Chest Chest Computed Tomography Images Research Articles

COVID-19 CT Image Synthesis With a Conditional Generative Adversarial Network.

Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has spread rapidly since December 2019. Real-time reverse transcription polymerase chain reaction (rRT-PCR) and chest computed tomography (CT) imaging both play an important role in COVID-19 diagnosis. Chest CT imaging offers the benefits of quick reporting, a low cost, and high sensitivity for the detection of pulmonary infection. Recently, deep-learning-based computer vision methods have demonstrated great promise for use in medical imaging applications, including X-rays, magnetic resonance imaging, and CT imaging. However, training a deep-learning model requires large volumes of data, and medical staff faces a high risk when collecting COVID-19 CT data due to the high infectivity of the disease. Another issue is the lack of experts available for data labeling. In order to meet the data requirements for COVID-19 CT imaging, we propose a CT image synthesis approach based on a conditional generative adversarial network that can effectively generate high-quality and realistic COVID-19 CT images for use in deep-learning-based medical imaging tasks. Experimental results show that the proposed method outperforms other state-of-the-art image synthesis methods with the generated COVID-19 CT images and indicates promising for various machine learning applications including semantic segmentation and classification.

Chest CT findings in RT-PCR positive asymptomatic COVID-19 patients

PurposeTo investigate chest computed tomography (CT) findings in asymptomatic patients tested positive for coronavirus disease (COVID-19) by reverse transcription-polymerase chain reaction (RT-PCR). Material and methodsThe chest CT images of 64 patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) who were RT-PCR test–positive but asymptomatic were retrospectively evaluated for the appearance and distribution of abnormal parenchymal findings. ResultsOf the 64 patients (mean age 59.4 ± 12; range 23–85), 42 (65%) were female, and 22 (35%) were male, and 16 (25%) of the patients had no abnormal findings on chest CT. Of the remaining 48 patients, lung involvement was bilateral in 32 (67%). Right upper lobe in 26 (54%), right middle lobe in 20 (42%), right lower lobe in 38 (79%), left upper lobe in 27 (56%), and left lower lobe were affected in 34 (71%) patients. The mean number of opacities detected in patients was 7.5 ± 5.7. The opacities were located only peripherally/subpleural in 22 (46%), only centrally/peribronchovascular in 5 (10%), and mixed in 21 (44%) patients. The frequency of pure ground glass opacities (GGO) was 63% GGO with a crazy-paving pattern or consolidation was 33%. Pure consolidation was detected in only two (4%) patients. Parenchymal opacities were only round in 27 (56%), only geographic demarcated in 3 (6%), only patchy in 2 (4%), and mixed in 16 (33%) patients. ConclusionChest CT was normal in only one-quarter of the asymptomatic patients. CT findings in asymptomatic COVID-19 patients were often peripherally located, mostly round-shaped GGO.

Severity assessment of COVID-19 using CT image features and laboratory indices

The coronavirus disease 2019 (COVID-19) is now a global pandemic. Tens of millions of people have been confirmed with infection, and also more people are suspected. Chest computed tomography (CT) is recognized as an important tool for COVID-19 severity assessment. As the number of chest CT images increases rapidly, manual severity assessment becomes a labor-intensive task, delaying appropriate isolation and treatment. In this paper, a study of automatic severity assessment for COVID-19 is presented. Specifically, chest CT images of 118 patients (age 46.5 ± 16.5 years, 64 male and 54 female) with confirmed COVID-19 infection are used, from which 63 quantitative features and 110 radiomics features are derived. Besides the chest CT image features, 36 laboratory indices of each patient are also used, which can provide complementary information from a different view. A random forest (RF) model is trained to assess the severity (non-severe or severe) according to the chest CT image features and laboratory indices. Importance of each chest CT image feature and laboratory index, which reflects the correlation to the severity of COVID-19, is also calculated from the RF model. Using three-fold cross-validation, the RF model shows promising results: 0.910 (true positive ratio), 0.858 (true negative ratio) and 0.890 (accuracy), along with AUC of 0.98. Moreover, several chest CT image features and laboratory indices are found to be highly related to COVID-19 severity, which could be valuable for the clinical diagnosis of COVID-19.

