Detection Of Coronavirus Disease 2019 Research Articles

Nanotechnology as a Shield against COVID-19: Current Advancement and Limitations.

The coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a global health problem that the WHO declared a pandemic. COVID-19 has resulted in a worldwide lockdown and threatened to topple the global economy. The mortality of COVID-19 is comparatively low compared with previous SARS outbreaks, but the rate of spread of the disease and its morbidity is alarming. This virus can be transmitted human-to-human through droplets and close contact, and people of all ages are susceptible to this virus. With the advancements in nanotechnology, their remarkable properties, including their ability to amplify signal, can be used for the development of nanobiosensors and nanoimaging techniques that can be used for early-stage detection along with other diagnostic tools. Nano-based protection equipment and disinfecting agents can provide much-needed protection against SARS-CoV-2. Moreover, nanoparticles can serve as a carrier for antigens or as an adjuvant, thereby making way for the development of a new generation of vaccines. The present review elaborates the role of nanotechnology-based tactics used for the detection, diagnosis, protection, and treatment of COVID-19 caused by the SARS-CoV-2 virus.

COVID-19 deep classification network based on convolution and deconvolution local enhancement

Computer Tomography (CT) detection can effectively overcome the problems of traditional detection of Corona Virus Disease 2019 (COVID-19), such as lagging detection results and wrong diagnosis results, which lead to the increase of disease infection rate and prevalence rate. The novel coronavirus pneumonia is a significant difference between the positive and negative patients with asymptomatic infections. To effectively improve the accuracy of doctors' manual judgment of positive and negative COVID-19, this paper proposes a deep classification network model of the novel coronavirus pneumonia based on convolution and deconvolution local enhancement. Through convolution and deconvolution operation, the contrast between the local lesion region and the abdominal cavity of COVID-19 is enhanced. Besides, the middle-level features that can effectively distinguish the image types are obtained. By transforming the novel coronavirus detection problem into the region of interest (ROI) feature classification problem, it can effectively determine whether the feature vector in each feature channel contains the image features of COVID-19. This paper uses an open-source COVID-CT dataset provided by Petuum researchers from the University of California, San Diego, which is collected from 143 novel coronavirus pneumonia patients and the corresponding features are preserved. The complete dataset (including original image and enhanced image) contains 1460 images. Among them, 1022 (70%) and 438 (30%) are used to train and test the performance of the proposed model, respectively. The proposed model verifies the classification precision in different convolution layers and learning rates. Besides, it is compared with most state-of-the-art models. It is found that the proposed algorithm has good classification performance. The corresponding sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and precision are 0.98, 0.96, 0.98, and 0.97, respectively.

The Practicality of Deep Learning Algorithms in COVID-19 Detection: Application to Chest X-ray Images

Since January 2020, the outbreak of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has affected the whole world, producing a respiratory disease that can become severe and even cause death in certain groups of people. The main method for diagnosing coronavirus disease 2019 (COVID-19) is performing viral tests. However, the kits for carrying out these tests are scarce in certain regions of the world. Lung conditions as perceived in computed tomography and radiography images exhibit a high correlation with the presence of COVID-19 infections. This work attempted to assess the feasibility of using convolutional neural networks for the analysis of pulmonary radiography images to distinguish COVID-19 infections from non-infected cases and other types of viral or bacterial pulmonary conditions. The results obtained indicate that these networks can successfully distinguish the pulmonary radiographies of COVID-19-infected patients from radiographies that exhibit other or no pathology, with a sensitivity of 100% and specificity of 97.6%. This could help future efforts to automate the process of identifying lung radiography images of suspicious cases, thereby supporting medical personnel when many patients need to be rapidly checked. The automated analysis of pulmonary radiography is not intended to be a substitute for formal viral tests or formal diagnosis by a properly trained physician but rather to assist with identification when the need arises.

Population surveillance approach to detect and respond to new clusters of COVID-19.

