Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 1.776
Filter
Add filters

Year range
1.
Computers and Electrical Engineering ; JOUR: 108479,
Article in English | ScienceDirect | ID: covidwho-2104658

ABSTRACT

Recent studies have shown that computed tomography (CT) scan images can characterize COVID-19 disease in patients. Several deep learning (DL) methods have been proposed for diagnosis in the literature, including convolutional neural networks (CNN). But, with inefficient patient classification models, the number of 'False Negatives' can put lives at risk. The primary objective is to improve the model so that it does not reveal 'Covid' as 'Non-Covid'. This study uses Dense-CNN to categorize patients efficiently. A novel loss function based on cross-entropy has also been used to improve the CNN algorithm's convergence. The proposed model is built and tested on a recently published large dataset. Extensive study and comparison with well-known models reveal the effectiveness of the proposed method over known methods. The proposed model achieved a prediction accuracy of 93.78%, while false-negative is only 6.5%. This approach's significant advantage is accelerating the diagnosis and treatment of COVID-19.

2.
Indian J Pathol Microbiol ; 65(4): 902-906, 2022.
Article in English | MEDLINE | ID: covidwho-2100021

ABSTRACT

COVID-19 pandemic caused by SARS-CoV-2 virus has been around for 2 years causing significant health-care catastrophes in most parts of the world. The understanding of COVID-19 continues to expand, with multiple newer developments such as the presence of asymptomatic cases, feco-oral transmission, and endothelial dysfunction. The existing classification was developed before this current understanding. With the availability of recent literature evidences, we have attempted a classification encompassing pathogenesis and clinical features for better understanding of the disease process. The pathogenesis of COVID-19 continues to evolve. The spiked protein of the SARS-CoV-2 virus binds to ACE2 receptors causes direct cytopathic damage and hyperinflammatory injury. In addition to alveolar cells, ACE2 is also distributed in gastrointestinal tract and vascular endothelium. ACE2-SARS-CoV-2 interaction engulfs the receptors leading to depletion. Accumulation of Ang2 via AT1 receptor (AT1R) binding causes upregulation of macrophage activity leading to pro-inflammatory cytokine release. Interleukin-6 (IL-6) has been attributed to cause hyperinflammatory syndrome in COVID-19. In addition, it also causes severe widespread endothelial injury through soluble IL-6 receptors. Thrombotic complications occur following the cleavage and activation of von Willebrand factor. Based on the above understanding, clinical features, organ involvement, risk stratification, and disease severity, we have classified COVID-19 patients into asymptomatic, pulmonary, GI, and systemic COVID-19 (S-COVID-19). Studies show that the infectivity and prognosis are different and distinct amongst these groups. Systemic-COVID-19 patients are more likely to be critically ill with multi-organ dysfunction and thrombo-embolic complications.


Subject(s)
COVID-19 , Humans , SARS-CoV-2 , Pandemics , Angiotensin-Converting Enzyme 2 , Peptidyl-Dipeptidase A/metabolism
3.
BMC Bioinformatics ; 22(Suppl 15): 625, 2022 Apr 19.
Article in English | MEDLINE | ID: covidwho-1798449

ABSTRACT

BACKGROUND: Being able to efficiently call variants from the increasing amount of sequencing data daily produced from multiple viral strains is of the utmost importance, as demonstrated during the COVID-19 pandemic, in order to track the spread of the viral strains across the globe. RESULTS: We present MALVIRUS, an easy-to-install and easy-to-use application that assists users in multiple tasks required for the analysis of a viral population, such as the SARS-CoV-2. MALVIRUS allows to: (1) construct a variant catalog consisting in a set of variations (SNPs/indels) from the population sequences, (2) efficiently genotype and annotate variants of the catalog supported by a read sample, and (3) when the considered viral species is the SARS-CoV-2, assign the input sample to the most likely Pango lineages using the genotyped variations. CONCLUSIONS: Tests on Illumina and Nanopore samples proved the efficiency and the effectiveness of MALVIRUS in analyzing SARS-CoV-2 strain samples with respect to publicly available data provided by NCBI and the more complete dataset provided by GISAID. A comparison with state-of-the-art tools showed that MALVIRUS is always more precise and often have a better recall.