Correlation between Computed Tomographic Analysis and Pulmonary Function Measurements in Patients with Relapsing Polychondritis

Background: Relapsing polychondritis (RP) is a rare systemic disease of unknown origin, with cartilaginous involvement in multiple organs. Airway involvement is the most important prognostic factor in RP. Objectives: Spirometric measurements and minimum tracheal cross-sectional area (mtCSA) have been reported as useful to assess the degree of airway stenosis. Because the length and severity of tracheal involvement in RP can vary, mtCSA might not provide enough information to assess tracheal abnormalities. We introduced tracheal volume (TrV) as a new method to evaluate correlations between chest computed tomography (CT) measurements and pulmonary function tests, including impulse oscillometry (IOS). Method: We analyzed chest CT images, spirometry, and IOS collected at our institution from April 2004 to March 2019. We calculated correlations between chest CT measurements using software (TrV, TrV/tracheal length [TrV/TL], and mtCSA) and pulmonary function parameters. Results: Twenty-five of 73 clinically diagnosed patients with RP were included. Spirometric findings showed moderate airway obstruction. Peak flow (PEF) was strongly correlated with mtCSA, TrV, and TrV/TL (ρ = 0.74, p < 0.001). FEV1 was significantly correlated with mtCSA (ρ = 0.56, p = 0.004), TrV (ρ = 0.52, p = 0.007), and TrV/TL (ρ = 0.53, p = 0.006). Whereas respiratory resistance at 5 Hz (R5) and 20 Hz (R20) and resonant frequencies (RFs) were significantly correlated with TrV (ρ = −0.46, p = 0.021; ρ = −0.46, p = 0.046; and ρ = −0.42, p = 0.037, respectively), IOS parameters and mtCSA were not. Conclusions: In patients with RP, TrV and mtCSA were strongly correlated with spirometric measurements. Respiratory resistances assessed by IOS correlated only with TrV. This suggests TrV assessment reflects pulmonary function in patients with RP more appropriately than mtCSA.

Glycemic status affects the severity of coronavirus disease 2019 in patients with diabetes mellitus: an observational study of CT radiological manifestations using an artificial intelligence algorithm

AimsIncreasing evidence suggests that poor glycemic control in diabetic individuals is associated with poor coronavirus disease 2019 (COVID-19) pneumonia outcomes and influences chest computed tomography (CT) manifestations. This study aimed to explore the impact of diabetes mellitus (DM) and glycemic control on chest CT manifestations, acquired using an artificial intelligence (AI)-based quantitative evaluation system, and COVID-19 disease severity and to investigate the association between CT lesions and clinical outcome.MethodsA total of 126 patients with COVID-19 were enrolled in this retrospective study. According to their clinical history of DM and glycosylated hemoglobin (HbA1c) level, the patients were divided into 3 groups: the non-DM group (Group 1); the well-controlled blood glucose (BG) group, with HbA1c < 7% (Group 2); and the poorly controlled BG group, with HbA1c ≥ 7% (Group 3). The chest CT images were analyzed with an AI-based quantitative evaluation system. Three main quantitative CT features representing the percentage of total lung lesion volume (PLV), percentage of ground-glass opacity volume (PGV) and percentage of consolidation volume (PCV) in bilateral lung fields were used to evaluate the severity of pneumonia lesions.ResultsPatients in Group 3 had the highest percentage of severe or critical illness, with 12 (32%) cases, followed by 6 (11%) and 7 (23%) cases in Groups 1 and 2, respectively (p = 0.042). The composite endpoints, including death or using mechanical ventilation or admission to the intensive care unit (ICU), were 3 (5%), 5 (16%) and 10 (26%) in Groups 1, 2 and 3, respectively (p = 0.013). The PLV, PGV and PCV in bilateral lung fields were significantly different among the three groups (all p < 0.001): the median PLVs were 12.5% (Group 3), 3.8% (Group 2) and 2.4% (Group 1); the median PGVs were 10.2% (Group 3), 3.6% (Group 2) and 1.9% (Group 1); and the median PCVs were 1.8% (Group 3), 0.3% (Group 2) and 0.1% (Group 1). In the linear regression analyses, which were adjusted for age, sex, BMI, and comorbidities, HbA1c remained positively associated with PLV (β = 0.401, p < 0.001), PGV (β = 0.364, p = 0.001) and PCV (β = 0.472, p < 0.001); this relationship was also observed between fasting blood glucose (FBG) and the three CT quantitative parameters. In the logistic regression analyses, PLV [OR 1.067 (1.032, 1.103)], PGV [OR 1.076 (1.034, 1.120)] and PCV [OR 1.280 (1.110, 1.476)] levels were independent predictors of the composite endpoints, as well as the areas under the ROC (AUCs) for PLV [AUC 0.796 (0.691, 0.900)], PGV [AUC 0.783 (0.678, 0.889)] and PCV [AUC 0.816 (0.722, 0.911)]; the ORs were still significant for CT lesions after adjusting for age, sex and poorly controlled diabetes.ConclusionsIncreased blood glucose level was correlated with the severity of lung involvement, as evidenced by certain chest CT parameters, and clinical prognosis in diabetic COVID-19 patients. There was a positive correlation between blood glucose level (both HbA1c and FBG) on admission and lung lesions. Moreover, the CT lesion severity by AI quantitative analysis was correlated with clinical outcomes.

