Automated Covid-19 Disease Identification on Chest-Ct Images Using Cnn and Vgg16

The human respiratory system is most affected by COVID-19, a coronavirus illness that has been identified. Infectious disease COVID-19 was brought on by a virus that emerged in Wuhan, China, in December 2019. The key problem for healthcare professionals is early diagnosis. Medical organizations were confused in the early stages because there were no suitable medical tools or medications to detect COVID-19. Reverse Transcription Polymerase Chain Reaction, a novel diagnostic technique, was released. The COVID-19 virus congregates in the patient's nose or throat, thus swab samples from those areas are collected. There are various accuracy and testing time restrictions with this method. Medical professionals advise using a different method called CT (Computerized Tomography), which can rapidly identify the infected lung regions and detect COVID-19 at an earlier stage. With the help of chest CT images, computer scientists created a number of deep learning models to recognize the COVID-19 condition. In this paper, a model for automatic COVID-19 recognition on chest CT images is presented that is based on Convolutional Neural Networks (CNN) and VGG16. A public dataset of 14320 CT scans was used in the experiment, and the findings revealed classification accuracy for CNN and VGG16 of 96.34% and 96.99%, respectively.Copyright © 2022, Anka Publishers. All rights reserved.

The Role of Computed Tomography in the Management of Hospitalized Patients With COVID-19.

The emergence of SARS-CoV-2 at the end of 2019 sparked the beginning of the COVID-19 pandemic. Even though it was a novel virus, the workup of suspected COVID-19 included standard protocols used for the investigation of similar respiratory infections and pneumonia. One of the most important diagnostic tests in this regard is computed tomography (CT). CT scans have a high sensitivity in diagnosing COVID-19, and many of the characteristic imaging findings of COVID-19 are used in its diagnosis. The role of CT in COVID-19 management is expanding as more and more hospital practices adopt regular CT use in both the initial workup and continued care of COVID-19 patients. CT has helped hospitalists diagnose complications such as pulmonary embolism, subcutaneous emphysema, pneumomediastinum, pneumothoraces, and nosocomial pneumonia. Although mainly used as a diagnostic tool, the prognostic role of CT in COVID-19 patients is developing. In this review, we explore the role of CT in the management of hospitalized patients with COVID-19, specifically elucidating its use as a diagnostic and prognostic modality, as well as its ability to guide hospital decision-making regarding complex cases. We will highlight important time points when CT scans are used: the initial encounter, the time at admission, and during hospitalization.

Imaging of COVID-19 simulators

BackgroundCoronavirus (COVID-19) pneumonia emerged in Wuhan, China, in December 2019. It was highly contagious spreading all over the world, with a rapid increase in the number of deaths. The reported cases have reached more than 14 million with more than 600,000 deaths around the world. So, the pandemic of COVID-19 became a surpassing healthcare crisis with an intensive load on the healthcare resources.In this study, the aim was to differentiate COVID-19 pneumonia from its mimickers as atypical infection, interstitial lung diseases, and eosinophilic lung diseases based on CT, clinical, and laboratory findings.ResultsThis retrospective study included 260 patients, of which 220 were confirmed as COVID-19 positive by two repeated RT-PCR test and 40 were classified as non-COVID by two repeated negative RT-PCR test or identification of other pathogens, other relevant histories, or clinical findings.In this study, 158 patients were male (60.7 %) and 102 patients were female (39.3%). There was 60.9% of the COVID-19 group were male and 39.1% were female. Patients in the non-COVID group were significantly older (the mean age was 46.4) than those in the confirmed COVID-19 group (35.2y). In the COVID-19 group, there was exposure history to positive cases in 84.1% while positive exposure history was 20% in the non-COVID group.ConclusionThe spectrum of CT imaging findings in COVID-19 pneumonia is wide that could be contributed by many other diseases making the interpretation of chest CTs nowadays challenging to differentiate between different diseases having the same signs and act as deceiving simulators in the era of COVID-19.

Evaluation of low-dose CT protocol of novel coronavirus pneumonia based on infection prevention and control.