Subject(s)
COVID-19 , Genome, Viral , High-Throughput Nucleotide Sequencing , Humans , Mutation , Pandemics , Phylogeny , SARS-CoV-2/genetics
4.
2022 International Joint Conference on Neural Networks, IJCNN 2022 ; JOUR, 2022-July.
Article in English | Scopus | ID: covidwho-2097612

ABSTRACT

Presently, the coronavirus disease 2019 (COVID-19) has infected more than 200 million of the world's population and has killed more than 4 million people. In addition to reverse transcription nucleic acid polymerase chain reaction (RT-PCR) as the main detection method, the deep learning-based method using diagnose X-ray or CT scans has become an promising alternative. Last years, Convolution neural network (CNN) has became the methodology choices in the field of medical images until the emergence of Vision Transformer (ViT) broke this situation. Transformer gradually dominates in the field of computer vision, but Transformer lacks inductive biases of convolution operation, requires a lot of data to achieve better performance than CNN, and the amount of calculation is too large when the input is a high-resolution picture. It is found that Transformer and CNN can complement each other. Therefore, there are many kinds of research on the combination of them. However, there is little research on the hybrid model's diagnostic direction of medical images, especially COVID-19 image classification. For this problem, we search the way of marrying CNN and Transformer and propose a hybrid model combining CNN and Transformer, which we called DenseTransformer. Experiments on our COVID-19 CT scans dataset show that the hybrid model, which combines CNN and Transformer properly, can perform better than pure CNN and pure Transformer in the COVID-19 image classification task, and the performance will be further improved after using self-supervised learning. © 2022 IEEE.

5.
J Int Med Res ; 50(11): 3000605221133009, 2022 Nov.
Article in English | MEDLINE | ID: covidwho-2098198

ABSTRACT

OBJECTIVE: To investigate the effect of coronavirus disease 2019 restrictions on ultrasound (US) screening of developmental dysplasia of the hip (DDH) in a children's hospital. METHODS: The records of US screening of DDH were retrospectively evaluated in the pandemic period (April 2020 to July 2021) and the pre-pandemic period (January 2019 to February 2020). The monthly US number, sex, radiologist number, and age at the initial examination were recorded. RESULTS: A total of 6107 US scans were performed during the pre-pandemic period, which significantly decreased to 3340 during the pandemic. The number of monthly US scans performed did not change between the pre-pandemic (142.7/month) and pandemic (128.2/month) periods. The number of delayed examinations in the total population did not significantly change between the two periods. However, the number of delayed examinations in patients with abnormal hips was significantly increased during the pandemic compared with that in the pre-pandemic period. CONCLUSIONS: Coronavirus disease 2019 restrictions decreased the US screening rate of DDH by almost half, but the number of US scans performed by each radiologist was unchanged. The compliance with follow-up recommendations was reduced by half, which may lead to an increase in the incidence of delayed and untreated DDH cases.


Subject(s)
COVID-19 , Developmental Dysplasia of the Hip , Hip Dislocation, Congenital , Child , Humans , Infant , Hip Dislocation, Congenital/diagnostic imaging , Hip Dislocation, Congenital/epidemiology , Pandemics , COVID-19/diagnostic imaging , COVID-19/epidemiology , Retrospective Studies , Follow-Up Studies , Turkey/epidemiology , Ultrasonography
6.
Mater Today Proc ; 2020 Sep 22.
Article in English | MEDLINE | ID: covidwho-2095742

ABSTRACT

COVID-19 pandemic has become the most devastating disease of the current century and spread over 216 countries around the world. The disease is spreading through outbreaks despite the availability of modern sophisticated medical treatment. Machine Learning and Image Analysis research has been making great progress in many directions in the healthcare field for providing support to subsequent medical diagnosis. In this paper, we have propose three research directions with methodologies in the fight against the pandemic namely: Chest X-Ray (CXR) images classification using deep convolution neural networks with transfer learning to assist diagnosis; Patient Risk prediction of pandemic based on risk factors such as patient characteristics, comorbidities, initial symptoms, vital signs for prognosis of disease; and forecasting of disease spread & case fatality rate using deep neural networks. Further, some of the challenges, open datasets and opportunities are discussed for researchers.