To maintain control of the coronavirus disease 2019 (COVID-19) epidemic as lockdowns are lifted, it will be crucial to enhance alternative public health measures. For surveillance, it will be necessary to detect a high proportion of any new cases quickly so that they can be isolated, and people who have been exposed to them traced and quarantined. Here we introduce a mathematical approach that can be used to determine how many samples need to be collected per unit area and unit time to detect new clusters of COVID-19 cases at a stage early enough to control an outbreak. We present a sample size determination method that uses a relative weighted approach. Given the contribution of COVID-19 test results from sub-populations to detect the disease at a threshold prevalence level to control the outbreak to 1) determine if the expected number of weekly samples provided from current healthcare-based surveillance for respiratory virus infections may provide a sample size that is already adequate to detect new clusters of COVID-19 and, if not, 2) to determine how many additional weekly samples were needed from volunteer sampling. In a demonstration of our method at the weekly and Canadian provincial and territorial (P/T) levels, we found that only the more populous P/T have sufficient testing numbers from healthcare visits for respiratory illness to detect COVID-19 at our target prevalence level-assumed to be high enough to identify and control new clusters. Furthermore, detection of COVID-19 is most efficient (fewer samples required) when surveillance focuses on healthcare symptomatic testing demand. In the volunteer populations: the higher the contact rates; the higher the expected prevalence level; and the fewer the samples were needed to detect COVID-19 at a predetermined threshold level. This study introduces a targeted surveillance strategy, combining both passive and active surveillance samples, to determine how many samples to collect per unit area and unit time to detect new clusters of COVID-19 cases. The goal of this strategy is to allow for early enough detection to control an outbreak.

Automatic detection of COVID-19 from chest CT scan and chest X-Rays images using deep learning, transfer learning and stacking.

One of the promising methods for early detection of Coronavirus Disease 2019 (COVID-19) among symptomatic patients is to analyze chest Computed Tomography (CT) scans or chest x-rays images of individuals using Deep Learning (DL) techniques. This paper proposes a novel stacked ensemble to detect COVID-19 either from chest CT scans or chest x-ray images of an individual. The proposed model is a stacked ensemble of heterogenous pre-trained computer vision models. Four pre-trained DL models were considered: Visual Geometry Group (VGG 19), Residual Network (ResNet 101), Densely Connected Convolutional Networks (DenseNet 169) and Wide Residual Network (WideResNet 50 2). From each pre-trained model, the potential candidates for base classifiers were obtained by varying the number of additional fully-connected layers. After an exhaustive search, three best-performing diverse models were selected to design a weighted average-based heterogeneous stacked ensemble. Five different chest CT scans and chest x-ray images were used to train and evaluate the proposed model. The performance of the proposed model was compared with two other ensemble models, baseline pre-trained computer vision models and existing models for COVID-19 detection. The proposed model achieved uniformly good performance on five different datasets, consisting of chest CT scans and chest x-rays images. In relevance to COVID-19, as the recall is more important than precision, the trade-offs between recall and precision at different thresholds were explored. Recommended threshold values which yielded a high recall and accuracy were obtained for each dataset.

The intersection of genetics and COVID-19 in 2021: preview of the 2021 Rodney Howell Symposium

The intersection of genetics and COVID-19 in 2021: preview of the 2021 Rodney Howell Symposium

Universal SARS-CoV-2 polymerase chain reaction screening and assisted reproductive technology in a coronavirus disease 2019 pandemic epicenter: screening and cycle outcomes from a New York City fertility center

ObjectiveTo evaluate the prevalence of coronavirus disease 2019 (COVID-19) and efficacy of a universal screening program in patients undergoing controlled ovarian stimulation (COS).DesignSingle-center retrospective cohort study.SettingAcademic fertility center in an epicenter of the COVID-19 pandemic.Patient(s)All patients undergoing COS from June 17, 2019, to February 28, 2021.Intervention(s)Universal COVID-19 screening starting June 17, 2020, with SARS-CoV-2 polymerase chain reaction testing within 5 days of oocyte retrieval, patient-reported symptom screening, and temperature monitoring.Main Outcomes Measure(s)The primary outcome was the number of positive COVID-19 cases in patients undergoing COS cycles. The secondary outcomes were cycle outcomes compared with before COVID-19 COS cycles, adverse outcomes in COVID-canceled cycles, and center-specific COVID-19 detection rates compared with New York City cases.Result(s)From June 17, 2020, to February 28, 2021, 1,696 COS cycles were initiated with only seven positive COVID-19 cases for an overall positivity rate of 0.4%. When compared with before COVID cycles from June 17, 2019, to February 28, 2020, the volume of COS cycles were higher, while the overall cycle cancelation rate was lower during COVID-19. Cycle outcomes including oocyte yield and blast utilization rates were unchanged from pre-COVID cycles. Cases of COVID-19, while very low, occurred more frequently during surges in New York City rates.Conclusion(s)Assisted reproductive technology can be performed during the COVID-19 pandemic utilizing frequent universal screening and safe practices with low SARS-CoV-2 positivity, low cycle cancelation rates, and positive patient outcomes.