Objective: To explore a low dose CT scanning method on novel coronavirus (COVID-19) pneumonia based on infection prevention and control. Method(s): A total of 140 patients with confirmed novel coronavirus pneumonia in Xiehe hospital from January 20, 2020 to February 28, 2020 were undertaken CT scan and divided into low dose group and conventional dose group. The patients in low dose group(120 kV, 31 mAs) consisted of mild type(51), severe type(15) and critically ill type(4);and those in conventional dose group(120 kv, adaptive milliampere second) consisted of mild type(48), severe type(17) and critically ill type(5). The effective radiation dose, SNR and CNR of CT scan were compared between two groups. A senior and a middle radiologist made the image subjective quality scores, respectively. Result(s): The effective dose in low dose group was lower than that of conventional dose group(t=-48.343, P<0.05). There was no significant difference in SNR and CNR between two groups(P>0.05). For severe and critically ill patients, the score in low dose group was significantly lower than that in conventional dose group(t=-2.781, P<0.05). There was no significant difference in scores between two groups for mild patients(P>0.05). Conclusion(s): Low-dose CT scanning could meet the image quality needs for patients with COVID-19 and meanwhile significantly reduce the radiation dose.Copyright © 2020 by the Chinese Medical Association.

Biomarkers of COVID-19 and technologies to combat SARS-CoV-2.

Due to the unprecedented public health crisis caused by COVID-19, our first contribution to the newly launching journal, Advances in Biomarker Sciences and Technology, has abruptly diverted to focus on the current pandemic. As the number of new COVID-19 cases and deaths continue to rise steadily around the world, the common goal of healthcare providers, scientists, and government officials worldwide has been to identify the best way to detect the novel coronavirus, named SARS-CoV-2, and to treat the viral infection - COVID-19. Accurate detection, timely diagnosis, effective treatment, and future prevention are the vital keys to management of COVID-19, and can help curb the viral spread. Traditionally, biomarkers play a pivotal role in the early detection of disease etiology, diagnosis, treatment and prognosis. To assist myriad ongoing investigations and innovations, we developed this current article to overview known and emerging biomarkers for SARS-CoV-2 detection, COVID-19 diagnostics, treatment and prognosis, and ongoing work to identify and develop more biomarkers for new drugs and vaccines. Moreover, biomarkers of socio-psychological stress, the high-technology quest for new virtual drug screening, and digital applications are described.

Coronavirus Disease 2019 Causing Infection of Transplanted Lung Allograft: A Pitfall of Prolonged Shedding of Severe Acute Respiratory Syndrome Coronavirus-2 Pretransplant.

Coronavirus disease 2019 (COVID-19) pandemic has led to considerable morbidity and mortality across the world. Lung transplant is a viable option for a few with COVID-19-related lung disease. Whom and when to transplant has been the major question impacting the transplant community given the novelty of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). We describe a pitfall of presumed prolonged shedding of SARS-CoV-2 in a patient with COVID-19 associated acute respiratory distress syndrome leading to COVID-19 pneumonia after lung transplant. This raises concerns that replication-competent SARS-CoV-2 virus can persist for months post-infection and can lead to re-infection of grafts in the future.

High-Risk Pulmonary Embolism During Labor: JACC Patient Care Pathways.

While in labor, a 37-year-old woman developed acute dyspnea, hypoxemia, and tachycardia. Transthoracic echocardiography demonstrated severe right ventricular dilation and dysfunction, raising the suspicion of acute pulmonary embolism. The patient indeed had bilateral pulmonary embolism, necessitating percutaneous thrombectomy. Her course was complicated by another saddle pulmonary embolus, heparin-induced thrombocytopenia, and COVID-19 infection. This clinical case illustrates the importance of prompt diagnosis of acute pulmonary embolism in a peripartum female patient, the multidisciplinary approach of management, and how to approach clinical complications such as heparin-induced thrombocytopenia. Furthermore, long-term management in acute pulmonary embolism is presented.

An unusual site of a pericardial cyst in a child: A case report.

Pericardial cysts are rare congenital anomalies, often clinically silent and incidentally found on imaging. However, patients with pericardial cysts may present with chest pain, tachypnea, and, rarely, symptoms secondary to cardiac tamponade. Echocardiography (transthoracic or transesophageal) and chest computed tomography (CT) scan with contrast are diagnostic modalities of choice in patients with pericardial cysts. Conservative management is justified in asymptomatic patients, while a surgical approach is recommended in symptomatic patients. Here, we describe the case of a 12-year-old boy who underwent imaging during the coronavirus disease 2019 (COVID-19) pandemic and was incidentally found to have a pericardial cyst.