7.
Knowledge-Based Systems ; JOUR: 110086,
Article in English | ScienceDirect | ID: covidwho-2095727

ABSTRACT

Online learning is also referred to as E-learning which has gained huge attention and attracted most people during the COVID-19 lockdowns. Due to the excess of online information, users face severe challenges and difficulties realizing the best course that is being competitive in the global market. Therefore, it is necessary to develop an online recommendation system that supports the users in selecting the finest course with E-learning. Thus, the proposed work develops a robust RS model using different approaches. Initially, the pre-processing stage is performed to reduce the presented noise in the website data. Then, the feature extraction stage is done to extract the needed features using Improved TF-IDF, W2V (Word 2 Vector), and Hybrid N-gram. Finally, Elman Minimal Redundancy Maximum Relevance and Enhanced Aquila Optimization (EMRMR_EAO) model is proposed to provide Robust course recommendations. In this work, the ERNN method is used to classify the sentiments based on the similarity measure of the MRMR model. The top course recommendation is afforded depending on the similarity scores like Jaccard similarity, cosine similarity and euclidean similarity. Also, the loss function in the classifier is reduced by optimizing the weight parameters using the EAO approach. The performance analysis shows that the proposed recommendation model obtains improved results in terms of accuracy of 99.98%, recall of 99.81%, precision of 99.65%, and F-measure of 99.95%. The comparative analysis exhibit that the proposed EMRMR_EAO model attains better performance than the other existing works in the literature.

8.
Traffic Inj Prev ; : 1-6, 2022 Nov 01.
Article in English | MEDLINE | ID: covidwho-2097143

ABSTRACT

OBJECTIVE: We investigated changes in the prevalence of speeding during March-June 2020, the beginning of the COVID-19 pandemic, in Virginia. METHODS: Vehicle speed data from 506 permanent speed counter stations around the state collected during March-June 2019 and March-June 2020 were analyzed. RESULTS: Increases in the proportion of vehicles traveling at least 5 mph and 10 mph above the speed limit were greatest on urban interstates and other freeways, during early morning (6:00-8:59 a.m.) and afternoon commuting hours (3:00-5:59 p.m.) on weekdays, and during afternoons (12:00-5:59 p.m.) on weekends. Logistic regression revealed that the risk of speeding by at least 5 mph increased in 2020 by 22% and by at least 10 mph increased 51% after accounting for road type, time of day, day of week, and traffic volume, relative to 2019. DISCUSSION: Future research should continue to identify where and when speeding problems are most severe, and countermeasures should be directed to the roads and time periods with the largest speeding problems.

9.
J Pharm Sci ; 2022 Nov 02.
Article in English | MEDLINE | ID: covidwho-2096154

ABSTRACT

The COVID-19 pandemic outbreak has been overwhelming the healthcare system worldwide. A rapidly growing number of younger pediatric patients in Thailand necessitated the formulation of favipiravir, the most locally accessible antiviral agent against COVID-19, into a child-friendly dosage form as a safer alternative to a dispersion of crushed tablets in simple syrup. While striving to quickly develop a liquid formulation that is feasible for any local hospital production units, an oral solution was chosen due to its simplicity. Despite the large dose and poor aqueous solubility of favipiravir, a combination of pH control and use of poloxamer as a solubilizing agent has enabled us to streamline the manufacturing process of a 200 mg/15 mL oral solution for hospital compounding. To ensure its efficacy and safety, a specification for quality control was also established in accordance with the ICH quality guidelines and USP. The finished product stability was subsequently demonstrated under the conditions of 5°C ± 3°C, 25°C ± 2°C/75% RH ± 5% RH, 30°C ± 2°C/75% RH ± 5% RH, and 40°C ± 2°C/75% RH ± 5% RH. The results indicated that our formulation can be stored at 30°C ± 2°C/75% RH for 30 days, which will very well serve the need to allow drug distribution and patient use during the crisis, while the shelf-life can be extended to 60 days when stored at 5°C ± 3°C. Thus, accessibility to an essential medical treatment has been successfully enhanced for pediatric patients in Thailand and neighboring countries during the COVID-19 outbreak.