COVID-19 classification of X-ray images using deep neural networks.

ObjectivesIn the midst of the coronavirus disease 2019 (COVID-19) outbreak, chest X-ray (CXR) imaging is playing an important role in diagnosis and monitoring of patients with COVID-19. We propose a deep learning model for detection of COVID-19 from CXRs, as well as a tool for retrieving similar patients according to the model’s results on their CXRs. For training and evaluating our model, we collected CXRs from inpatients hospitalized in four different hospitals.MethodsIn this retrospective study, 1384 frontal CXRs, of COVID-19 confirmed patients imaged between March and August 2020, and 1024 matching CXRs of non-COVID patients imaged before the pandemic, were collected and used to build a deep learning classifier for detecting patients positive for COVID-19. The classifier consists of an ensemble of pre-trained deep neural networks (DNNS), specifically, ReNet34, ReNet50¸ ReNet152, and vgg16, and is enhanced by data augmentation and lung segmentation. We further implemented a nearest-neighbors algorithm that uses DNN-based image embeddings to retrieve the images most similar to a given image.ResultsOur model achieved accuracy of 90.3%, (95% CI: 86.3–93.7%) specificity of 90% (95% CI: 84.3–94%), and sensitivity of 90.5% (95% CI: 85–94%) on a test dataset comprising 15% (350/2326) of the original images. The AUC of the ROC curve is 0.96 (95% CI: 0.93–0.97).ConclusionWe provide deep learning models, trained and evaluated on CXRs that can assist medical efforts and reduce medical staff workload in handling COVID-19.Key Points• A machine learning model was able to detect chest X-ray (CXR) images of patients tested positive for COVID-19 with accuracy and detection rate above 90%.• A tool was created for finding existing CXR images with imaging characteristics most similar to a given CXR, according to the model’s image embeddings.Supplementary InformationThe online version contains supplementary material available at 10.1007/s00330-021-08050-1.

Artificial Intelligence–Based COVID-19 Detection Using Cough Records

In 2019, with the emergence of coronavirus disease 2019 (COVID-19) and its spread all over the world, many people were directly affected by the pandemic. As its spread increases, it is difficult to diagnose who is actually infected. In addition to continuing vaccination studies, some technological solutions are being used to try to control the virus. One of these technological solutions is presented in this study. The disease is detected using cough data through artificial intelligence (AI). To do this, an open source data set was used from the opensigma.mit.edu website. More than 20,000 cough records representing age, gender, geographic location, and COVID-19 status are available from this site. The Al model trained on cough detection achieved 79% COVID-19 accuracy with an F1 of 80%. With the designed Al based mobile application, COVID-19 can be detected and monitored.

Is saliva a reliable biofluid for the detection of COVID-19?

This review aimed to assess the current evidence on the diagnostic potential of saliva regarding the detection of coronavirus disease 2019 (COVID-19). The literature published until May 24, 2020 was searched in the Web of Science, PubMed and Google Scholar databases with the keywords "COVID-19", "SARS-CoV-2", "2019-nCoV", "oral fluid", "saliva", and "diagnosis", individually and in combination, and 11 studies that explored the efficacy of saliva in the diagnosis of COVID-19 in different patient groups were found. Together, these studies suggest that saliva is a safe and reliable tool for the diagnosis of COVID-19. Further, saliva offers enhanced safety as well as logistical and economic benefits as compared to the current methods used to diagnose COVID-19. However, there is still limited evidence in the literature to make a definitive, clinically appropriate decision. The ideal specimen for the detection of acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is still an issue under investigation. Thus, new studies with large sample sets for the validation of easy, safe and reliable methods applicable for large-scale testing are immediately required.

Rapid single-molecule detection of COVID-19 and MERS antigens via nanobody-functionalized organic electrochemical transistors.

The coronavirus disease 2019 (COVID-19) pandemic has highlighted the need for rapid and sensitive protein detection and quantification in simple and robust formats for widespread point-of-care applications. Here, we report on nanobody-functionalized organic electrochemical transistors with a modular architecture for the rapid quantification of single-molecule-to-nanomolar levels of specific antigens in complex bodily fluids. The sensors combine a solution-processable conjugated polymer in the transistor channel and high-density and orientation-controlled bioconjugation of nanobody-SpyCatcher fusion proteins on disposable gate electrodes. The devices provide results after 10 min of exposure to 5 μl of unprocessed samples, maintain high specificity and single-molecule sensitivity in human saliva and serum, and can be reprogrammed to detect any protein antigen if a corresponding specific nanobody is available. We used the sensors to detect green fluorescent protein, and severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and Middle East respiratory syndrome coronavirus (MERS-CoV) spike proteins, and for the COVID-19 screening of unprocessed clinical nasopharyngeal swab and saliva samples with a wide range of viral loads.

