Classifying Chest X-rays for COVID-19 using Deep Learning

A developing virus called COVID-19 infects the lungs and upper layer respiratory system. Medical imaging and PCR assays can be used to identify COVID-19. Medical images are used to identify COVID-19 diseases in the proposed classification model, which works well. A crucial step in the battle against this fatal illness may turn out to be an efficient screening and diagnostic phase in treating infected sufferers. Chest X-ray (CXR) scans could be used to do this. The utilization of chest X-ray imaging for early detection may prove to be a crucial strategy in the fight against COVID-19. Many computer- aided diagnostic (CAD) methods have been developed to help radiologists and provide them with more information for the same. In a training network with many classes, tertiary classification starts to become more accurate as the number of classes increases. © 2023 IEEE.

Federated Learning for Detecting COVID-19 in Chest CT Images: A Lightweight Federated Learning Approach

The novel coronavirus is spreading rapidly worldwide, and finding an effective and rapid diagnostic method is apriority. Medical data involves patient privacy, and the centralized collection of large amounts of medical data is impossible. Federated learning is a privacy-preserving machine learning paradigm that can be well applied to smart healthcare by coordinating multiple hospitals to perform deep learning training without transmitting data. This paper demonstrates the feasibility of a federated learning approach for detecting COVID-19 through chest CT images. We propose a lightweight federated learning method that normalizes the local training process by globally averaged feature vectors. In the federated training process, the models' parameters do not need to be transmitted, and the local client only uploads the average of the feature vectors of each class. Clients can choose different local models according to their computing capabilities. We performed a comprehensive evaluation using various deep-learning models on COVID-19 chest CT images. The results show that our approach can effectively reduce the communication load of federated learning while having high accuracy for detecting COVID-19 on chest CT images. © 2022 IEEE.

A Novel Explainable CNN Model for Screening COVID-19 on X-ray Images

Due to the rapid propagation characteristic of the Coronavirus (COV-ID-19) disease, manual diagnostic methods cannot handle the large number of infected individuals to prevent the spread of infection. Despite, new automated diagnostic methods have been brought on board, particularly methods based on artificial intelligence using different medical data such as X-ray imaging. Thoracic imaging, for example, produces several image types that can be processed and analyzed by machine and deep learning methods. X-ray imaging materials widely exist in most hospitals and health institutes since they are affordable compared to other imaging machines. Through this paper, we propose a novel Convolutional Neural Network (CNN) model (COV2Net) that can detect COVID-19 virus by analyzing the X-ray images of suspected patients. This model is trained on a dataset containing thousands of X-ray images collected from different sources. The model was tested and evaluated on an independent dataset. In order to approve the performance of the proposed model, three CNN models namely MobileNet, Residential Energy Services Network (Res-Net), and Visual Geometry Group 16 (VGG-16) have been implemented using transfer learning technique. This experiment consists of a multi-label classification task based on X-ray images for normal patients, patients infected by COVID-19 virus and other patients infected with pneumonia. This proposed model is empowered with Gradient-weighted Class Activation Mapping (Grad-CAM) and Grad-Cam++ techniques for a visual explanation and methodology debugging goal. The finding results show that the proposed model COV2Net outperforms the state-of-the-art methods. © 2023 CRL Publishing. All rights reserved.

3D CNN-Based Classification of Severity in COVID-19 Using CT Images

With the pandemic worldwide due to COVID-19, several detections and diagnostic methods have been in place. One of the standard modes of detection is computed tomography imaging. With the availability of computing resources and powerful GPUs, the analyses of extensive image data have been possible. Our proposed work initially deals with the classification of CT images as normal and infected images, and later, from the infected data, the images are classified based on their severity. The proposed work uses a 3D convolution neural network model to extract all the relevant features from the CT scan images. The results are also compared with the existing state-of-the-art algorithms. The proposed work is evaluated in accuracy, precision, recall, kappa value, and Intersection over Union. The model achieved an overall accuracy of 94.234% and a kappa value of 0.894. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Main Diagnostic Methods for Covid-19: Integrative Review.