The presence of emphysema on chest imaging and mid-life cognition.

BackgroundAirflow obstruction is associated with cognitive dysfunction but studies have not assessed how emphysema, a structural phenotype of lung disease, might be associated with cognitive function independent from pulmonary function measured by spirometry. We aimed to determine the relationship between the presence of visually detectable emphysema on chest computed tomography (CT) imaging and cognitive function.MethodsWe examined 2491 participants, mean age of 50 years, from the Coronary Artery Risk Development in Young Adults study who were assessed for the presence of emphysema on chest CT imaging and had cognitive function measured 5 years later with a battery of six cognitive tests.ResultsOf those assessed, 172 (7%) had emphysema. After adjusting for age, sex, height, study centre, race, body mass index, education and smoking, visual emphysema was significantly associated with worse performance on most cognitive tests. Compared to those without emphysema, participants with emphysema performed worse on cognitive testing: 0.39 sd units lower (95% CI −0.53– −0.25) on the Montreal Cognitive Assessment, 0.27 sd units lower (95% CI −0.42– −0.12) on the Rey Auditory Verbal Learning Test, 0.29 sd units lower (95% CI −0.43– −0.14) on the Digit Symbol Substitution Test and 0.25 sd units lower (95% CI −0.42– −0.09) on letter fluency. Further adjustment for forced expiratory volume in 1 s (FEV1), peak FEV1 and annualised FEV1 decline did not attenuate these associations.ConclusionsThe presence of emphysema on chest CT is associated with worse cognitive function, independent of airflow obstruction. These data suggest that emphysema may be a novel risk factor for cognitive impairment.

Novel artificial intelligence algorithm for automatic detection of COVID-19 abnormalities in computed tomography images

Background: Chest computed tomography (CT) is a readily available diagnostic test that can aid in the detection and assessment of the severity of the coronavirus disease 2019 (COVID-19). Given the wide community spread of the disease, it can be difficult for radiologists to differentiate between COVID-19 and non-COVID-19 pneumonia, especially in the oncological setting. Objective: This study was aimed at developing an artificial intelligence (AI) algorithm that could automatically detect COVID-19-related abnormalities from chest CT images and could serve as a diagnostic tool for COVID-19. In addition, we assessed the performance and accuracy of the algorithm in differentiating COVID-19 from non-COVID-19 lung parenchyma pathologies. Materials and Methods: A total of 1581 chest CT images of individuals affected with COVID-19, individuals affected with non-COVID-19 pathologies, and healthy individuals were included in this study. All the digital images of COVID-19-positive cases were obtained from web databases available in the public domain. About 60% of the data were used for training and validation of the algorithm, and the remaining 40% were used as a test set. A single-stage deep learning architecture based on the RetinaNet framework was used as the AI model for image classification. The performance of the algorithm was evaluated using various publicly available datasets comprising patients with COVID-19, patients with pneumonia, other lung diseases (underlying malignancies), and healthy individuals without any abnormalities. The specificity, sensitivity, and area under the receiver operating characteristic curve (AUC) were measured to estimate the effectiveness of our method. Results: The semantic and non-semantic features of the algorithm were analyzed. For the COVID-19 classification network, the sensitivity, specificity, accuracy, and AUC were 0.92 (95% confidence interval [CI]: 0.85–0.97), 0.995 (95% CI: 0.984–1.0), 0.972 (95% CI: 0.952–0.988), and 0.97 (95% CI: 0.945–0.986), respectively. For the non-COVID classification network, the sensitivity, specificity, and accuracy were 0.931 (95% CI: 0.88–0.975), 0.94 (95% CI: 0.90–0.974), and 0.935 (95% CI: 0.90, 0.965), respectively. Conclusion: The AI algorithm developed in our study can detect COVID-19 abnormalities from CT images with high sensitivity and specificity. Our AI algorithm can be used for the early detection and timely management of patients with COVID-19.

Clinical and imaging findings of patients diagnosed with adenovirus-positive pneumonia during 2015-2019 in Shanghai, China