Emerging point-of-care biosensors for rapid diagnosis of COVID-19: current progress, challenges, and future prospects.

Coronavirus disease 2019 (COVID-19) pandemic is currently a serious global health threat. While conventional laboratory tests such as quantitative real-time polymerase chain reaction (qPCR), serology tests, and chest computerized tomography (CT) scan allow diagnosis of COVID-19, these tests are time-consuming and laborious, and are limited in resource-limited settings or developing countries. Point-of-care (POC) biosensors such as chip-based and paper-based biosensors are typically rapid, portable, cost-effective, and user-friendly, which can be used for COVID-19 in remote settings. The escalating demand for rapid diagnosis of COVID-19 presents a strong need for a timely and comprehensive review on the POC biosensors for COVID-19 that meet ASSURED criteria: Affordable, Sensitive, Specific, User-friendly, Rapid and Robust, Equipment-free, and Deliverable to end users. In the present review, we discuss the importance of rapid and early diagnosis of COVID-19 and pathogenesis of COVID-19 along with the key diagnostic biomarkers. We critically review the most recent advances in POC biosensors which show great promise for the detection of COVID-19 based on three main categories: chip-based biosensors, paper-based biosensors, and other biosensors. We subsequently discuss the key benefits of these biosensors and their use for the detection of antigen, antibody, and viral nucleic acids. The commercial POC biosensors for COVID-19 are critically compared. Finally, we discuss the key challenges and future perspectives of developing emerging POC biosensors for COVID-19. This review would be very useful for guiding strategies for developing and commercializing rapid POC tests to manage the spread of infections.Graphical abstract

Transfer Learning to Detect COVID-19 Automatically from X-Ray Images Using Convolutional Neural Networks.

The novel coronavirus disease 2019 (COVID-19) is a contagious disease that has caused thousands of deaths and infected millions worldwide. Thus, various technologies that allow for the fast detection of COVID-19 infections with high accuracy can offer healthcare professionals much-needed help. This study is aimed at evaluating the effectiveness of the state-of-the-art pretrained Convolutional Neural Networks (CNNs) on the automatic diagnosis of COVID-19 from chest X-rays (CXRs). The dataset used in the experiments consists of 1200 CXR images from individuals with COVID-19, 1345 CXR images from individuals with viral pneumonia, and 1341 CXR images from healthy individuals. In this paper, the effectiveness of artificial intelligence (AI) in the rapid and precise identification of COVID-19 from CXR images has been explored based on different pretrained deep learning algorithms and fine-tuned to maximise detection accuracy to identify the best algorithms. The results showed that deep learning with X-ray imaging is useful in collecting critical biological markers associated with COVID-19 infections. VGG16 and MobileNet obtained the highest accuracy of 98.28%. However, VGG16 outperformed all other models in COVID-19 detection with an accuracy, F1 score, precision, specificity, and sensitivity of 98.72%, 97.59%, 96.43%, 98.70%, and 98.78%, respectively. The outstanding performance of these pretrained models can significantly improve the speed and accuracy of COVID-19 diagnosis. However, a larger dataset of COVID-19 X-ray images is required for a more accurate and reliable identification of COVID-19 infections when using deep transfer learning. This would be extremely beneficial in this pandemic when the disease burden and the need for preventive measures are in conflict with the currently available resources.

Detection of COVID-19 in X-ray images by classification of bag of visual words using neural networks

Coronavirus disease 2019 (COVID-19) was classified as a pandemic by the World Health Organization in March 2020. Given that this novel virus most notably affects the human respiratory system, early detection may help prevent severe lung damage, save lives, and help prevent further disease spread. Given the constraints on the healthcare facilities and staff, the role of artificial intelligence for automatic diagnosis is critical. The automatic diagnosis of COVID-19 based on medical images is, however, not straightforward. Due to the novelty of the disease, available X-ray datasets are very limited. Furthermore, there is a significant similarity between COVID-19 X-rays and other lung infections. In this paper, these challenges are addressed by proposing an approach consisting of a bag of visual words and a neural network classifier. The proposed method can classify X-ray chest images into non-COVID-19 and COVID-19 with high performance. Three public datasets are used to evaluate the proposed approach. Our best accuracy on the first, second, and third datasets is 96.1, 99.84, and 98 percent. Since detection of COVID-19 is important, sensitivity is used as a criterion. The proposed method’s best sensitivities are 90.32, 99.65, and 91 percent on these datasets, respectively. The experimental results show that extracting features with the bag of visual words results in better classification accuracy than the state-of-the-art techniques.