BACKGROUND: COVID-19 has reached more than 20 million people since its appearance in December 2019. As a result of the infection process by the Sars-CoV-2 virus, patients manifest initial symptoms easily mistaken for common flu. However, in a small group of the population, the condition may progress to pneumonia or Severe Acute Respiratory Syndrome (SARS). OBJECTIVE: The objective of this study was to carry out an integrative review on laboratory and imaging diagnostics for COVID-19, in the period from 2019 to 2021. METHOD: Electronic databases PubMed, Google Scholar, SciELO, Virtual Library, LILACS, MEDLINE, ScienceDirect and the official website of the World Health Organization were used. RESULTS: RT-qPCR identifies fragments of viral RNA in the initial stage of the disease since the genes E and RdRp are the most used, given the great sensitivity. Imaging and serological methods can be used as complementary exams. The main radiographic findings are reticular and ground-glass opacity patterns, reversed halo sign, mosaic attenuation, and consolidations. The antibody levels are detected after the seventh day of symptom onset. CONCLUSION: Caution should be exercised when interpreting the results for the diagnosis of COVID-19, since the onset of clinical symptoms and laboratory and imaging tests must be taken into account.

Identification of SARS-CoV-2 Pneumonia in Chest X-ray Images Using Convolutional Neural Networks

In 2019, COVID-19 disease emerged in Wuhan, China, leading to a pandemic that saturated health systems, raising the need to develop effective diagnostic methods. This work presents an approach based on artificial intelligence applied to X-ray images obtained from Mexican patients, provided by Hospital General de Zona No. 24. A dataset of 612 images with 2 classes: COVID and HEALTHY, were labelled by a radiologist and also verified with positive RT-PCR test. The first class contains X-ray images of patients with pneumonia due to SARS-CoV-2 and the second contains patients without diseases affecting the lung parenchyma. The proposed work aims to classify COVID-19 pneumonia using convolutional neural networks to provide the physician with a suggestive diagnosis. Images were automatically trimmed and then transfer learning was applied to VGG-16 and ResNet-50 models, which were trained and tested using the generated dataset, both achieving an accuracy, recall, specificity and F1-score of over 98%. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Electrochemical biosensing based on graphene for detection of the SARS-Co V-2 Nucleocapsid Protein

Monitoring and controlling infection is required in order to prevent the progression of the coronavirus severe acute respiratory syndrome 2(SARS-Co- V-2). To accomplish this goal, the development and implementation of sensitive, quick and accurate diagnostic methods are essential. Electrochemical sensors have exposed large application possibilities in biological detection due to the advantages of high sensitivity, short time-consuming and specificity. Here, we report the improvement of a sensitive electrochemical sensor capable of detecting the presence of the SARS-CoV-2 virus using graphene-modified interdigitated working electrodes functionalized with antibodies targeting the SARS-CoV-2 nucleocapsid protein (N protein). © 2022 IEEE.

COVID-19 Diagnostic Methods and Detection Techniques

Coronavirus disease 2019 (COVID-19) is an emerging human-to-human infectious disease that broke out in early December 2019 and threatens global public health, causing widespread concern. This respiratory disease is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The development of rapid and reliable techniques for COVID-19 diagnosis is a significant step to prevent further infections. Combinations of genome sequencing, nucleic acid molecular testing, clustered regularly interspaced short palindromic repeats editing technology, antigen/antibody detection, and computed tomography imaging have been implemented to identify and screen COVID-19 infections. Moreover, other new diagnosis methods such as dried blood spots and biosensors are being developed and are summarized here. This manuscript reviews currently available methods for SARS-CoV-2 detection with the aim of helping researchers develop timely and effective technologies to detect this emerging virus and its variants.

Caps-3WD: A three-way diagnostic CapsNet for COVID-19

Pulmonary medical image processing is an effective diagnostic method for COVID-19, and CapsNet-based methods have achieved good performance. However, as cost-blind methods, these diagnostic methods only consider immediate and deterministic decisions, which easily lead to misdiagnosis and high costs. Therefore, based on a revised CapsNet, we propose a cost-sensitive three-way decision (3WD) method for COVID-19 diagnosis, named as Caps-3WD. To enhance the feature extraction ability for pneumonia areas, we introduce a Restage module to improve convolution layer of the original CapsNet. Further, to lighten the model, we introduce depth wise separable convolution to reconstruct decoder. Additionally, three options are considered in the decision set: infected, normal, and suspected, which are given different costs, respectively. The lowest-cost decision is chosen for each input. In the experimental analysis, we compare Caps-3WD with CNN-based and CapsNet-based methods on COVID-CXR dataset, which proves the effectiveness of 3WD and the superiority of Caps-3WD in COVID-19 diagnosis. © 2022 SPIE. Downloading of the is permitted for personal use only.