10.
An Interdisciplinary Approach in the Post-COVID-19 Pandemic Era ; CHAP: 197-206,
Article in English | Scopus | ID: covidwho-2092866

ABSTRACT

There is a lot of change in the learning of the students after the pandemic COVID-19. To study the resulting impact on their learning is the main aim of this article. To review this, a dataset of the various students is created and subsequently processed and visualized. The data is undergone to the various classification techniques using machine learning. It is observed after the analysis that the support vector machine (SVM) method is best in terms of the classification accuracy while random forest (RF) method is best in terms of the classification sensitivity. © 2022 Nova Science Publishers, Inc..

11.
Journal of Intelligent & Fuzzy Systems ; JOUR: 1-16,
Article in English | Academic Search Complete | ID: covidwho-2089733

ABSTRACT

The Corona virus pandemic has affected the normal course of life. People all over the world take the social media to express their opinions and general emotions regarding this phenomenon. In a relatively short period of time, tweets about the new Corona virus increased by an amount never before seen on the social networking site Twitter. In this research work, Sentiment Analysis of Social Media Data to Identify the Feelings of Indians during Corona Pandemic under National Lockdown using recurrent neural network is proposed. The proposed method is analyzed using four steps: that is Data collection, data preparation, Building sentiment analysis model and Visualization of the results. For Data collection, the twitter dataset are collected from social networking platform twitter by application programming interface. For Data preparation, the input data set are pre-processed for removing URL links, removing unnecessary spaces, removing punctuations and numbers. After data cleaning or preprocessing entire particular characters and non-US characters from Standard Code for Information Interchange, apart from hash tag, are extracted as refined tweet text. In addition, entire behaviors less than three alphabets are not assumed at analysis of tweets, lastly, tokenization and derivation was carried out by Porter Stemmer to perform opinion mining. To authenticate the method, categorized the tweets linked to COVID-19 national lockdown. For categorization, recurrent neural method is used. RNN classify the sentiment classification as positive, negative and neutral sentiment scores. The efficiency of the proposed RNN based Sentimental analysis classification of COVID-19 is assessed various performances by evaluation metrics, like sensitivity, precision, recall, f-measure, specificity and accuracy. The proposed method attains 24.51%, 25.35%, 31.45% and 24.53% high accuracy, 43.51%, 52.35%, 21.45% and 28.53% high sensitivity than the existing methods. [ FROM AUTHOR]

12.
Technol Health Care ; 30(6): 1299-1314, 2022.
Article in English | MEDLINE | ID: covidwho-2089739

ABSTRACT

BACKGROUND: Coronavirus disease 2019 (COVID-19) is a deadly viral infection spreading rapidly around the world since its outbreak in 2019. In the worst case a patient's organ may fail leading to death. Therefore, early diagnosis is crucial to provide patients with adequate and effective treatment. OBJECTIVE: This paper aims to build machine learning prediction models to automatically diagnose COVID-19 severity with clinical and computed tomography (CT) radiomics features. METHOD: P-V-Net was used to segment the lung parenchyma and then radiomics was used to extract CT radiomics features from the segmented lung parenchyma regions. Over-sampling, under-sampling, and a combination of over- and under-sampling methods were used to solve the data imbalance problem. RandomForest was used to screen out the optimal number of features. Eight different machine learning classification algorithms were used to analyze the data. RESULTS: The experimental results showed that the COVID-19 mild-severe prediction model trained with clinical and CT radiomics features had the best prediction results. The accuracy of the GBDT classifier was 0.931, the ROUAUC 0.942, and the AUCPRC 0.694, which indicated it was better than other classifiers. CONCLUSION: This study can help clinicians identify patients at risk of severe COVID-19 deterioration early on and provide some treatment for these patients as soon as possible. It can also assist physicians in prognostic efficacy assessment and decision making.