Clinical efficacy of combination therapy of FuXi-Tiandi-Wuxing Decoction and anti-viral drugs in the treatment of novel coronavirus pneumonia: A prospective interventional study.

Introduction: The National Administration of Traditional Chinese Medicine of the People's Republic of China (NATCM) and the State Administration of Traditional Chinese medicine (TCM) advocated a combination therapy of TCM and anti-viral drugs for novel coronavirus pneumonia (NCP) to improve the efficacy of clinical treatment. Methods: Forty-six patients diagnosed with NCP were sequentially divided into intent-to-treat population: the experimental group (combination of FuXi-Tiandi-Wuxing Decoction and anti-viral drugs; n = 23) and the control group (anti-viral drugs only) (n = 23). The two groups were compared in terms of duration of fever, cough symptom score, fatigue, appetite, dyspnea, out-of-bed activities, chest computer tomography (CT) recovery, virological clearance, average length of hospital stay, and clinical effective rate of drug. After 6 days of observation, patients from the control group were divided into as-treated population: experimental subgroup (n = 14) to obtain clinical benefit and control subgroup (n = 9). Results: There was a significant improvement in the duration of fever (1.087 ± 0.288 vs 4.304 ± 2.490), cough (0.437 ± 0.589 vs 2.435 ± 0.662; P < 0.05), chest CT evaluation (82.6% vs 43.4%; P < 0.05), and virological clearance (60.8% vs 8.7%; P < 0.05) in patients of the experimental group compared with patients in the control group. Further observation in as-treated population reported that cough (0.742 ± 0.463 vs 1.862 ± 0.347; P < 0.05) and fatigue (78.5% vs 33.3%; P < 0.05) were significantly relieved after adding FuXi-Tiandi-Wuxing Decoction to the existing treatment. Conclusion: An early treatment with combination therapy of FuXi-Tiandi-Wuxing Decoction and anti-viral drugs significantly relieves the clinical symptoms of NCP, shows improvement in chest CT scan, improves virological clearance, shortens average length of hospital stay, and reduces the risk of severe illness. The effect of FuXi-Tiandi-Wuxing Decoction in NCP may be clinically important and require further consideration.

Clinical, Biochemical, and Radiological Presentation of RT-PCR-Positive vs RT-PCR-Negative SARS-CoV-2 Pneumonia Requiring ICU Care: An Observational, Cross-Sectional, Single-Center Study in Kalaburagi, Kalyana Karnataka.

Introduction Studies have reported similar clinical, biochemical, and radiological features between real-time polymerase chain reaction (RT-PCR)-positive and RT-PCR-negative patients. Therefore, the present study aims to assess differences in RT-PCR-positive versus RT-PCR-negative patients' characteristics. Methods We prospectively included 70 consecutive patients with typical coronavirus disease 2019 (COVID-19)-like clinical features who were either RT-PCR-positive or negative, requiring admission to the intensive care unit. The patients were classified into positive and negative RT-PCR groups and evaluated for clinical features, comorbidities, laboratory findings, and radiologic features. Results Fifty-seven point one percent (57.1%; 40/70) were RT-PCR positive, and 42.9% (30/70) were RT-PCR negative patients. The respiratory rate was higher among negative patients (P = 0.02), whereas the mean duration of fever was longer (3.34 vs 2.5; P = 0.022) among positive patients. At presentation, RT-PCR-negative patients had lower saturation of peripheral oxygen (SpO2) (near significant P = 0.058). Evaluation of co-morbidities revealed no differences. The neutrophil/lymphocyte ratio (NLR) (4.57 vs 6.52; P = 0.048), C-reactive protein (CRP) (9.97 vs 22.7; P = 0.007), and serum ferritin (158 vs 248.52; P = 0.010) were higher in patients who tested negative for RT-PCR. Thrombocytopenia (2.42 vs 1.76; P = 0.009), D-dimer levels (408.91 vs 123.06; P = 0.03), and interleukin (IL-6) levels (219.3 vs 80.81; P = 0.04) were significantly elevated among RT-PCR positive patients. The percentage of lung involvement in negative cases was 42.29+/-22.78 vs 36.21+/-21.8 in positive cases (P=0.23). The CT severity score was similar in both cohorts. Conclusion Both RT-PCR-positive and negative patients have similar clinical, biochemical, and radiological features. Considering that we are amidst a pandemic, it is advisable to have a similar approach irrespective of the RT-PCR report and triage and isolate accordingly. We recommend an RT-PCR-negative intensive care unit (ICU) ward and that the treating physician take a call on the management with a holistic approach driven clinically by the laboratory findings and helped by radiological findings. Stressing only on the RT-PCR report for management can be counterproductive.