A systematic review of the case findings, testing and management of COVID-19

Background: Mass testing and adequate management are essential to terminate the spread of coronavirus disease 2019 (COVID-19). This testing is due to the possibility of unidentified cases, especially ones without COVID-19 related symptoms. This review aimed to examine the outcome of the existing studies on the ways of identifying COVID-19 cases, and determine the populations at risk, symptom and diagnostic test management of COVID-19. Methods: The articles reviewed were scientific publications on the PubMed, Science Direct, ProQuest, and Scopus databases. The keywords used to obtain the data were COVID-19, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and case detection, case management or diagnostic test. We applied the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Population, Intervention, Control and Outcomes (PICO) approaches. Results: A total of 21 articles from 13 countries met the inclusion criteria and were further analyzed qualitatively. However, 62% of the articles used a rapid antibody test for screening rather than a rapid antigen test. According to the rapid antigen test, 51.3% were positive, with men aged above 50 years recording the highest number of cases. Furthermore, 57.1% of patients were symptomatic, while diagnostic tests' sensitivity and specificity increased to 100% in 14 days after the onset. Conclusion s: Real-time polymerase chain reaction (RT-PCR) is recommended by the World Health Organization for detection of COVID-19. Suppose it is unavailable, the rapid antigen test is used as an alternative rather than the rapid antibody test. Diagnosis is expected to be confirmed using the PCR and serological assay to achieve an early diagnosis of COVID-19, according to disease progression, gradual rapid tests can be used, such as rapid antigen in an earlier week and antibody tests confirmed by RT-PCR and serological assay in the second week of COVID-19.

Detection of SARS-CoV-2 infection by RT-PCR test: factors influencing interpretation of results.

In this current pandemic of coronavirus disease 2019 (COVID-19), prompt interventions in terms of early detection and clinical management along with isolation of positive cases is of utmost importance. This helps to limit not only the spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infections but also the morbidity and mortality associated with it. Different strategies for screening of COVID-19 in containment zones and non-containment areas include testing of symptomatic patients and their contacts in fever clinics, hospital-based testing, testing on demand and population-based screening. The choice of tests like reverse-transcription polymerase chain reaction (RT-PCR), rapid antigen testing (RAT) or antibody test depends upon these strategies and also the turnaround time. Currently, RT-PCR is considered the gold standard for COVID-19 detection. This commentary provides the insights and experiences on COVID-19 diagnosis by RT-PCR. The utility of this test is limited by several false positive, false negative and inconclusive results at early stages of infection, scarcity of reagents and lack of well-equipped labs including trained staff. Moreover, appropriate sample collection and transport, standard laboratory protocols, stringent quality control norms, good quality RNA extraction kits, PCR kits with suitable primers can help in improving accuracy of the test results. A careful assessment of clinical, radiological and molecular findings is required for identifying potential cases of COVID-19.

Chest CT versus RT-PCR for the detection of COVID-19: systematic review and meta-analysis of comparative studies.

ObjectivesTo compare the performance of chest computed tomography (CT) scan versus reverse transcription polymerase chain reaction (RT-PCR) as the reference standard in the initial diagnostic assessment of coronavirus disease 2019 (COVID-19) patients.DesignA systematic review and meta-analysis were performed as per the Preferred Reporting Items for Systematic Reviews and Meta-analyses guidelines. A search of electronic information was conducted using the following databases: MEDLINE, EMBASE, EMCARE, CINAHL and the Cochrane Central Register of Controlled Trials.SettingStudies that compared the diagnostic performance within the same patient cohort of chest CT scan versus RT-PCR in COVID-19 suspected patients.ParticipantsThirteen non-randomised studies enrolling 4092 patients were identified.Main outcome measuresSensitivity, specificity and accuracy were primary outcome measures. Secondary outcomes included other test performance characteristics and discrepant findings between both investigations.ResultsChest CT had a median sensitivity, specificity and accuracy of 0.91 (range 0.82–0.98), 0.775 (0.25–1.00) and 0.87 (0.68–0.99), respectively, with RT-PCR as the reference. Importantly, early small, China-based studies tended to favour chest CT versus later larger, non-China studies.ConclusionsA relatively high false positive rate can be expected with chest CT. It is possible it may still be useful to provide circumstantial evidence, however, in some patients with a suspicious clinical presentation of COVID-19 and negative initial Severe Acute Respiratory Syndrome Coronavirus 2 RT-PCR tests, but more evidence is required in this context. In acute cardiorespiratory presentations, negative CT scan and RT-PCR tests is likely to be reassuring.