ULTRASENSITIVE AND RAPID DETECTION OF COVID-19 VIRUS USING DUAL-CLAMPED SURFACE-ENHANCED-RAMAN-SCATTERING NANOSENSORS

The COVID-19 outbreak spreads around world, accumulated to more than 27 million confirmed cases and 800k deaths. Polymerase Chain Reaction (PCR), a gold-standard diagnostic method, were labor intensive, time-consuming and costly, which restricted its application to widespread screening. Herein, this study purposes a one-pot and non-washing method to rapidly detect virus by dual-clamped surface-enhanced Raman scattering (SERS) mechanism. COVID Antigens were captured by SERS nanoparticles and novel SERS substrate simultaneously to achieve 6 order enhancements within 20 minutes. The dual-SERS sensors have reached a detection limit of 1 ng/ml in clinical samples for recognizing nucleocapsid & Spike proteins of COVID-19, which is comparable with PCR results. © 2021 MicroTAS 2021 - 25th International Conference on Miniaturized Systems for Chemistry and Life Sciences. All rights reserved.

A Design Using the IoT to Prevent Future Pandemics and Identify People with COVID-19 Symptoms

The WHO has given a pandemic situation alert to world countries due to the Novel Corona Virus Disease (COVID-19) outbreak. The COVID-19 is basically has spread four various stages namely appearance of the disease, local transmission, community transmission, Widespread outbreak but still now India staying in the second stage only and trying to avoid the third stage of community transmission via various actions and strategy like effective treatment, lockdown and community distance. Suppose virus affected and house quadrant persons roaming outside and contact with many people's causes of India enter the third stage of community spread and increases COVID-19 positive cases and death rate. The main aim of this research paper is avoided Covid-19 community spared using prevent corona virus affected and house quadrant persons and monitoring high temperature having persons roaming outside with help of drone face identification and thermal scanning mechanisms. © 2022 IEEE.

Utilizing Electrochemical-Based Sensing Approaches for the Detection of SARS-CoV-2 in Clinical Samples: A Review.

The development of precise and efficient diagnostic tools enables early treatment and proper isolation of infected individuals, hence limiting the spread of coronavirus disease 2019 (COVID-19). The standard diagnostic tests used by healthcare workers to diagnose severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection have some limitations, including longer detection time, the need for qualified individuals, and the use of sophisticated bench-top equipment, which limit their use for rapid SARS-CoV-2 assessment. Advances in sensor technology have renewed the interest in electrochemical biosensors miniaturization, which provide improved diagnostic qualities such as rapid response, simplicity of operation, portability, and readiness for on-site screening of infection. This review gives a condensed overview of the current electrochemical sensing platform strategies for SARS-CoV-2 detection in clinical samples. The fundamentals of fabricating electrochemical biosensors, such as the chosen electrode materials, electrochemical transducing techniques, and sensitive biorecognition molecules, are thoroughly discussed in this paper. Furthermore, we summarised electrochemical biosensors detection strategies and their analytical performance on diverse clinical samples, including saliva, blood, and nasopharyngeal swab. Finally, we address the employment of miniaturized electrochemical biosensors integrated with microfluidic technology in viral electrochemical biosensors, emphasizing its potential for on-site diagnostics applications.

Express Diagnosis of COVID-19 on Cough Audiograms with Machine Learning Algorithms from Scikit-learn library and GMDH Shell tool

The ongoing COVID-19 pandemic and necessity of mass control of population makes to create inexpensive rapid diagnostic methods that could replace or complement existing methods based on clinical studies. In response to this challenge, at the end of 2020 MIT scientists proposed a way to detect COVID-19 sick patients using audio recordings of their cough. They build a binary classifier based on a trained deep neural network that provides 99% precision in detecting sick patients on a dataset of 5000 people (the precision of detecting the healthy ones is not reported). In our study, we propose another technology, which uses: (a) a simple transformation of digital audiograms being matrices 'fequency-time'and (b) typical machine learning algorithms from the popular scikit-learn Python library and the platform GMDH Shell. Objects of consideration are: a large unbalanced dataset (282 sick and 1595 healthy) and a small balanced dataset (174 sick and 193 healthy). In total GMDH-based algorithms demonstrated some better results with both datasets. The winners provides the following precisions of detecting sick/healthy patients [%]: (a) 92/95 on the small dataset and 78/95 on the large data set for the algorithm SVM with a Gaussian kernel;(b) 95/97 on the small dataset and 82/96 on the large data set for the algorithm Random Forest based on GMDH. We suppose these results are promising. © 2021 IEEE.