Prospective evaluation of thoracic diseases using a compact flat-panel detector spiral computed tomographic scanner.

Objective: To prospectively evaluate the image quality and diagnostic performance of a compact flat-panel detector (FD) scanner for thoracic diseases compared to a clinical CT scanner. Materials and methods: The institutional review board approved this single-center prospective study, and all participants provided informed consent. From December 2020 to May 2021, 30 patients (mean age, 67.1 ± 8.3 years) underwent two same-day low-dose chest CT scans using clinical state-of-art and compact FDCT scanners. Image quality was assessed visually and quantitatively. Two readers evaluated the diagnostic performance for nodules, parenchymal opacifications, bronchiectasis, linear opacities, and pleural abnormalities in 40 paired CT scans. The other 20 paired CT scans were used to examine the agreement of semi-quantitative CT scoring regarding bronchiectasis, bronchiolitis, nodules, airspace consolidations, and cavities. Results: FDCT images had significantly lower visual image quality than clinical CT images (all p < 0.001). The two CT image sets showed no significant differences in signal-to-noise and contrast-to-noise ratios (56.8 ± 12.5 vs. 57.3 ± 15.2; p = 0.985 and 62.9 ± 11.7 vs. 60.7 ± 16.9; p = 0.615). The pooled sensitivity was comparable for nodules, parenchymal opacifications, linear opacities, and pleural abnormalities (p = 0.065-0.625), whereas the sensitivity was significantly lower in FDCT images than in clinical CT images for micronodules (p = 0.007) and bronchiectasis (p = 0.004). The specificity was mostly 1.0. Semi-quantitative CT scores were similar between the CT image sets (p > 0.05), and intraclass correlation coefficients were around 0.950 or higher, except for bronchiectasis (0.869). Conclusion: Compact FDCT images provided lower image quality but comparable diagnostic performance to clinical CT images for nodules, parenchymal opacifications, linear opacities, and pleural abnormalities.

Recurrent upper extremity arterial thrombosis preceding a diagnosis of COVID-19.

Arterial thrombosis occurs when there is endothelial damage in the setting of hypercoagulability and arterial blood stasis. COVID-19 has been theorized to cause both endothelial damage and promote hypercoagulability by causing an imbalance of clotting factors. In many studies, there have been a large proportion of COVID-19 patients that suffered a thromboembolic event, in both the venous and arterial systems. Our patient, who did not have a significant past medical history, presented with a recurrent brachial artery occlusion despite medical and surgical management, and subsequently tested positive for COVID-19 late in his admission. In conclusion, there is high suspicion that there is a relationship between COVID-19 infection and recurrent arterial thrombosis.

Haploidentical CD3+ TCR αß/CD19+ depleted HSCT for MHC Class II deficiency and persistent SARS-CoV-2 pneumonitis.

Background & Objectives: SARS-CoV-2 infection leads to coronavirus disease 2019 (COVID-19), which can range from a mild illness to a severe phenotype characterised by acute respiratory distress, needing mechanical ventilation. Children with combined immunodeficiencies might be unable to mount a sufficient cellular and humoral immune response against Covid-19 and have persistent disease. The authors describe a child with combined immunodeficiency, with favorable post-HSCT course following a haploidentical haematopoietic stem cell transplant in the presence of persistent SARS-CoV-2 infection. Methods & results: A 13-month-old girl with MHC class II deficiency developed persistent pre-HSCT SARS-CoV-2 infection. Faced with a significant challenge of balancing the risk of progressive infection due to incompetent immune system with the danger of inflammatory pneumonitis peri-immune reconstitution post-HSCT, she underwent a maternal (with a recent history of Covid-19 infection) haploidentical haematopoietic stem cell transplant. The patient received Regdanvimab® (post stem cell infusion) and Remdesivir (pre and post stem cell infusion). We noted a gradual increase in the Ct (cycle threshold) values, implying reduction in viral RNA with concomitant expansion in the CD3 lymphocyte subset and clinical/radiological improvement. Conclusions: Combination of adoptive transfer of maternal CD45RO+ memory add-back T-lymphocytes after haploidentical HSCT, use of Regdanvimab® (SARS-CoV-2 neutralising monoclonal antibody) and Remdesivir may have led to the successful outcome in our patient with severe immunodeficiency, undergoing HSCT. Our case highlights the role of novel antiviral strategies (monoclonal antibodies and CD45RO+ memory T-lymphocytes) in contributing to viral clearance in a challenging clinical scenario.

