CXray-EffDet: Chest Disease Detection and Classification from X-ray Images Using the EfficientDet Model.

The competence of machine learning approaches to carry out clinical expertise tasks has recently gained a lot of attention, particularly in the field of medical-imaging examination. Among the most frequently used clinical-imaging modalities in the healthcare profession is chest radiography, which calls for prompt reporting of the existence of potential anomalies and illness diagnostics in images. Automated frameworks for the recognition of chest abnormalities employing X-rays are being introduced in health departments. However, the reliable detection and classification of particular illnesses in chest X-ray samples is still a complicated issue because of the complex structure of radiographs, e.g., the large exposure dynamic range. Moreover, the incidence of various image artifacts and extensive inter- and intra-category resemblances further increases the difficulty of chest disease recognition procedures. The aim of this study was to resolve these existing problems. We propose a deep learning (DL) approach to the detection of chest abnormalities with the X-ray modality using the EfficientDet (CXray-EffDet) model. More clearly, we employed the EfficientNet-B0-based EfficientDet-D0 model to compute a reliable set of sample features and accomplish the detection and classification task by categorizing eight categories of chest abnormalities using X-ray images. The effective feature computation power of the CXray-EffDet model enhances the power of chest abnormality recognition due to its high recall rate, and it presents a lightweight and computationally robust approach. A large test of the model employing a standard database from the National Institutes of Health (NIH) was conducted to demonstrate the chest disease localization and categorization performance of the CXray-EffDet model. We attained an AUC score of 0.9080, along with an IOU of 0.834, which clearly determines the competency of the introduced model.

COVID-19 classification using chest X-ray images based on fusion-assisted deep Bayesian optimization and Grad-CAM visualization.

The COVID-19 virus's rapid global spread has caused millions of illnesses and deaths. As a result, it has disastrous consequences for people's lives, public health, and the global economy. Clinical studies have revealed a link between the severity of COVID-19 cases and the amount of virus present in infected people's lungs. Imaging techniques such as computed tomography (CT) and chest x-rays can detect COVID-19 (CXR). Manual inspection of these images is a difficult process, so computerized techniques are widely used. Deep convolutional neural networks (DCNNs) are a type of machine learning that is frequently used in computer vision applications, particularly in medical imaging, to detect and classify infected regions. These techniques can assist medical personnel in the detection of patients with COVID-19. In this article, a Bayesian optimized DCNN and explainable AI-based framework is proposed for the classification of COVID-19 from the chest X-ray images. The proposed method starts with a multi-filter contrast enhancement technique that increases the visibility of the infected part. Two pre-trained deep models, namely, EfficientNet-B0 and MobileNet-V2, are fine-tuned according to the target classes and then trained by employing Bayesian optimization (BO). Through BO, hyperparameters have been selected instead of static initialization. Features are extracted from the trained model and fused using a slicing-based serial fusion approach. The fused features are classified using machine learning classifiers for the final classification. Moreover, visualization is performed using a Grad-CAM that highlights the infected part in the image. Three publically available COVID-19 datasets are used for the experimental process to obtain improved accuracies of 98.8, 97.9, and 99.4%, respectively.

COVID-19 Classification from Chest X-Ray Images: A Framework of Deep Explainable Artificial Intelligence.

COVID-19 detection and classification using chest X-ray images is a current hot research topic based on the important application known as medical image analysis. To halt the spread of COVID-19, it is critical to identify the infection as soon as possible. Due to time constraints and the expertise of radiologists, manually diagnosing this infection from chest X-ray images is a difficult and time-consuming process. Artificial intelligence techniques have had a significant impact on medical image analysis and have also introduced several techniques for COVID-19 diagnosis. Deep learning and explainable AI have shown significant popularity among AL techniques for COVID-19 detection and classification. In this work, we propose a deep learning and explainable AI technique for the diagnosis and classification of COVID-19 using chest X-ray images. Initially, a hybrid contrast enhancement technique is proposed and applied to the original images that are later utilized for the training of two modified deep learning models. The deep transfer learning concept is selected for the training of pretrained modified models that are later employed for feature extraction. Features of both deep models are fused using improved canonical correlation analysis that is further optimized using a hybrid algorithm named Whale-Elephant Herding. Through this algorithm, the best features are selected and classified using an extreme learning machine (ELM). Moreover, the modified deep models are utilized for Grad-CAM visualization. The experimental process was conducted on three publicly available datasets and achieved accuracies of 99.1, 98.2, and 96.7%, respectively. Moreover, the ablation study was performed and showed that the proposed accuracy is better than the other methods.

Amelioration of SARS-CoV-2 infection by ANO6 phospholipid scramblase inhibition.