This study was to describe the clinical characteristics, chest CT image findings and potential role of T cells immunity in adenovirus positive pneumonia. In this retrospective study, medical records of 53 adult Adv+ patients who were admitted to the Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, from May 2015 to August 2019 were included. Presence of adenovirus and other respiratory viruses was detected using by polymerase chain reaction of throat swabs samples. Clinical features and chest computed tomography (CT) findings were compared between patients with Adv+ pneumonia and Adv+ non-pneumonia. The top 3 most commonly occurring symptoms in Adv+ pneumonia patients were fever (66.7%), cough (63.3%), and tachypnea (16.7%). Patients with Adv+ pneumonia showed significantly higher rates of cough and fever and longer duration of hospitalization than patients with Adv+ non-pneumonia. In the Adv+ pneumonia group, consolidation (73.3%) was the most common imaging finding on chest CT scan, and the likelihood of involvement of bilateral lobes (60%) was high. Classical conspicuous consolidation with surrounding ground-glass opacity was observed in 5 (16.6%) patients with Adv+ pneumonia. Patients with Adv+ pneumonia showed a higher inhibition of T-cell immunity than did patients with Adv+ non-pneumonia, and counts of CD3+, CD4+, and CD8+ T-cells may predict the presence of pneumonia in Adv+ patients. With regard to Adv+ pneumonia, the most frequent symptoms were cough and fever, and the most common CT pattern was consolidation; classical CT findings such as consolidation with surrounding ground-glass opacity could also be observed. Furthermore, our data indicated the incidence of abrogated cellular immunity in patients with Adv+ pneumonia.

Evaluation of the RSNA and CORADS classifications for COVID-19 on chest computed tomography in the Brazilian population

OBJECTIVE:To determine the correlation between the two tomographic classifications for coronavirus disease (COVID-19), COVID-19 Reporting and Data System (CORADS) and Radiological Society of North America Expert Consensus Statement on Reporting Chest Computed Tomography (CT) Findings Related to COVID-19 (RSNA), in the Brazilian population and to assess the agreement between reviewers with different experience levels.METHODS:Chest CT images of patients with reverse transcriptase-polymerase chain reaction (RT-PCR)-positive COVID-19 were categorized according to the CORADS and RSNA classifications by radiologists with different levels of experience and who were initially unaware of the RT-PCR results. The inter- and intra-observer concordances for each of the classifications were calculated, as were the concordances between classifications.RESULTS:A total of 100 patients were included in this study. The RSNA classification showed an almost perfect inter-observer agreement between reviewers with similar experience levels, with a kappa coefficient of 0.892 (95% confidence interval [CI], 0.788-0.995). CORADS showed substantial agreement among reviewers with similar experience levels, with a kappa coefficient of 0.642 (95% CI, 0.491-0.793). There was inter-observer variation when comparing less experienced reviewers with more experienced reviewers, with the highest kappa coefficient of 0.396 (95% CI, 0.255-0.588). There was a significant correlation between both classifications, with a Kendall coefficient of 0.899 (p<0.001) and substantial intra-observer agreement for both classifications.CONCLUSION:The RSNA and CORADS classifications showed excellent inter-observer agreement for reviewers with the same level of experience, although the agreement between less experience reviewers and the reviewer with the most experience was only reasonable. Combined analysis of both classifications with the first RT-PCR results did not reveal any false-negative results for detecting COVID-19 in patients.

The effect of hepatic steatosis on COVID-19 severity: Chest computed tomography findings

Background:The objective of our study was to investigate the location, extension and type of novel coronavirus-induced disease 2019 (COVID-19) infection involvement and hepatic steatosis on initial chest computed tomography (CT). The relationship between fatty liver and severity of the disease was also investigated by measuring the liver attenuation index (LAI).Methods:This study evaluated the chest CT images of 343 patients (201 male, mean age 48.43 years) who were confirmed to have COVID-19, using nasopharyngeal swab. The chest CTs were analyzed for laterality, number of involved lobes, diffuseness, number of lesions, and lesion types. The CT attenuation values of liver and spleen were measured, and LAI was calculated for the detection of hepatic steatosis. Univariate and multivariate logistic regression analysis were used to identify the independent early predictors for severe COVID-19.Results:There was no significant difference between genders in terms of clinical course. Liver density and LAI were significantly lower in the intensive care unit (ICU) patients. The prevalence of severe disease was higher in the patients with hepatic steatosis than in the non-steatotic group (odds ratio [OR] 3.815, 95% confidence interval [CI] 1.97–7.37, P < 0.001). After adjusting for age and comorbidities including hypertension, diabetes mellitus, coronary artery disease, chronic obstructive pulmonary disease, and chronic kidney disease, multivariate logistic regression analysis showed that non-alcoholic fatty liver disease (NAFLD) was an independent risk factor for COVID-19 severity (OR 3.935, 95% CI 1.77-8.70, P = 0.001). The optimal cut-off value for LAI was calculated as 0.5 for predicting patients who required ICU treatment.Conclusions:On the initial chest CT images of COVID-19 patients, presence of fatty liver is a strong predictor for severe disease.