Tween 80 Improves the Acid-Fast Bacilli Quantification in the Magnetic Nanoparticle-Based Colorimetric Biosensing Assay (NCBA).

Despite its reduced sensitivity, sputum smear microscopy (SSM) remains the main diagnostic test for detecting tuberculosis in many parts of the world. A new diagnostic technique, the magnetic nanoparticle-based colorimetric biosensing assay (NCBA) was optimized by evaluating different concentrations of glycan-functionalized magnetic nanoparticles (GMNP) and Tween 80 to improve the acid-fast bacilli (AFB) count. Comparative analysis was performed on 225 sputum smears: 30 with SSM, 107 with NCBA at different GMNP concentrations, and 88 with NCBA-Tween 80 at various concentrations and incubation times. AFB quantification was performed by adding the total number of AFB in all fields per smear and classified according to standard guidelines (scanty, 1+, 2+ and 3+). Smears by NCBA with low GMNP concentrations (≤1.5 mg/mL) showed higher AFB quantification compared to SSM. Cell enrichment of sputum samples by combining NCBA-GMNP, incubated with Tween 80 (5%) for three minutes, improved capture efficiency and increased AFB detection up to 445% over SSM. NCBA with Tween 80 offers the opportunity to improve TB diagnostics, mainly in paucibacillary cases. As this method provides biosafety with a simple and inexpensive methodology that obtains results in a short time, it might be considered as a point-of-care TB diagnostic method in regions where resources are limited.

Micro/nanotechnology-inspired rapid diagnosis of respiratory infectious diseases.

Humans have suffered from a variety of infectious diseases since a long time ago, and now a new infectious disease called COVID-19 is prevalent worldwide. The ongoing COVID-19 pandemic has led to research of the effective methods of diagnosing respiratory infectious diseases, which are important to reduce infection rate and help the spread of diseases be controlled. The onset of COVID-19 has led to the further development of existing diagnostic methods such as polymerase chain reaction, reverse transcription polymerase chain reaction, and loop-mediated isothermal amplification. Furthermore, this has contributed to the further development of micro/nanotechnology-based diagnostic methods, which have advantages of high-throughput testing, effectiveness in terms of cost and space, and portability compared to conventional diagnosis methods. Micro/nanotechnology-based diagnostic methods can be largely classified into (1) nanomaterials-based, (2) micromaterials-based, and (3) micro/nanodevice-based. This review paper describes how micro/nanotechnologies have been exploited to diagnose respiratory infectious diseases in each section. The research and development of micro/nanotechnology-based diagnostics should be further explored and advanced as new infectious diseases continue to emerge. Only a handful of micro/nanotechnology-based diagnostic methods has been commercialized so far and there still are opportunities to explore.

A simple, safe and sensitive method for SARS-CoV-2 inactivation and RNA extraction for RT-qPCR.

The SARS-CoV-2 pandemic has created an urgent need for diagnostic tests to detect viral RNA. Commercial RNA extraction kits are often expensive, in limited supply, and do not always fully inactivate the virus. Together, this calls for the development of safer methods for SARS-CoV-2 extraction that utilize readily available reagents and equipment present in most standard laboratories. We optimized and simplified a RNA extraction method combining a high molar acidic guanidinium isothiocyanate (GITC) solution, phenol and chloroform. First, we determined the GITC/RNA dilution thresholds compatible with an efficient two-step RT-qPCR for B2M mRNA in nasopharyngeal (NP) or oropharyngeal (OP) swab samples. Second, we optimized a one-step RT-qPCR against SARS-CoV-2 using NP and OP samples. We furthermore tested a SARS-CoV-2 dilution series to determine the detection threshold. The method enables downstream detection of SARS-CoV-2 by RT-qPCR with high sensitivity (~4 viral RNA copies per RT-qPCR). The protocol is simple, safe, and expands analysis capacity as the inactivated samples can be used in RT-qPCR detection tests at laboratories not otherwise classified for viral work. The method takes about 30 min from swab to PCR-ready viral RNA and circumvents the need for commercial RNA purification kits.

Current challenges in identification of clinical characteristics and detection of COVID-19: A comprehensive review.