Laparoscopic appendectomy for acute appendicitis in patients with COVID-19 confirmation: A case report.

Introduction: Strategies to postpone elective surgeries were proposed to maintain the hospital capacity to cater for coronavirus disease 2019 (COVID-19) and emergency non-COVID cases. Non-operative management (NOM) was recommended when possible during the COVID-19 era. However, the optimal approach to acute appendicitis (AA) in patients with COVID-19 remains controversial. Presentation of case: A 25-year-old man who tested positive for severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2) was referred to our institution with a diagnosis of AA with appendicolith. Chest computed tomography did not detect evidence of pneumonia. Laparoscopic appendectomy was performed after strict infection prevention measures were taken. The postoperative course was uneventful. No respiratory symptoms such as cough or sputum production occurred postoperatively. No signs of infection in medical staff or spread in the operating room and infectious disease ward were observed. Discussion: The treatment policy should fully consider the risk of COVID-19 infection to medical staff and the risk of aggravation in patients who tested positive for SARS-Cov-2. Surgery was chosen over NOM for AA with appendicolith because the presence of appendicolith was thought to indicate a high probability of treatment failure in NOM and possible perforation; thus, case more difficult measures were required for SARS-Cov-2-positive cases. Conclusion: Careful assessment of the patient's condition and consideration of the treatment method is important, rather than choosing NOM over operative management based solely on SARS-Cov-2-positive status. Laparoscopic appendectomy with adequate infection control measures can be safely performed in SARS-Cov-2-positive cases.

Artificial intelligence model on chest imaging to diagnose COVID-19 and other pneumonias: A systematic review and meta-analysis.

Objectives: When diagnosing Coronavirus disease 2019(COVID-19), radiologists cannot make an accurate judgments because the image characteristics of COVID-19 and other pneumonia are similar. As machine learning advances, artificial intelligence(AI) models show promise in diagnosing COVID-19 and other pneumonias. We performed a systematic review and meta-analysis to assess the diagnostic accuracy and methodological quality of the models. Methods: We searched PubMed, Cochrane Library, Web of Science, and Embase, preprints from medRxiv and bioRxiv to locate studies published before December 2021, with no language restrictions. And a quality assessment (QUADAS-2), Radiomics Quality Score (RQS) tools and CLAIM checklist were used to assess the quality of each study. We used random-effects models to calculate pooled sensitivity and specificity, I2 values to assess heterogeneity, and Deeks' test to assess publication bias. Results: We screened 32 studies from the 2001 retrieved articles for inclusion in the meta-analysis. We included 6737 participants in the test or validation group. The meta-analysis revealed that AI models based on chest imaging distinguishes COVID-19 from other pneumonias: pooled area under the curve (AUC) 0.96 (95 % CI, 0.94-0.98), sensitivity 0.92 (95 % CI, 0.88-0.94), pooled specificity 0.91 (95 % CI, 0.87-0.93). The average RQS score of 13 studies using radiomics was 7.8, accounting for 22 % of the total score. The 19 studies using deep learning methods had an average CLAIM score of 20, slightly less than half (48.24 %) the ideal score of 42.00. Conclusions: The AI model for chest imaging could well diagnose COVID-19 and other pneumonias. However, it has not been implemented as a clinical decision-making tool. Future researchers should pay more attention to the quality of research methodology and further improve the generalizability of the developed predictive models.

Concomitant Purulent Pericarditis and Pleuritis Due to Actinomyces odontolyticus Following Endobronchial Biopsy for Pulmonary Sarcoidosis.