COVID-19: Chest Computed Tomography Imaging Patterns in Assessment of Disease Progression and Severity

Introduction: Chest Computed Tomography (CT) plays an important role in the diagnosis and management of Corona Virus Disease (COVID-19) infection. A better understanding of the chest CT imaging findings in COVID-19 disease may help in accurate diagnosis and staging of the disease. The temporal changes in the chest CT imaging findings follows a specific pattern which helps in identification of disease progression or recovery from the illness. Aim: To evaluate the chest CT imaging findings of COVID-19 patients during the course of disease. Materials and Methods: This was a retrospective observational study in which 110 hospitalised patients with COVID-19 disease were evaluated for chest CT imaging findings and severity of the infection. Chest CT findings with respect to duration of symptoms onset were divided into early phase disease (&lt;5 days of symptom onset), intermediate phase (5-12 days) and late phase disease (&gt;12 days of symptom onset). Based on visual assessment, CT severity score was given depending on the percentage of each lobe involved in bilateral lung parenchyma. Descriptive statistics were expressed using percentage, range, means and Standard Deviation (mean±SD). Results: A total of 110 COVID-19 positive patients (79 males and 31 females) with mean age of 48.33±9.18 years (range between 22-84 years) were included in the study. CT chest was performed during the different time periods of hospital stay ranging from 2 to 16 days. Early phase disease constituted 53 (48.18%) patients, 21 (19.09%) patients in the intermediate phase and 36 (32.72%) patients were in the late phase. Nineteen (17.27%) patients in the early phase disease (&lt;5 days) had a normal scan. Out of 91 chest CT positive patients, 13 patients (14.28%) were asymptomatic and 78 patients were symptomatic (85.71%). Among the CT positive patients, early phase disease constituted 34 (37.36%) patients, 21 (23.07%) patients were in the intermediate phase and 36 (39.56%) patients in the late phase disease. Early phase disease was predominantly characterised by Ground Glass Opacities (GGOs) which were seen in 27 patients (79.41%), gradual conversion of these GGOs into consolidations during the intermediate phase. Consolidations with fibrotic bands were predominant imaging patterns during the late phase disease seen in 21 patients (58.33%). Mean CT severity score during the early, intermediate and late phase diseases were 4.14±2.12, 14.71±4.80 and 11.08±4.68, respectively. Along with few existing signs described in COVID-19 disease, two signs during the late phase disease were observed such as target sign in 5 patients (13.88%) and centipede sign in 13 patients (36.11%). Splenomegaly was an additional extrapulmonary finding seen in 27 patients (24.5%) which has not been described previously. Conclusion: Specific imaging patterns during the course of COVID- 19 illness provide an information regarding the stage of the illness and disease severity. Ideal timing of chest CT is found to be during the intermediate phase of disease (5-12 days of symptom onset), since most of the lesions evolve in this period and provide accurate disease severity which in turn helps in treatment planning.

Evaluation of the RSNA and CORADS classifications for COVID-19 on chest computed tomography in the Brazilian population

OBJECTIVE:To determine the correlation between the two tomographic classifications for coronavirus disease (COVID-19), COVID-19 Reporting and Data System (CORADS) and Radiological Society of North America Expert Consensus Statement on Reporting Chest Computed Tomography (CT) Findings Related to COVID-19 (RSNA), in the Brazilian population and to assess the agreement between reviewers with different experience levels.METHODS:Chest CT images of patients with reverse transcriptase-polymerase chain reaction (RT-PCR)-positive COVID-19 were categorized according to the CORADS and RSNA classifications by radiologists with different levels of experience and who were initially unaware of the RT-PCR results. The inter- and intra-observer concordances for each of the classifications were calculated, as were the concordances between classifications.RESULTS:A total of 100 patients were included in this study. The RSNA classification showed an almost perfect inter-observer agreement between reviewers with similar experience levels, with a kappa coefficient of 0.892 (95% confidence interval [CI], 0.788-0.995). CORADS showed substantial agreement among reviewers with similar experience levels, with a kappa coefficient of 0.642 (95% CI, 0.491-0.793). There was inter-observer variation when comparing less experienced reviewers with more experienced reviewers, with the highest kappa coefficient of 0.396 (95% CI, 0.255-0.588). There was a significant correlation between both classifications, with a Kendall coefficient of 0.899 (p<0.001) and substantial intra-observer agreement for both classifications.CONCLUSION:The RSNA and CORADS classifications showed excellent inter-observer agreement for reviewers with the same level of experience, although the agreement between less experience reviewers and the reviewer with the most experience was only reasonable. Combined analysis of both classifications with the first RT-PCR results did not reveal any false-negative results for detecting COVID-19 in patients.

