Hybrid quantum-classical convolutional neural network model for COVID-19 prediction using chest X-ray images

Prolonged SARS-CoV-2 shedding and mild course of COVID-19 in a patient after recent heart transplantation.

Is Africa prepared for tackling the COVID-19 (SARS-CoV-2) epidemic. Lessons from past outbreaks, ongoing pan-African public health efforts, and implications for the future

The coronavirus disease 2019 (COVID-19) led to a dramatic increase in the number of cases of patients with pneumonia worldwide. In this study, we aimed to develop an AI-assisted multistrategy image enhancement technique for chest X-ray (CXR) images to improve the accuracy of COVID-19 classification. Our new classification strategy consisted of 3 parts. First, the improved U-Net model with a variational encoder segmented the lung region in the CXR images processed by histogram equalization. Second, the residual net (ResNet) model with multidilated-rate convolution layers was used to suppress the bone signals in the 217 lung-only CXR images. A total of 80% of the available data were allocated for training and validation. The other 20% of the remaining data were used for testing. The enhanced CXR images containing only soft tissue information were obtained. Third, the neural network model with a residual cascade was used for the super-resolution reconstruction of low-resolution bone-suppressed CXR images. The training and testing data consisted of 1,200 and 100 CXR images, respectively. To evaluate the new strategy, improved visual geometry group (VGG)-16 and ResNet-18 models were used for the COVID-19 classification task of 2,767 CXR images. The accuracy of the multistrategy enhanced CXR images was verified through comparative experiments with various enhancement images. In terms of quantitative verification, 8-fold cross-validation was performed on the bone suppression model. In terms of evaluating the COVID-19 classification, the CXR images obtained by the improved method were used to train 2 classification models. Compared with other methods, the CXR images obtained based on the proposed model had better performance in the metrics of peak signal-to-noise ratio and root mean square error. The super-resolution CXR images of bone suppression obtained based on the neural network model were also anatomically close to the real CXR images. Compared with the initial CXR images, the classification accuracy rates of the internal and external testing data on the VGG-16 model increased by 5.09% and 12.81%, respectively, while the values increased by 3.51% and 18.20%, respectively, for the ResNet-18 model. The numerical results were better than those of the single-enhancement, double-enhancement, and no-enhancement CXR images. The multistrategy enhanced CXR images can help to classify COVID-19 more accurately than the other existing methods.

COVID-19 and Gastrointestinal Tract Symptoms: Recognition, Containment, and Learning From the Past

ABSTRACTIntroduction:With the current coronavirus disease 2019 (COVID-19) pandemic, concerns have been raised about the risk to children with inflammatory bowel diseases (IBD). We aimed to collate global experience and provide provisional guidance for managing paediatric IBD (PIBD) in the era of COVID-19.Methods:An electronic reporting system of children with IBD infected with SARS-CoV-2 has been circulated among 102 PIBD centres affiliated with the Porto and Interest-group of ESPGHAN. A survey has been completed by major PIBD centres in China and South-Korea to explore management during the pandemic. A third survey collected current practice of PIBD treatment. Finally, guidance points for practice have been formulated and voted upon by 37 PIBD authors and Porto group members.Results:Eight PIBD children had COVID-19 globally, all with mild infection without needing hospitalization despite treatment with immunomodulators and/or biologics. No cases have been reported in China and South Korea but biologic treatment has been delayed in 79 children, of whom 17 (22%) had exacerbation of their IBD. Among the Porto group members, face-to-face appointments were often replaced by remote consultations but almost all did not change current IBD treatment. Ten guidance points for clinicians caring for PIBD patients in epidemic areas have been endorsed with consensus rate of 92% to 100%.Conclusions:Preliminary data for PIBD patients during COVID-19 outbreak are reassuring. Standard IBD treatments including biologics should continue at present through the pandemic, especially in children who generally have more severe IBD course on one hand, and milder SARS-CoV-2 infection on the other.Supplemental digital content:An infographic accompanying this article can be found at.