Subject(s)
COVID-19 , Humans , COVID-19/diagnostic imaging , Tomography, X-Ray Computed/methods , Machine Learning , Lung/diagnostic imaging , Algorithms , Retrospective Studies
13.
EURASIP J Adv Signal Process ; 2022(1): 100, 2022.
Article in English | MEDLINE | ID: covidwho-2089237

ABSTRACT

Representation of one-dimensional (1D) signals as surfaces and higher-dimensional manifolds reveals geometric structures that can enhance assessment of signal similarity and classification of large sets of signals. Motivated by this observation, we propose a novel robust algorithm for extraction of geometric features, by mapping the obtained geometric objects into a reference domain. This yields a set of highly descriptive features that are instrumental in feature engineering and in analysis of 1D signals. Two examples illustrate applications of our approach to well-structured audio signals: Lung sounds were chosen because of the interest in respiratory pathologies caused by the coronavirus and environmental conditions; accent detection was selected as a challenging speech analysis problem. Our approach outperformed baseline models under all measured metrics. It can be further extended by considering higher-dimensional distortion measures. We provide access to the code for those who are interested in other applications and different setups (Code: https://github.com/jeremy-levy/Classification-of-audio-signals-using-spectrogram-surfaces-and-extrinsic-distortion-measures). Supplementary Information: The online version contains supplementary material available at 10.1186/s13634-022-00933-9.

14.
IPEM Transl ; : 100008, 2022 Oct 26.
Article in English | MEDLINE | ID: covidwho-2086322

ABSTRACT

The infectious disease known as COVID-19 has spread dramatically all over the world since December 2019. The fast diagnosis and isolation of infected patients are key factors in slowing down the spread of this virus and better management of the pandemic. Although the CT and X-ray modalities are commonly used for the diagnosis of COVID-19, identifying COVID-19 patients from medical images is a time-consuming and error-prone task. Artificial intelligence has shown to have great potential to speed up and optimize the prognosis and diagnosis process of COVID-19. Herein, we review publications on the application of deep learning (DL) techniques for diagnostics of patients with COVID-19 using CT and X-ray chest images for a period from January 2020 to October 2021. Our review focuses solely on peer-reviewed, well-documented articles. It provides a comprehensive summary of the technical details of models developed in these articles and discusses the challenges in the smart diagnosis of COVID-19 using DL techniques. Based on these challenges, it seems that the effectiveness of the developed models in clinical use needs to be further investigated. This review provides some recommendations to help researchers develop more accurate prediction models.

15.
Multimed Syst ; : 1-13, 2022 Oct 26.
Article in English | MEDLINE | ID: covidwho-2085390

ABSTRACT

The pandemic that the SARS-CoV-2 originated in 2019 is continuing to cause serious havoc on the global population's health, economy, and livelihood. A critical way to suppress and restrain this pandemic is the early detection of COVID-19, which will help to control the virus. Chest X-rays are one of the more straightforward ways to detect the COVID-19 virus compared to the standard methods like CT scans and RT-PCR diagnosis, which are very complex, expensive, and take much time. Our research on various papers shows that the currently researchers are actively working for an efficient Deep Learning model to produce an unbiased detection of COVID-19 through chest X-ray images. In this work, we propose a novel convolution neural network model based on supervised classification that simultaneously computes identification and verification loss. We adopt a transfer learning approach using pretrained models trained on imagenet dataset such as Alex Net and VGG16 as back-bone models and use data augmentation techniques to solve class imbalance and boost the classifier's performance. Finally, our proposed classifier architecture model ensures unbiased and high accuracy results, outperforming existing deep learning models for COVID-19 detection from chest X-ray images producing State of the Art performance. It shows strong and robust performance and proves to be easily deployable and scalable, therefore increasing the efficiency of analyzing chest X-ray images with high accuracy in detection of Coronavirus.

