-interpretable information from the neural network’s nonlinear discovery process have earned it a reputation of being a “black box” that can perform impressively well at prediction but cannot be used to shed any meaningful insight on underlying mechanisms of variation in biological data sets. Our goal in this paper is to establish unsupervised deep learning as a practical tool to gain scientific insight into biological data by first establishing the interpretability of our particular data set (images of the shapes of motile neutrophils) using more traditional techniques. Using the insight gained from this as a guide allows us to shine light into the “black box” of unsupervised deep learning.

scholarly journals AI-based Diagnosis of COVID-19 Patients Using X-ray Scans with Stochastic Ensemble of CNNs

2020 ◽  
Author(s):  
Ridhi Arora ◽  
Vipul Bansal ◽  
Himanshu Buckchash ◽  
Rahul Kumar ◽  
Vinodh J Sahayasheela ◽  
...  
Keyword(s):  
Comprehensive Evaluation ◽  
State Of The Art ◽  
Empirical Evaluation ◽  
Main Idea ◽  
Feature Space ◽  
Disease Diagnosis ◽  
X Ray ◽  
Main Challenge ◽  
Latent Space ◽  
Chest X Ray

<div>According to WHO, COVID-19 is an infectious disease and has a significant social and economic impact. The main challenge in ?fighting against this disease is its scale. Due to the imminent outbreak, the medical facilities are over exhausted and unable to accommodate the piling cases. A quick diagnosis system is required to address these challenges. To this end, a stochastic deep learning model is proposed. The main idea is to constrain the deep representations over a gaussian prior to reinforce the discriminability in feature space. The model can work on chest X-ray or CT-scan images. It provides</div><div>a fast diagnosis of COVID-19 and can scale seamlessly. This work presents a comprehensive evaluation of previously proposed approaches for X-ray based</div><div>disease diagnosis. Our approach works by learning a latent space over X-ray image distribution from the ensemble of state-of-the-art convolutional-nets,</div><div>and then linearly regressing the predictions from an ensemble of classifi?ers which take the latent vector as input. We experimented with publicly available datasets having three classes { COVID-19, normal, Pneumonia. Moreover, for robust evaluation, experiments were performed on a large chest X-ray dataset with fi?ve different very similar diseases. Extensive empirical evaluation shows</div><div>how the proposed approach advances the state-of-the-art.</div>

scholarly journals A Self-Attention Mechanism for COVID-19 Detection using Chest X-Ray Images

2021 ◽  
Author(s):  
Usman Muhammad ◽  
Md Ziaul Hoque ◽  
Mourad Oussalah ◽  
Anja Keskinarkaus ◽  
Tapio Seppänen ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Feature Space ◽  
Viral Disease ◽  
Attention Mechanism ◽  
Current Evidence ◽  
Great Promise ◽  
X Ray ◽  
Benchmark Datasets ◽  
Chest X Ray ◽  
Low Dimensional

<p>COVID-19 is a rapidly spreading viral disease and has affected over 100 countries worldwide. The numbers of casualties and infected cases have been escalated particularly in vulnerable states with weakened healthcare systems. Recently, reverse transcription-polymerase chain reaction (RT-PCR) is the test of choice for diagnosing COVID-19. However, current evidence suggests that COVID-19 infected patients are mostly stimulated from a lung infection after coming in contact with this virus. Therefore, chest X-ray (i.e., radiography) and chest CT can be a surrogate in some countries where PCR is not readily available. This has forced the scientific community to detect COVID-19 infection from X-ray images and recently proposed machine learning methods offer great promise for fast and accurate detection. Deep learning with convolutional neural networks (CNNs) has been successfully applied to radiological imaging for improving the accuracy of diagnosis. However, the performance remains limited due to the lack of representative X-ray images available in public benchmark datasets. To alleviate this issue, we propose an attention mechanism for data augmentation in the feature space rather than in the data space using reconstruction independent component analysis (RICA). Specifically, a unified architecture is proposed which contains a deep convolutional neural network (CNN), an attention mechanism, and a bidirectional LSTM (BiLSTM). The CNN provides the high-level features extracted at the pooling layer where the attention mechanism chooses the most relevant features and generates low-dimensional augmented features. Finally, BiLSTM is used to classify the processed sequential information. We conducted experiments on two publicly available databases to show that the proposed approach achieves the state-of-the-art results with an accuracy of 97% and 84% while being able to generate explanations. Explainability analysis has been carried out using feature visualization through PCA projection and t-SNE plots.<br></p>

Sign in / Sign up

Export Citation Format

Share Document