Chest X-rays (CXR) images are a useful noninvasive diagnostic tool for assessing various lung diseases. In this paper, we propose transfer learning with a fine-tuning-based model to detect and classify COVID-19 and pneumonia using CXR images to assist the radiologist with diagnosis. One of the difficulties with the medical imaging classification is the limited number of available datasets, and hence training a deep Convolutional Neural Network (CNN) model for medical image classification on a small dataset is challenging. We address this issue by exploiting transfer learning via fine-tuning. In this paper, we use a pre-trained deep CNN model and then fine-tune the layers of the neural network to perform multi-class classification using CXR images. The model is trained to perform multi-class classification, such as two-class (COVID-19 vs normal), three-class (COVID-19 vs Bacterial Pneumonia vs normal), four-class (COVID-19 vs Bacterial Pneumonia vs lung opacity vs normal), and five-class (COVID-19 vs Bacterial Pneumonia vs Viral Pneumonia vs lung opacity vs normal) classification. The performance of the model is evaluated in terms of accuracy, precision, recall, and F1-score.

In December 2019, a novel coronavirus was identified in Wuhan City, Hubei Province, China and later the disease was named coronavirus disease 2019 (COVID-19). On March 11, 2020, the World Health Organization (WHO) officially announced that COVID-19 had reached global pandemic status. This article summarized the understanding of the etiology, pathogenesis, epidemiology, clinical characteristics, diagnosis, treatment, rehabilitation, and prevention and control measures of COVID-19 based on the available data and anti-epidemic experience in China.

PurposeThe coronavirus disease 2019 (COVID-19) pandemic has spread to all countries in the world, and different countries have been impacted differently. The study aims to understand what factors contribute to different COVID-19 impacts at the country level. MethodsMultivariate statistical analyses were used to evaluate COVID-19 deaths and cases relative to nine other demographic and socioeconomic factors in all countries and regions of the world using data as of August 1, 2020. The factors analyzed in the study include a country’s total COVID-19 deaths and cases per million population, per capita gross domestic product (GDP), population density, virus tests per million population, median age, government response stringency index, hospital beds availability per thousand population, extreme poverty rate, Bacille Calmette–Guérin (BCG) vaccination rate, and diphtheria–tetanus–pertussis (DTP3) immunization rate. ResultsThe study reveals that COVID-19 deaths per million population in a country most significantly correlates, inversely, with the country’s BCG vaccination rate (r = − 0.50, p = 5.3e-5), and also significantly correlates a country’s per capita GDP (r = 0.39, p = 7.4e-3) and median age (r = 0.30, p = 0.042), while COVID-19 cases per million population significantly correlate with per capita GDP and tests per thousand population. To control for possible confounding effects of age, the correlation was assessed in countries propensity score matched for age. The inverse correlation between BCG vaccination rates and COVID-19 case (r = − 0.30, p = 0.02) and death (r = − 0.42, p = 0.0007) remained significant among the top 61 countries with the highest median age.ConclusionThis study contributes to a growing body of evidence supporting the notion that BCG vaccination may be protective against COVID-19 mortality.Supplementary InformationThe online version contains supplementary material available at 10.1007/s15010-020-01566-6.

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

Reply

The COVID-19 diffused quickly throughout the world and converted as a pandemic. It has caused a destructive effect on both regular lives, common health and global business. It is crucial to identify positive patients as shortly as desirable to limit this epidemic’s further diffusion and to manage immediately affected cases. The demand for quick assistant distinguishing devices has developed. Recent findings achieved utilizing radiology imaging systems propose that such images include salient data about the COVID-19. The utilization of progressive artificial intelligence (AI) methods linked by radiological imaging can help the reliable diagnosis of COVID-19. As radiography images can recognize pneumonia infections, this research brings an accurate and automatic technique based on a deep residual network to analyze chest X-ray images to monitor COVID-19 and diagnose verified patients. The physician states that it is significantly challenging to separate COVID-19 from common viral and bacterial pneumonia, while COVID-19 is additionally a variety of viruses. The proposed network is expanded to perform detailed diagnostics for two multi-class classification (COVID-19, Normal, Viral Pneumonia) and (COVID-19, Normal, Viral Pneumonia, Bacterial Pneumonia) and binary classification. By comparing the proposed network with the popular methods on public databases, the results show that the proposed algorithm can provide an accuracy of 92.1% in classifying multi-classes of COVID-19, normal, viral pneumonia, and bacterial pneumonia cases. It can be applied to support radiologists in verifying their first viewpoint.