Deep learning for differentiating novel coronavirus pneumonia and influenza pneumonia

BackgroundChest computed tomography (CT) has been found to have high sensitivity in diagnosing novel coronavirus pneumonia (NCP) at the early stage, giving it an advantage over nucleic acid detection during the current pandemic. In this study, we aimed to develop and validate an integrated deep learning framework on chest CT images for the automatic detection of NCP, focusing particularly on differentiating NCP from influenza pneumonia (IP).MethodsA total of 148 confirmed NCP patients [80 male; median age, 51.5 years; interquartile range (IQR), 42.5–63.0 years] treated in 4 NCP designated hospitals between January 11, 2020 and February 23, 2020 were retrospectively enrolled as a training cohort, along with 194 confirmed IP patients (112 males; median age, 65.0 years; IQR, 55.0–78.0 years) treated in 5 hospitals from May 2015 to February 2020. An external validation set comprising 57 NCP patients and 50 IP patients from 8 hospitals was also enrolled. Two deep learning schemes (the Trinary scheme and the Plain scheme) were developed and compared using receiver operating characteristic (ROC) curves.ResultsOf the NCP lesions, 96.6% were >1 cm and 76.8% were of a density <−500 Hu, indicating them to have less consolidation than IP lesions, which had nodules ranging from 5–10 mm. The Trinary scheme accurately distinguished NCP from IP lesions, with an area under the curve (AUC) of 0.93. For patient-level classification in the external validation set, the Trinary scheme outperformed the Plain scheme (AUC: 0.87 vs. 0.71) and achieved human specialist-level performance.ConclusionsOur study has potentially provided an accurate tool on chest CT for early diagnosis of NCP with high transferability and showed high efficiency in differentiating between NCP and IP; these findings could help to reduce misdiagnosis and contain the pandemic transmission.

Rapid screening for COVID-19 by applying artificial intelligence to chest computed tomography images: A feasibility study.

Aim:The aim of the study was to present the results and impact of the application of artificial intelligence (AI) in the rapid diagnosis of COVID-19 by telemedicine in public health in Paraguay.Methods:This is a descriptive, multi-centered, observational design feasibility study based on an AI tool for the rapid detection of COVID-19 in chest computed tomography (CT) images of patients with respiratory difficulties attending the country’s public hospitals. The patients’ digital CT images were transmitted to the AI diagnostic platform, and after a few minutes, radiologists and pneumologists specialized in COVID-19 downloaded the images for evaluation, confirmation of diagnosis, and comparison with the genetic diagnosis (reverse transcription polymerase chain reaction (RT-PCR)). It was also determined the percentage of agreement between two similar AI systems applied in parallel to study the viability of using it as an alternative method of screening patients with COVID-19 through telemedicine.Results:Between March and August 2020, 911 rapid diagnostic tests were carried out on patients with respiratory disorders to rule out COVID-19 in 14 hospitals nationwide. The average age of patients was 50.7 years, 62.6% were male and 37.4% female. Most of the diagnosed respiratory conditions corresponded to the age group of 27–59 years (252 studies), the second most frequent corresponded to the group over 60 years, and the third to the group of 19–26 years. The most frequent findings of the radiologists/pneumologists were severe pneumonia, bilateral pneumonia with pleural effusion, bilateral pulmonary emphysema, diffuse ground glass opacity, hemidiaphragmatic paresis, calcified granuloma in the lower right lobe, bilateral pleural effusion, sequelae of tuberculosis, bilateral emphysema, and fibrotic changes, among others. Overall, an average of 86% agreement and 14% diagnostic discordance was determined between the two AI systems. The sensitivity of the AI system was 93% and the specificity 80% compared with RT-PCR.Conclusion:Paraguay has an AI-based telemedicine screening system for the rapid stratified detection of COVID-19 from chest CT images of patients with respiratory conditions. This application strengthens the integrated network of health services, rationalizing the use of specialized human resources, equipment, and inputs for laboratory diagnosis.

Chest Computed Tomography Severity Score to Predict Adverse Outcomes of Patients with COVID-19.

BackgroundThe novel coronavirus disease 2019 (COVID-19) continues to wreak havoc worldwide. This study assessed the ability of chest computed tomography (CT) severity score (CSS) to predict intensive care unit (ICU) admission and mortality in patients with COVID-19 pneumonia.Materials and MethodsA total of 192 consecutive patients with COVID-19 pneumonia aged more than 20 years and typical CT findings and reverse-transcription polymerase chain reaction positive admitted in a tertiary hospital were included. Clinical symptoms at admission and short-term outcome were obtained. A semi-quantitative scoring system was used to evaluate the parenchymal involvement. The association between CSS, disease severity, and outcomes were evaluated. Prediction of CSS was assessed with the area under the receiver-operating characteristic (ROC) curves.ResultsThe incidence of admission to ICU was 22.8% in men and 14.1% in women. CSS was related to ICU admission and mortality. Areas under the ROC curves were 0.764 for total CSS. Using a stepwise binary logistic regression model, gender, age, oxygen saturation, and CSS had a significant independent relationship with ICU admission and death. Patients with CSS ≥12.5 had about four-time risk of ICU admission and death (odds ratio 1.66, 95% confidence interval 1.66 – 9.25). The multivariate regression analysis showed the superiority of CSS over other clinical information and co-morbidities.ConclusionCSS was a strong predictor of progression to ICU admission and death and there was a substantial role of non-contrast chest CT imaging in the presence of typical features for COVID-19 pneumonia as a reliable predictor of clinical severity and patient’s outcome.