Deep Learning-Based COVID-19 Detection Using CT and X-Ray Images: Current Analytics and Comparisons.

Currently, the world faces a novel coronavirus disease 2019 (COVID-19) challenge and infected cases are increasing exponentially. COVID-19 is a disease that has been reported by the WHO in March 2020, caused by a virus called the SARS-CoV-2. As of 10 March 2021, more than 150 million people were infected and 3v million died. Researchers strive to find out about the virus and recommend effective actions. An unprecedented increase in pathogens is happening and a major attempt is being made to tackle the epidemic. This article presents deep learning-based COVID-19 detection using CT and X-ray images and data analytics on its spread worldwide. This article's research structure builds on a recent analysis of the COVID-19 data and prospective research to systematize current resources, help the researchers, practitioners by using in-depth learning methodologies to build solutions for the COVID-19 pandemic.

COVID-19 infection map generation and detection from chest X-ray images

Computer-aided diagnosis has become a necessity for accurate and immediate coronavirus disease 2019 (COVID-19) detection to aid treatment and prevent the spread of the virus. Numerous studies have proposed to use Deep Learning techniques for COVID-19 diagnosis. However, they have used very limited chest X-ray (CXR) image repositories for evaluation with a small number, a few hundreds, of COVID-19 samples. Moreover, these methods can neither localize nor grade the severity of COVID-19 infection. For this purpose, recent studies proposed to explore the activation maps of deep networks. However, they remain inaccurate for localizing the actual infestation making them unreliable for clinical use. This study proposes a novel method for the joint localization, severity grading, and detection of COVID-19 from CXR images by generating the so-called infection maps. To accomplish this, we have compiled the largest dataset with 119,316 CXR images including 2951 COVID-19 samples, where the annotation of the ground-truth segmentation masks is performed on CXRs by a novel collaborative human–machine approach. Furthermore, we publicly release the first CXR dataset with the ground-truth segmentation masks of the COVID-19 infected regions. A detailed set of experiments show that state-of-the-art segmentation networks can learn to localize COVID-19 infection with an F1-score of 83.20%, which is significantly superior to the activation maps created by the previous methods. Finally, the proposed approach achieved a COVID-19 detection performance with 94.96% sensitivity and 99.88% specificity.

Semi-supervised learning for an improved diagnosis of COVID-19 in CT images.

Coronavirus disease 2019 (COVID-19) has been spread out all over the world. Although a real-time reverse-transcription polymerase chain reaction (RT-PCR) test has been used as a primary diagnostic tool for COVID-19, the utility of CT based diagnostic tools have been suggested to improve the diagnostic accuracy and reliability. Herein we propose a semi-supervised deep neural network for an improved detection of COVID-19. The proposed method utilizes CT images in a supervised and unsupervised manner to improve the accuracy and robustness of COVID-19 diagnosis. Both labeled and unlabeled CT images are employed. Labeled CT images are used for supervised leaning. Unlabeled CT images are utilized for unsupervised learning in a way that the feature representations are invariant to perturbations in CT images. To systematically evaluate the proposed method, two COVID-19 CT datasets and three public CT datasets with no COVID-19 CT images are employed. In distinguishing COVID-19 from non-COVID-19 CT images, the proposed method achieves an overall accuracy of 99.83%, sensitivity of 0.9286, specificity of 0.9832, and positive predictive value (PPV) of 0.9192. The results are consistent between the COVID-19 challenge dataset and the public CT datasets. For discriminating between COVID-19 and common pneumonia CT images, the proposed method obtains 97.32% accuracy, 0.9971 sensitivity, 0.9598 specificity, and 0.9326 PPV. Moreover, the comparative experiments with respect to supervised learning and training strategies demonstrate that the proposed method is able to improve the diagnostic accuracy and robustness without exhaustive labeling. The proposed semi-supervised method, exploiting both supervised and unsupervised learning, facilitates an accurate and reliable diagnosis for COVID-19, leading to an improved patient care and management.