Search

Coronavirus disease (COVID-19) is a viral pneumonia that originated in China and has rapidly spread around the world. Early diagnosis is important to provide effective and timely treatment. Thus, many studies have attempted to solve the COVID-19 classification problems of workload classification, disease detection, and differentiation from other types of pneumonia and healthy lungs using different radiological imaging modalities. To date, several researchers have investigated the problem of using deep learning methods to detect COVID-19, but there are still unsolved challenges in this field, which this review aims to identify. The existing research on the COVID-19 classification problem suffers from limitations due to the use of the binary or flat multiclass classification, and building classifiers based on only a few classes. Moreover, most prior studies have focused on a single feature modality and evaluated their systems using a small public dataset. These studies also show a reliance on diagnostic processes based on CT as the main imaging modality, ignoring chest X-rays, as explained below. Accordingly, the aim of this review is to examine existing methods and frameworks in the literature that have been used to detect and classify COVID-19, as well as to identify research gaps and highlight the limitations from a critical perspective. The paper concludes with a list of recommendations, which are expected to assist future researchers in improving the diagnostic process for COVID-19 in particular. This should help to develop effective radiological diagnostic data for clinical applications and to open future directions in this area in general. [ABSTRACT FROM AUTHOR]

Coronavirus disease 2019 (COVID-19), originating in China, has rapidly spread worldwide. Physicians must examine infected patients and make timely decisions to isolate them. However, completing these processes is difficult due to limited time and availability of expert radiologists, as well as limitations of the reverse-transcription polymerase chain reaction (RT-PCR) method. Deep learning, a sophisticated machine learning technique, leverages radiological imaging modalities for disease diagnosis and image classification tasks. Previous research on COVID-19 classification has encountered several limitations, including binary classification methods, single-feature modalities, small public datasets, and reliance on CT diagnostic processes. Additionally, studies have often utilized a flat structure, disregarding the hierarchical structure of pneumonia classification. This study aims to overcome these limitations by identifying pneumonia caused by COVID-19, distinguishing it from other types of pneumonia and healthy lungs using chest X-ray (CXR) images and related tabular medical data, and demonstrate the value of incorporating tabular medical data in achieving more accurate diagnoses. Resnet-based and VGG-based pre-trained convolutional neural network (CNN) models were employed to extract features, which were then combined using early fusion for the classification of eight distinct classes. We leveraged the hierarchal structure of pneumonia classification within our approach to achieve improved classification outcomes. Since an imbalanced dataset is common in this field, a variety of versions of generative adversarial networks (GANs) were used to generate synthetic data. The proposed approach tested in our private datasets of 4523 patients achieved a macro-avg F1-score of 95.9% and an F1-score of 87.5% for COVID-19 identification using a Resnet-based structure. In conclusion, in this study, we were able to create an accurate deep learning multi-modal to diagnose COVID-19 and differentiate it from other kinds of pneumonia and normal lungs, which will enhance the radiological diagnostic process. [ABSTRACT FROM AUTHOR]

Background: The current outbreak of COVID-19 infection, which started in Wuhan, Hubei province, China, in December 2019, is an ongoing challenge and a significant threat to public health requiring surveillance, prompt diagnosis, and research efforts to understand a new, emergent, and unknown pathogen and to develop effective therapies. Despite the increasing number of published studies on COVID-19, in all the examined studies the lack of a well-defined pathophysiology of death among patients who died following COVID-19 infection is evident. Autopsy should be considered mandatory to define the exact cause of death, thus providing useful clinical and epidemiologic information as well as pathophysiological insights to further provide therapeutic tools. Methods: A literature review was performed on PubMed database, using the key terms: "COVID-19", "nCov 19", and "Sars Cov 2". 9709 articles were retrieved; by excluding all duplicated articles, additional criteria were then applied: articles or abstracts in English and articles containing one of the following words: "death", "died", "comorbidity", "cause of death", "biopsy", "autopsy", or "pathological". Results: A total of 50 articles met the inclusion criteria. However, only 7 of these studies reported autopsy-based data. Discussion: The analysis of the main data from the selected studies concerns the complete analysis of 12,954 patients, of whom 2269 died (with a mortality rate of 17.52%). Laboratory confirmation of COVID-19 infection was obtained in all cases and comorbidities were fully reported in 46 studies. The most common comorbidities were: cardiovascular diseases (hypertension and coronary artery disease), metabolic disorders (diabetes, overweight, or obesity), respiratory disorders (chronic obstructive pulmonary disease), and cancer. The most common reported complications were: acute respiratory distress syndrome (ARDS), acute kidney injury, cardiac injury, liver insufficiency, and septic shock. Only 7 papers reported histological investigations. Nevertheless, only two complete autopsies are described and the cause of death was listed as COVID-19 in only one of them. The lack of postmortem investigation did not allow a definition of the exact cause of death to determine the pathways of this infection. Based on the few histopathological findings reported in the analyzed studies, it seems to be a clear alteration of the coagulation system: frequently prothrombotic activity with consequent thromboembolism was described in COVID-19 patients. As a scientific community, we are called on to face this global threat, and to defeat it with all the available tools necessary. Despite the improvement and reinforcement of any method of study in every field of medicine and science, encouraging the autopsy practice as a tool of investigation could also therefore, help physicians to define an effective treatment to reduce mortality. [ABSTRACT FROM AUTHOR]