Clinical Features and Outcomes of Acute Kidney Injury in Patients Infected with COVID-19 in Xiangyang, China

Background: In December 2019, pneumonia associated with COVID-19 has spread from Wuhan to other areas in China. In the present study, we aimed to further clarify the clinical features and outcomes of acute kidney injury (AKI) in patients infected with COVID-19 in Xiangyang, Hubei, China. Methods: All confirmed cases of COVID-19 with AKI in Xiangyang Central Hospital from January 22 to May 31, 2020, were included in this retrospective study. Data of epidemiological, clinical, laboratory, radiological tests, treatment, complication, and outcomes were collected and analyzed. Patients were divided into intensive care unit (ICU) group and isolation ward (non-ICU) group. Results: Of the total patients, 33.3% in the non-ICU group and 85.7% in the ICU group had chronic diseases. In addition, 85.7% of patients in the ICU group died. The most common symptoms were fever, cough, and fatigue. The lymphocyte count in the ICU group was significantly reduced compared with the non-ICU group. The chest computed tomography (CT) images appeared showed multiple mottles and ground-glass opacity. Strip shadow could be found in chest CT images of some recovered patients. All patients received antiviral treatment. Most patients in the ICU group were given methylprednisolone, immunoglobulin, antibiotics, and mechanical ventilation and 35.7% of patients in the ICU group received continuous renal replacement therapy. Conclusions: Elderly with chronic comorbidities were more susceptible to COVID-19, showing a higher mortality rate due to multiple organ damage, and 35.7% of patients with AKI in ICU received renal replacement therapy. Moreover, part of the cured patients might need additional time to recover for poor lung function.

High serum lactate dehydrogenase and dyspnea: Positive predictors of adverse outcome in critical COVID-19 patients in Yichang.

BACKGROUNDCoronavirus disease 2019 (COVID-19) caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) outbreak in China, constitutes a Public Health Emergency of International Concern. It is well known that COVID-19 patients may have increased serum lactate dehydrogenase (LDH) levels in the early stage. The clinical changes in LDH may have predictive value in disease evolution and prognosis in critically ill COVID-19 patients.AIMTo examine serum LDH and clinical characteristics in patients with COVID-19 and their predictive value for prognosis.METHODSThis retrospective study analyzed the clinical data of forty-seven critical COVID-19 patients in the intensive care unit of the Third People's Hospital of Yichang City from January 27 to March 25, 2020 and divided them into survivors and non-survivors. The patients were diagnosed according to the World Health Organization interim guidance and critical cases met any one of the following criteria: Respiratory failure and required mechanical ventilation, the occurrence of shock, and the combined failure of other organs that required intensive care unit monitoring and treatments, according to the diagnostic criteria of critical COVID-19. Clinical data including symptoms, detection of SARS-CoV-2, chest computed tomography (CT) images, changes in serum LDH in different clinical phases, and prognosis were collected. Statistical analysis of the data was performed. Continuous variables were expressed as median (interquartile range) and compared with the Mann-Whitney U test. Categorical variables were compared with the Chi-square test. Survival data were analyzed using Kaplan-Meier survival curves and log-rank tests.RESULTSAccording to chest CT images, we observed the alveolitis and fibrosis stages in all critical patients in this study. Most non-survivors died in the fibrosis stage. Non-survivors had fewer days of hospitalization, shorter disease duration, shorter duration of alveolitis and fibrosis, and had dyspnea symptoms at disease onset (P = 0.05). Both first and lowest LDH values in the alveolitis stage were more pronounced in non-survivors than in survivors (449.0 U/L vs 288.0 U/L, P = 0.0243; 445.0 U/L vs 288.0 U/L, P = 0.0199, respectively), while the first, lowest and highest values of serum LDH in non-survivors were all significantly increased compared to survivors in the fibrosis phase (449.0 U/L vs 225.5 U/L, P = 0.0028; 432.0 U/L vs 191.0 U/L, P = 0.0007; 1303.0 U/L vs 263.5 U/L, P = 0.0001, respectively). The cut-off points of first LDH values in the alveolitis and fibrosis phase for distinction of non-survivors from survivors were 397.0 U/L and 263.0 U/L, respectively. In the fibrosis stage, non-survivors had more days with high LDH than survivors (7.0 d vs 0.0 d, P = 0.0002). Importantly, patients with high LDH had a significantly shorter median survival time than patients with low LDH in the alveolitis phase (22.0 d vs 36.5 d, P = 0.0002), while patients with high LDH also had a significantly shorter median survival time than patients with low LDH in the fibrosis phase (27.5 d vs 40.0 d, P = 0.0008). The proportion of non-survivors with detectable SARS-CoV-2 until death in the alveolitis stage was significantly increased compared with that in the fibrosis stage (100% vs 35.7%, P = 0.0220).CONCLUSIONHigh LDH and dyspnea symptoms were positive predictors of an adverse outcome in critical COVID-19. The rapid progressive fibrosis stage was more perilous than the alveolitis stage, even if SARS-CoV-2 is undetectable.