World Health Organization (WHO) declares the COVID-19 outbreak as a pandemic. The newly emerging infection has caused around one million deaths worldwide and still counting. There is no specific treatment for the disease, and it can only contain by breaking the spread. So that early and rapid diagnosis of the infection is the only way to control the outbreak. The COVID-19 virus affects the human respiratory system and subsequently infects other vital organs. In consideration of the diagnosis, the present review focuses on the critical diagnostic approaches for COVID-19, including RT-PCR, Chest-CT scan, some biosensor-based systems, etc. Moreover, this review is a specific bird's eye view on recent developments on the point of care devices and related technologies. Additionally, it presented a small glimpse of the pathophysiology and structural aspects of COVID-19. Therefore, the current review can motivate and help the reader to develop cutting-edge diagnostic technologies for the early and rapid detection of the COVID-19.

A multi-class COVID-19 segmentation network with pyramid attention and edge loss in CT images.

At the end of 2019, a novel coronavirus COVID-19 broke out. Due to its high contagiousness, more than 74 million people have been infected worldwide. Automatic segmentation of the COVID-19 lesion area in CT images is an effective auxiliary medical technology which can quantitatively diagnose and judge the severity of the disease. In this paper, a multi-class COVID-19 CT image segmentation network is proposed, which includes a pyramid attention module to extract multi-scale contextual attention information, and a residual convolution module to improve the discriminative ability of the network. A wavelet edge loss function is also proposed to extract edge features of the lesion area to improve the segmentation accuracy. For the experiment, a dataset of 4369 CT slices is constructed, including three symptoms: ground glass opacities, interstitial infiltrates, and lung consolidation. The dice similarity coefficients of three symptoms of the model achieve 0.7704, 0.7900, 0.8241 respectively. The performance of the proposed network on public dataset COVID-SemiSeg is also evaluated. The results demonstrate that this model outperforms other state-of-the-art methods and can be a powerful tool to assist in the diagnosis of positive infection cases, and promote the development of intelligent technology in the medical field.

COVID-19, Chikungunya, Dengue and Zika Diseases: An Analytical Platform Based on MALDI-TOF MS, IR Spectroscopy and RT-qPCR for Accurate Diagnosis and Accelerate Epidemics Control.

COVID-19 and arboviruses (ARBOD) epidemics co-occurrence is a great concern. In tropical and subtropical regions, ARBOD diseases such as chikungunya, dengue, and Zika are frequent. In both COVID-19 and ARBOD cases, an accurate diagnosis of infected patients is crucial to promote adequate treatment and isolation measures in COVID-19 cases. Overlap of clinical symptoms and laboratory parameters between COVID-19 and ARBOD present themselves as an extra challenge during diagnosis. COVID-19 diagnosis is mainly performed by quantitative reverse polymerase chain reaction (RT-qPCR), while ARBOD diagnosis is performed by serology, detection of antigen or antibody, and molecular diagnosis. In this review, the epidemiologic profile of arboviruses and SARS-CoV-2 is analyzed, and potential risks of symptom overlap is addressed. The implementation of an analytical platform based on infrared (IR) spectroscopy, MALDI-TOF mass spectrometry, and RT-qPCR is discussed as an efficient strategy for a fast, robust, reliable, and cost-effective diagnosis system even during the co-occurrence of virus outbreaks. The spectral data of IR spectroscopy and MALDI-TOF MS obtained from COVID-19 infected and recovered patients can be used to build up an integrated spectral database. This approach can enable us to determine quickly the groups that have been exposed and have recovered from COVID-19 or ARBOD, avoiding misdiagnoses.

COVID-19: Virology, biology and novel laboratory diagnosis.

BACKGROUND: At the end of December 2019, a novel coronavirus tentatively named SARS-CoV-2 in Wuhan, a central city in China, was announced by the World Health Organization. SARS-CoV-2 is an RNA virus that has become a major public health concern after the outbreak of the Middle East Respiratory Syndrome-CoV (MERS-CoV) and Severe Acute Respiratory Syndrome-CoV (SARS-CoV) in 2002 and 2012, respectively. As of 29 October 2020, the total number of COVID-19 cases had reached over 44 million worldwide, with more than 1.17 million confirmed deaths. DISCUSSION: SARS-CoV-2 infected patients usually present with severe viral pneumonia. Similar to SARS-CoV, the virus enters respiratory tract cells via the angiotensin-converting enzyme receptor 2. The structural proteins play an essential role in budding the virus particles released from different host cells. To date, an approved vaccine or treatment option of a preventive character to avoid severe courses of COVID-19 is still not available. CONCLUSIONS: In the present study, we provide a brief review of the general biological features of CoVs and explain the pathogenesis, clinical symptoms and diagnostic approaches regarding monitoring future infectivity and prevent emerging COVID-19 infections.