Dear Editor We read with great interest the letter of Chung HY et al1 in which they refer to our recent publication in the Annals of Neurology on “Serum Neurofilament Light Chain Levels in the Intensive Care Unit: Comparison between Severely Ill Patients with and without Coronavirus Disease 2019.”2 The authors compared plasma neurofilament light chain (pNfL) levels in patients with bacterial and coronavirus disease 2019 (COVID-19) pneumonia; pNfL levels in bacterial pneumonia 3 days after onset of sepsis were considerably higher than those in COVID-19 pneumonia at days 3 and 7. Chung and colleagues concluded that their results are corroborated by those of others3, 4 showing “low to intermediate NfL levels in COVID-19 patients as compared to other infectious diseases…” and that their “own data and current evidence do not indicate commonly occurring neuronal damage in COVID-19.” Noteworthy, the clinical severity of patients with COVID-19 pneumonia by Chung HY et al were lower with a mean Sequential Organ Failure Assessment (SOFA) score of 4, whereas in our cohort it was 7; 86% of the critically ill patients in our study were ventilated and 17% died (no data are provided about eg, ventilation, comorbidities, intensive care unit [ICU] admission, oxygenation indexes, and outcome in patients with COVID-19 in the cohort of Chung HY et al). In contrast to our cohort, which was analyzed after disease progression that led to an admission to the ICU (ie, representing a later stage of the disease), the patients presented by Chung HY et al were analyzed within the first few days after onset of pneumonia. In fact, the patients with COVID-19 described by us match better with the subgroup categorized as “severe” by Kanberg et al3 where the median pNfL level was 32.7 pg/ml, very similar to our finding of 36.1 pg/ml in serum (vs approximately 5–10 pg/ml in Fig 1C of Chung HY et al). We consider these levels not as “low to intermediate” as they are in the range of patients with bacterial pneumonia presented by Chung HY et al. Patients with sepsis-associated encephalopathy show radiological signs of brain damage and neuropsychological signs of brain dysfunction,4 pNfL levels were strongly increased compared to patients without brain dysfunction; further, they correlated with a poorer long-term neurofunctional outcome. Neuronal damage can be assumed as the cause for the elevation of serum neurofilament light chain (sNfL) observed by Chung et al in their cohort with bacterial pneumonia. Important in our view is the observation that neuronal damage occurs in the course of both COVID-19 and sepsis-associated encephalopathy (ie, also in absence of overt infection of the central nervous system).4, 5 We agree that neuronal damage is not specific for COVID-19, but seems likely a generic consequence in severe infectious disease of various etiologies. We agree as well that the role of renal dysfunction and other metabolic changes as factors modulating NfL levels during infectious diseases needs to be explored. The authors declared no conflict of interest.

Electrocardiographic features of patients with COVID-19: One year of unexpected manifestations

The newly discovered Coronavirus Disease 2019 (COVID-19) has been globally spreading and causing hundreds of thousands of deaths around the world as of its first emergence in late 2019. The rapid outbreak of this disease has overwhelmed health care infrastructures and arises the need to allocate medical equipment and resources more efficiently. The early diagnosis of this disease will lead to the rapid separation of COVID-19 and non-COVID cases, which will be helpful for health care authorities to optimize resource allocation plans and early prevention of the disease. In this regard, a growing number of studies are investigating the capability of deep learning for early diagnosis of COVID-19. Computed tomography (CT) scans have shown distinctive features and higher sensitivity compared to other diagnostic tests, in particular the current gold standard, i.e., the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. Current deep learning-based algorithms are mainly developed based on Convolutional Neural Networks (CNNs) to identify COVID-19 pneumonia cases. CNNs, however, require extensive data augmentation and large datasets to identify detailed spatial relations between image instances. Furthermore, existing algorithms utilizing CT scans, either extend slice-level predictions to patient-level ones using a simple thresholding mechanism or rely on a sophisticated infection segmentation to identify the disease. In this paper, we propose a two-stage fully automated CT-based framework for identification of COVID-19 positive cases referred to as the “COVID-FACT”. COVID-FACT utilizes Capsule Networks, as its main building blocks and is, therefore, capable of capturing spatial information. In particular, to make the proposed COVID-FACT independent from sophisticated segmentations of the area of infection, slices demonstrating infection are detected at the first stage and the second stage is responsible for classifying patients into COVID and non-COVID cases. COVID-FACT detects slices with infection, and identifies positive COVID-19 cases using an in-house CT scan dataset, containing COVID-19, community acquired pneumonia, and normal cases. Based on our experiments, COVID-FACT achieves an accuracy of , a sensitivity of , a specificity of , and an Area Under the Curve (AUC) of 0.98, while depending on far less supervision and annotation, in comparison to its counterparts.

Plasma exchange and COVID 19