16.
Mobile Networks and Applications ; JOUR
Article in English | Web of Science | ID: covidwho-2082795

ABSTRACT

Medical emergency transit counts minutes as real human lives. It is important to plan emergency transport routes according to real-time traffic flow status which leads to the the essential requirement of correct dynamic traffic prediction. Many Internet of Things (IoT) devices have been employed to assist emergency transit. Dynamic traffic flow patterns can be better predicted using data given by those devices. In small cities, however, the data are sent into separated management offices or just saved inside edge devices due to system compatibility or the cost of mobile network to computer centres. This condition leads to small and local datasets. Making full use of small local data to conduct prediction is one way to solve local emergency planning problems. In this work, we design a dynamic graph structure to work with Graph Neural Network (GNN) algorithm to forecast traffic flow levels considering this scenario. The proposed graph considers both geographical and time information with the potential to grow within a local mobile communication network. The commonly used Extreme Gradient Boosting (XGBoost) is included in the comparison. Experimental results show that our new design provides high prediction efficiency and accuracy.

17.
Measurement: Sensors ; JOUR:100537, 24.
Article in English | ScienceDirect | ID: covidwho-2082545

ABSTRACT

Coronavirus is a disease connected to coronavirus. World Health Organization has declared COVID-19 a pandemic. It has an impact on 212 nations and territories worldwide. Examining and identifying patterns in X-Ray pictures of the lungs is still necessary. Early diagnosis may help to lessen a person's virus exposure and prevent it. Manual diagnosis is a time- and labor-intensive process. Since the COVID-19 virus has the potential to infect individuals all around the world, its finding is extremely concerning. The purpose of this study is to apply machine learning to identify and classify coronaviruses. The COVID-19 is anticipated to be discriminated and categorized in CT-Lung screening and computer-aided diagnosis (CAD). Several machine learning methods, including Decision Tree, Support Vector Machine, K-means clustering, and Radial Basis Function, were utilised in conjunction with clinical samples from patients who had contracted corona. While some medical professionals think an RT-PCR test is the most reliable and economical way to detect Covid-19 patients, others think a lung CT scan is more precise and less expensive. Serum samples, respiratory secretions, and whole blood samples are examples of clinical specimens. As a result of the earlier clinical evaluations, these tissues are used to assess 15 different parameters. As part of the proposed four-phase CAD system, the CT lungs screening collection is followed by a pre-processing step that enhances the appearance of ground-glass opacities (GGOs) nodules, which are initially extremely fuzzy and poorly contrasting due to the absence of contrast. These zones will be found and segmented using a modified K-means technique. Support vector machines (SVM) and radial basis functions (RBF) will be used as the input and target data for machine learning classifiers with a 50x50 pixel resolution to categorise the contaminated zones found during the detection phase (RBF). The 15 input items gathered from clinical specimens may be entered into a graphical user interface (GUI) tool that has been created to help doctors receive accurate findings.

18.
Concurrency and Computation: Practice and Experience ; JOUR
Article in English | Web of Science | ID: covidwho-2082435

ABSTRACT

Many researchers in various disciplines have focused on extracting meaningful information from social media platforms in recent years. Identification of behaviors and emotions from user posts is examined under the heading of sentiment analysis (SA) studies using the natural language processing (NLP) techniques. In this study, a novel TCNN-Bi-LSTM model using the two-stage convolutional neural network (TCNN) and bidirectional long short-term memory (Bi-LSTM) architectures was proposed. While TCNN layers enable the extraction of strong local features, the output of these layers feeds the Bi-LSTM model that remembers forward-looking information and capture long-term dependencies. In this study, first, preprocessing steps were applied to the raw dataset. Thus, strong features were extracted from the obtained quality dataset using the FastText word embedding technique that pre-trained with location-based and sub-word information features. The experimental results of the proposed method are promising compared to the baseline deep learning and machine learning models. Also, experimental results show that while the FastText data embedding technique achieves the best performance compared to other word embedding techniques in all deep learning classification models, it has not had the same outstanding success in machine learning models. This study aims to investigate the sentiments of tweets about the COVID-19 vaccines and comments on these tweets among Twitter users by using the power of Twitter data. A new dataset collected from Twitter was constructed to be used in experimental results. This study will facilitate detecting inappropriate, incomplete, and erroneous information about vaccination. The results of this study will enable society to broaden its perspective on the administered vaccines. It can also assist the government and healthcare agencies in planning and implementing the vaccination's promotion on time to achieve the herd immunity provided by the vaccination.