Background: Since December 2019, SARS-CoV-2 has been causing cases of severe pneumonia in China and has spread all over the world, putting great pressure on health systems. Nasopharyngeal swab (NPS) sensitivity is suboptimal. When the SARS-CoV-2 infection is suspected despite negative NPSs, other tests may help to rule out the infection. Objectives: To evaluate the yield of the lower respiratory tract (LRT) isolation of SARS-CoV-2. To evaluate the correlations between SARS-CoV-2 detection and clinical symptoms, and laboratory values and RSNA CT review scores in suspect patients after two negative NPSs. To assess the safety of bronchoscopy in this scenario. Method: A retrospective analysis of data from LRT sampling (blind nasotracheal aspiration or bronchial washing) for suspected COVID-19 after two negative NPS. Chest CT scans were reviewed by two radiologists using the RSNA imaging classification. Results: SARS-CoV-2 was detected in 14/99 patients (14.1%). A correlation was found between SARS-CoV2 detection on the LRT and the presence of a cough as well as with typical CT features. Typical CT resulted in 57.1% sensitivity, 80.8% accuracy and 92.3% NPV. Neither severe complications nor infections in the personnel were reported. Conclusions: In suspect cases after two negative swabs, CT scan revision can help to rule out COVID-19. In selected cases, with consistent CT features above all, LRT sampling can be of help in confirming COVID-19. [ABSTRACT FROM AUTHOR]

The new coronavirus that was first identified in December 2019 in Wuhan China, now called SARS-CoV-2, which causes the disease called COVID-19, has spread from China to the entire world in a few months. Due to its contagious potential (R0: 5.7) and because there is still no effective treatment to stop the infection, and a vaccine for prevention it is not yet available to the general population, COVID-19 is currently considered a global health problem. The need to implement sensitive methods for the identification of individuals with COVID-19 has led to the development of different molecular and immunological tests. The importance of a timely and accurate diagnosis is essential to determine the course of the pandemic. The interpretation of the results obtained by each test as well as the factors that affect these results have not been fully described. In this review, we describe and analyze the different SARS-CoV-2 detection methods that have been performed in Mexico and are available worldwide, outlining their strengths and weaknesses. Further, a broader perspective of the correct use and interpretation of the results obtained with these diagnostic tools is proposed to improve the containment strategy and identify the true impact of the pandemic. [ABSTRACT FROM AUTHOR]

A pneumonia outbreak with unknown etiology was reported in Wuhan, Hubei province, China, in December 2019, associated with the Huanan Seafood Wholesale Market. The causative agent of the outbreak was identified by the WHO as the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), producing the disease named coronavirus disease-2019 (COVID-19). The virus is closely related (96.3%) to bat coronavirus RaTG13, based on phylogenetic analysis. Human-to-human transmission has been confirmed even from asymptomatic carriers. The virus has spread to at least 200 countries, and more than 1,700,000 confirmed cases and 111,600 deaths have been recorded, with massive global increases in the number of cases daily. Therefore, the WHO has declared COVID-19 a pandemic. The disease is characterized by fever, dry cough, and chest pain with pneumonia in severe cases. In the beginning, the world public health authorities tried to eradicate the disease in China through quarantine but are now transitioning to prevention strategies worldwide to delay its spread. To date, there are no available vaccines or specific therapeutic drugs to treat the virus. There are many knowledge gaps about the newly emerged SARS-CoV-2, leading to misinformation. Therefore, in this review, we provide recent information about the COVID-19 pandemic. This review also provides insights for the control of pathogenic infections in humans such as SARS-CoV-2 infection and future spillovers. [ABSTRACT FROM AUTHOR]