The Effects of Traditional Chinese Medicine as an Auxiliary Treatment for COVID-19: A Systematic Review and Meta-Analysis.

Background: Coronavirus disease 2019 (COVID-19) has become a pandemic with no specific and widely accepted effective drug or vaccine. However, studies have shown that Traditional Chinese Medicine (TCM) may play a significant role as an auxiliary treatment for COVID-19. Objective: This study aimed to assess the effects of TCM as an auxiliary treatment for COVID-19 through a systematic review of randomized-controlled trials (RCTs). Methods: Four English and three Chinese language databases were searched from December 1, 2019, to June 30, 2020. RCTs comparing TCM in combination with Western medicine (WM) with the same WM therapies alone for confirmed COVID-19 patients were included. The outcome measures were cure rate, lowering of body temperature, cough relief, improvement in chest computed tomography (CT) images, deterioration of condition, and adverse effects. Methodological quality was assessed using the Cochrane risk-of-bias tool. A series of meta-analyses were conducted for selected outcomes using RevMan 5.3 software. The quality of evidence was appraised using the grading of recommendation, assessment, development, and evaluation (GRADE) recommendations. Results: Ten RCTs with a total of 1,285 patients were included. Compared with WM alone in treating COVID-19, WM with auxiliary treatment by TCM appears to have increased the cure rate (risk ratio [RR] 1.15 [95% confidence interval (CI) 1.04-1.26]), relieved cough (RR 1.32 [95% CI 1.15-1.52]), improved chest CT images (RR 1.23 [95% CI 1.11-1.37]), and reduced the number of cases transitioning from a moderate to severe condition (RR 0.58 [95% CI 0.43-0.77]). The authors are uncertain whether TCM combined WM has effects on fever normalization (RR 1.10 [95% CI 0.94-1.29]) or adverse effects (RR 0.81 (95% CI 0.42-1.57]). Although they evaluated the certainty of evidence for lowering body temperature and adverse effects as very low, and low for cure rate, certainty was evaluated as moderate for improvement in chest CT images, cough relief, and deterioration of condition. Conclusion: TCM may be an effective auxiliary treatment for COVID-19 patients, which is likely to help improve the main symptoms and reduce disease progression. However, due to the limited number of studies and apparent heterogeneity among them, a more definitive conclusion on the effect of TCM on lowering body temperature and adverse effects cannot be drawn at this time.

The image quality of deep-learning image reconstruction of chest CT images on a mediastinal window setting

To assess the image quality of deep-learning image reconstruction (DLIR) of chest computed tomography (CT) images on a mediastinal window setting in comparison to an adaptive statistical iterative reconstruction (ASiR-V). Thirty-six patients were evaluated retrospectively. All patients underwent contrast-enhanced chest CT and thin-section images were reconstructed using filtered back projection (FBP); ASiR-V (60% and 100% blending setting); and DLIR (low, medium, and high settings). Image noise, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were evaluated objectively. Two independent radiologists evaluated ASiR-V 60% and DLIR subjectively, in comparison with FBP, on a five-point scale in terms of noise, streak artefact, lymph nodes, small vessels, and overall image quality on a mediastinal window setting (width 400 HU, level 60 HU). In addition, image texture of ASiR-Vs (60% and 100%) and DLIR-high was analysed subjectively. Compared with ASiR-V 60%, DLIR-med and DLIR-high showed significantly less noise, higher SNR, and higher CNR (p<0.0001). DLIR-high and ASiR-V 100% were not significantly different regarding noise (p=0.2918) and CNR (p=0.0642). At a higher DLIR setting, noise was lower and SNR and CNR were higher (p<0.0001). DLIR-high showed the best subjective scores for noise, streak artefact, and overall image quality (p<0.0001). Compared with ASiR-V 60%, DLIR-med and DLIR-high scored worse in the assessment of small vessels (p<0.0001). The image texture of DLIR-high was significantly finer than that of ASIR-Vs (p<0.0001). DLIR-high improved the objective parameters and subjective image quality by reducing noise and streak artefacts and providing finer image texture.

Middle-aged and elderly patients with COVID-19 pneumonia arising from asymptomatic carriers: A report of six cases.

Middle-aged and elderly patients with COVID-19 pneumonia arising from asymptomatic carriers: A report of six cases.