The authors present a very rare case of bacterial purulent pericarditis due to Actinomyces odontolyticus 2 weeks following an endobronchial ultrasound bronchoscopy. On his presentation, he was in cardiac tamponade, for which he underwent an emergent pericardiocentesis with purulent drainage. Similar organisms grew in his left pleural effusion. (Level of Difficulty: Intermediate.).

A COMPARATIVE STUDY OF X-RAY AND CT IMAGES IN COVID-19 DETECTION USING IMAGE PROCESSING AND DEEP LEARNING TECHNIQUES.

The deadly coronavirus has not just devastated the lives of millions but has put the entire healthcare system under tremendous pressure. Early diagnosis of COVID-19 plays a significant role in isolating the positive cases and preventing the further spread of the disease. The medical images along with deep learning models provided faster and more accurate results in the detection of COVID-19. This article extensively reviews the recent deep learning techniques for COVID-19 diagnosis. The research articles discussed reveal that Convolutional Neural Network (CNN) is the most popular deep learning algorithm in detecting COVID-19 from medical images. An overview of the necessity of pre-processing the medical images, transfer learning and data augmentation techniques to deal with data scarcity problems, use of pre-trained models to save time and the role of medical images in the automatic detection of COVID-19 are summarized. This article also provides a sensible outlook for the young researchers to develop highly effective CNN models coupled with medical images in the early detection of the disease.

SARS-CoV-2 infection showing signs of cerebral sinus vein thrombosis in the infantile period.

The clinical manifestations of SARS-CoV-2 infection mainly involve the respiratory system. However, there is increasing evidence that this virus can affect other organs, causing a wide range of clinical symptoms. This is the report of a 40-day-old patient who presented with sepsis and had no risk factors other than SARS-CoV-2 infection, whose radiological findings were compatible with cerebral sinus vein thrombosis.

Development and integration of VGG and dense transfer-learning systems supported with diverse lung images for discovery of the Coronavirus identity.

The contagious SARS-CoV-2 has had a tremendous impact on the life and health of many communities. It was first rampant in early 2019 and so far, 539 million cases of COVID-19 have been reported worldwide. This is reminiscent of the 1918 influenza pandemic. However, we can detect the infected cases of COVID-19 by analysing either X-rays or CT, which are presumably considered the least expensive methods. In the existence of state-of-the-art convolutional neural networks (CNNs), which integrate image pre-processing techniques with fully connected layers, we can develop a sophisticated AI system contingent on various pre-trained models. Each pre-trained model we involved in our study assumed its role in extracting some specific features from different chest image datasets in many verified sources, such as (Mendeley, Kaggle, and GitHub). First, for CXR datasets associated with the CNN trained model from the beginning, whereby is comprised of four layers beginning with the Conv2D layer, which comprises 32 filters, followed by the MaxPooling and afterwards, we reiterated similarly. We used two techniques to avoid overgeneralization, the early stopping and the Dropout techniques. After all, the output was one neuron to classify both cases of 0 or 1, followed by a sigmoid function; in addition, we used the Adam optimizer owing to the more improved outcomes than what other optimizers conducted; ultimately, we referred to our findings by using a confusion matrix, classification report (Recall & Precision), sensitivity and specificity; in this approach, we achieved a classification accuracy of 96%. Our three integrated pre-trained models (VGG16, DenseNet201, and DenseNet121) yielded a remarkable test accuracy of 98.81%. Besides, our merged models (VGG16, DenseNet201) trained on CT images with the utmost effort; this model held an accurate test of 99.73% for binary classification with the (Normal/Covid-19) scenario. Comparing our results with related studies shows that our proposed models were superior to the previous CNN machine learning models in terms of various performance metrics. Our pre-trained model associated with the CT dataset achieved 100% of the F1score and the loss value was approximately 0.00268.

Facial myonecrosis following COVID-19.

Myositis and myonecrosis are rare sequela of coronavirus disease 2019 (COVID-19). Until now, it has not been seen in muscles of the head and neck. We present a 22-year-old male with 4 months of retroauricular headaches following COVID-19 infection. Magnetic resonance imaging revealed rim-enhancing fluid collections in the bilateral masticator spaces which were sampled by fine-needle aspiration. We also discuss this case in the context of the current understanding of COVID-19-related myositis.