As an enveloped virus, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) delivers its viral genome into host cells via fusion of the viral and cell membranes. Here, we show that ANO6/TMEM16F-mediated cell surface exposure of phosphatidylserine is critical for SARS-CoV-2 entry and that ANO6-selective inhibitors are effective against SARS-CoV-2 infections. Application of the SARS-CoV-2 Spike pseudotyped virus (SARS2-PsV) evokes a cytosolic Ca2+ elevation and ANO6-dependent phosphatidylserine externalization in ACE2/TMPRSS2-positive mammalian cells. A high-throughput screening of drug-like chemical libraries identifies three different structural classes of chemicals showing ANO6 inhibitory effects. Among them, A6-001 displays the highest potency and ANO6 selectivity and it inhibits the single-round infection of SARS2-PsV in ACE2/TMPRSS2-positive HEK 293T cells. More importantly, A6-001 strongly inhibits authentic SARS-CoV-2-induced phosphatidylserine scrambling and SARS-CoV-2 viral replications in Vero, Calu-3, and primarily cultured human nasal epithelial cells. These results provide mechanistic insights into the viral entry process and offer a potential target for pharmacological intervention to protect against coronavirus disease 2019 (COVID-19).

TMED3 Complex Mediates ER Stress-Associated Secretion of CFTR, Pendrin, and SARS-CoV-2 Spike.

Under ER stress conditions, the ER form of transmembrane proteins can reach the plasma membrane via a Golgi-independent unconventional protein secretion (UPS) pathway. However, the targeting mechanisms of membrane proteins for UPS are unknown. Here, this study reports that TMED proteins play a critical role in the ER stress-associated UPS of transmembrane proteins. The gene silencing results reveal that TMED2, TMED3, TMED9 and TMED10 are involved in the UPS of transmembrane proteins, such as CFTR, pendrin and SARS-CoV-2 Spike. Subsequent mechanistic analyses indicate that TMED3 recognizes the ER core-glycosylated protein cargos and that the heteromeric TMED2/3/9/10 complex mediates their UPS. Co-expression of all four TMEDs improves, while each single expression reduces, the UPS and ion transport function of trafficking-deficient ΔF508-CFTR and p.H723R-pendrin, which cause cystic fibrosis and Pendred syndrome, respectively. In contrast, TMED2/3/9/10 silencing reduces SARS-CoV-2 viral release. These results provide evidence for a common role of TMED3 and related TMEDs in the ER stress-associated, Golgi-independent secretion of transmembrane proteins.

South Korean validation of the COVID-related-PTSD scale in a non-clinical sample exposed to the COVID-19 pandemic.

The threat of COVID-19 outbreak in South Korea and around the globe challenged not only physical health but also mental health, increasing the chances of disorders such as posttraumatic stress disorder (PTSD). Such pandemic situation can be referred to a traumatic event for citizens. The present study aims to examine the psychometric properties of the PTSD Checklist (PCL-5), which is named the K-COVID-related-PTSD. The scale measures PTSD symptomology in the context of the COVID-19 pandemic in South Korea. A total of 1434 South Korean citizens were included in this study. The data were statistically analyzed using SPSS 21.0 and Mplus 8.0. The results of confirmatory factor analysis demonstrated a superior fit for the seven-factor hybrid model (x2 = 1425.445 (df = 149), CFI = 0.950, TLI = 0.937, SRMR = 0.033, RMSEA = 0.077) consisting of re-experiencing, negative affect, anxious arousal, dysphoric arousal, avoidance, anhedonia, and externalizing behaviors. Furthermore, the K-COVID-related-PTSD showed a satisfactory level of internal consistency (α = 0.793 to α = 0.939) with good convergent and discriminant validity. Finally, concurrent validity was confirmed by the significant correlations with all the negative mental health outcomes, such as PTSD symptoms, somatization, depression, anxiety, anger, negative affect, job burnout, and suicidal ideation. Overall, the current results demonstrate the K-COVID-related-PTSD is a valid scale and therefore has important implications for future pandemic-related studies.

Rapid identification of a human antibody with high prophylactic and therapeutic efficacy in three animal models of SARS-CoV-2 infection.

Effective therapies are urgently needed for the SARS-CoV-2/COVID-19 pandemic. We identified panels of fully human monoclonal antibodies (mAbs) from large phage-displayed Fab, scFv, and VH libraries by panning against the receptor binding domain (RBD) of the SARS-CoV-2 spike (S) glycoprotein. A high-affinity Fab was selected from one of the libraries and converted to a full-size antibody, IgG1 ab1, which competed with human ACE2 for binding to RBD. It potently neutralized replication-competent SARS-CoV-2 but not SARS-CoV, as measured by two different tissue culture assays, as well as a replication-competent mouse ACE2-adapted SARS-CoV-2 in BALB/c mice and native virus in hACE2-expressing transgenic mice showing activity at the lowest tested dose of 2 mg/kg. IgG1 ab1 also exhibited high prophylactic and therapeutic efficacy in a hamster model of SARS-CoV-2 infection. The mechanism of neutralization is by competition with ACE2 but could involve antibody-dependent cellular cytotoxicity (ADCC) as IgG1 ab1 had ADCC activity in vitro. The ab1 sequence has a relatively low number of somatic mutations, indicating that ab1-like antibodies could be quickly elicited during natural SARS-CoV-2 infection or by RBD-based vaccines. IgG1 ab1 did not aggregate, did not exhibit other developability liabilities, and did not bind to any of the 5,300 human membrane-associated proteins tested. These results suggest that IgG1 ab1 has potential for therapy and prophylaxis of SARS-CoV-2 infections. The rapid identification (within 6 d of availability of antigen for panning) of potent mAbs shows the value of large antibody libraries for response to public health threats from emerging microbes.