19.
Comput Med Imaging Graph ; 102: 102129, 2022 Oct 19.
Article in English | MEDLINE | ID: covidwho-2083067

ABSTRACT

The emerging field of radiomics that transforms standard-of-care images to quantifiable scalar statistics endeavors to reveal the information hidden in these macroscopic images. The concept of texture is widely used and essential in many radiomic-based studies. Practice usually reduces spatial multidimensional texture matrices, e.g., gray-level co-occurrence matrices (GLCMs), to summary scalar features. These statistical features have been demonstrated to be strongly correlated and tend to contribute redundant information; and does not account for the spatial information hidden in the multivariate texture matrices. This study proposes a novel pipeline to deal with spatial texture features in radiomic studies. A new set of textural features that preserve the spatial information inherent in GLCMs is proposed and used for classification purposes. The set of the new features uses the Wasserstein metric from optimal mass transport theory (OMT) to quantify the spatial similarity between samples within a given label class. In particular, based on a selected subset of texture GLCMs from the training cohort, we propose new representative spatial texture features, which we incorporate into a supervised image classification pipeline. The pipeline relies on the support vector machine (SVM) algorithm along with Bayesian optimization and the Wasserstein metric. The selection of the best GLCM references is considered for each classification label and is performed during the training phase of the SVM classifier using a Bayesian optimizer. We assume that sample fitness is defined based on closeness (in the sense of the Wasserstein metric) and high correlation (Spearman's rank sense) with other samples in the same class. Moreover, the newly defined spatial texture features consist of the Wasserstein distance between the optimally selected references and the remaining samples. We assessed the performance of the proposed classification pipeline in diagnosing the coronavirus disease 2019 (COVID-19) from computed tomographic (CT) images. To evaluate the proposed spatial features' added value, we compared the performance of the proposed classification pipeline with other SVM-based classifiers that account for different texture features, namely: statistical features only, optimized spatial features using Euclidean metric, non-optimized spatial features with Wasserstein metric. The proposed technique, which accounts for the optimized spatial texture feature with Wasserstein metric, shows great potential in classifying new COVID CT images that the algorithm has not seen in the training step. The MATLAB code of the proposed classification pipeline is made available. It can be used to find the best reference samples in other data cohorts, which can then be employed to build different prediction models.

20.
Knowl Based Syst ; 258: 110040, 2022 Dec 22.
Article in English | MEDLINE | ID: covidwho-2082723

ABSTRACT

During the past two years, a highly infectious virus known as COVID-19 has been damaging and harming the health of people all over the world. Simultaneously, the number of patients is rising in various countries, with many new cases appearing daily, posing a significant challenge to hospital medical staff. It is necessary to improve the efficiency of virus detection. To this end, we combine modern technology and visual assistance to detect COVID-19. Based on the above facts, for accurate and rapid identification of infected persons, the BND-VGG-19 method was proposed. This method is based on VGG-19 and further incorporates batch normalization and dropout layers between the layers to improve network accuracy. Then, the COVID-19 dataset including viral pneumonia, COVID-19, and normal X-ray images, are used to diagnose lung abnormalities and test the performance of the proposed algorithm. The experimental results show the superiority of BND-VGG-19 with a 95.48% accuracy rate compared with existing COVID-19 diagnostic methods.

SELECTION OF CITATIONS
SEARCH DETAIL