Longitudinal Assessment of Chest CT Findings and Pulmonary Function after COVID-19 Infection.

Background Information on pulmonary sequelae and pulmonary function 2 years after recovery from SARS-CoV-2 infection is lacking. Purpose To longitudinally assess changes in chest CT abnormalities and pulmonary function in individuals after SARS-CoV-2 infection. Materials and Methods In this prospective study, participants discharged from the hospital after SARS-CoV-2 infection from January 20 to March 10, 2020, were considered for enrollment. Participants without chest CT scans at admission or with complete resolution of lung abnormalities at discharge were excluded. Serial chest CT scans and pulmonary function test results were obtained 6 months (June 20 to August 31, 2020), 12 months (December 20, 2020, to February 3, 2021), and 2 years (November 16, 2021, to January 10, 2022) after symptom onset. The term interstitial lung abnormality (ILA) and two subcategories, fibrotic ILAs and nonfibrotic ILAs, were used to describe residual CT abnormalities on follow-up CT scans. Differences between groups were compared with the χ2 test, Fisher exact test, or independent samples t test. Results Overall, 144 participants (median age, 60 years [range, 27-80 years]; 79 men) were included. On 2-year follow-up CT scans, 39% of participants (56 of 144) had ILAs, including 23% (33 of 144) with fibrotic ILAs and 16% (23 of 144) with nonfibrotic ILAs. The remaining 88 of 144 participants (61%) showed complete radiologic resolution. Over 2 years, the incidence of ILAs gradually decreased (54%, 42%, and 39% of participants at 6 months, 12 months, and 2 years, respectively; P < .001). Respiratory symptoms (34% vs 15%, P = .007) and abnormal diffusing capacity of lung for carbon monoxide (43% vs 20%, P = .004) occurred more frequently in participants with ILAs than in those with complete radiologic resolution. Conclusion More than one-third of participants had persistent interstitial lung abnormalities 2 years after COVID-19 infection, which were associated with respiratory symptoms and decreased diffusion pulmonary function. Chinese Clinical Trial Registry no. ChiCTR2000038609 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by van Beek in this issue.

Chest CT Patterns from Diagnosis to 1 Year of Follow-up in Patients with COVID-19.

Background The chest CT manifestations of COVID-19 from hospitalization to convalescence after 1 year are unknown. Purpose To assess chest CT manifestations of COVID-19 up to 1 year after symptom onset. Materials and Methods Patients were enrolled if they were admitted to the hospital because of COVID-19 and underwent CT during hospitalization at two isolation centers between January 27, 2020, and March 31, 2020. In a prospective study, three serial chest CT scans were obtained at approximately 3, 7, and 12 months after symptom onset and were longitudinally analyzed. The total CT score of pulmonary lobe involvement, ranging from 0 to 25, was assessed (score of 1-5 for each lobe). Univariable and multivariable logistic regression analyses were performed to explore independent risk factors for residual CT abnormalities after 1 year. Results A total of 209 study participants (mean age, 49 years ± 13 [standard deviation]; 116 women) were evaluated. CT abnormalities had resolved in 61% of participants (128 of 209) at 3 months and in 75% of participants (156 of 209) at 12 months. Among participants with chest CT abnormalities that had not resolved, there were residual linear opacities in 25 of the 209 participants (12%) and multifocal reticular or cystic lesions in 28 of the 209 participants (13%). Age 50 years or older, lymphopenia, and severe or aggravation of acute respiratory distress syndrome were independent risk factors for residual CT abnormalities at 1 year (odds ratios = 15.9, 18.9, and 43.9, respectively; P < .001 for each comparison). In 53 participants with residual CT abnormalities at 12 months, reticular lesions (41 of 53 participants [77%]) and bronchial dilation (39 of 53 participants [74%]) were observed at discharge and were persistent in 28 (53%) and 24 (45%) of the 53 participants, respectively. Conclusion One year after COVID-19 diagnosis, chest CT scans showed abnormal findings in 53 of the 209 study participants (25%), with 28 of the 209 participants (13%) showing subpleural reticular or cystic lesions. Older participants with severe COVID-19 or acute respiratory distress syndrome were more likely to develop lung sequelae that persisted at 1 year. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Lee and Wi et al in this issue.

Association of anemia and COVID-19 in hospitalized patients.

Aim: COVID-19 is a major threat to public health worldwide. A large proportion of COVID-19 patients is proved to develop anemia. Herein, we investigate the association between anemia and severe pneumonia. Materials & methods: 137 of COVID-19-confirmed patients admitted to Wuhan Union Hospital (Wuhan, China) from 13 February to 17 March 2020 were included. Their clinical characteristics and laboratory data were studied, and multivariable logistic regression analyses were performed. Results: The anemic patients were less likely to develop fever in the early stage of COVID-19. Elevated IL-6 levels were found in anemic COVID-19 patients compared with those without anemia. COVID-19 patients with anemia had an 8.2 times greater possibility of developing severe pneumonia compared with their counterparts without anemia. Conclusion: This study comprehensively describes the clinical characteristics of anemic patients with ordinary, severe and critical COVID-19 and demonstrates the close relationship between the anemia and severe COVID-19.

Total Lung and Lobar Quantitative Assessment Based on Paired Inspiratory-Expiratory Chest CT in Healthy Adults: Correlation with Pulmonary Ventilatory Function.

OBJECTIVE: To provide the quantitative volumetric data of the total lung and lobes in inspiration and expiration from healthy adults, and to explore the value of paired inspiratory-expiratory chest CT scan in pulmonary ventilatory function and further explore the influence of each lobe on ventilation. METHODS: A total of 65 adults (29 males and 36 females) with normal clinical pulmonary function test (PFT) and paired inspiratory-expiratory chest CT scan were retrospectively enrolled. The inspiratory and expiratory volumetric indexes of the total lung (TL) and 5 lobes (left upper lobe [LUL], left lower lobe [LLL], right upper lobe [RUL], right middle lobe [RML], and right lower lobe [RLL]) were obtained by Philips IntelliSpace Portal image postprocessing workstation, including inspiratory lung volume (LVin), expiratory lung volume (LVex), volume change (∆LV), and well-aerated lung volume (WAL, lung tissue with CT threshold between -950 and -750 HU in inspiratory scan). Spearman correlation analysis was used to explore the correlation between CT quantitative indexes of the total lung and ventilatory function indexes (including total lung capacity [TLC], residual volume [RV], and force vital capacity [FVC]). Multiple stepwise regression analysis was used to explore the influence of each lobe on ventilation. RESULTS: At end-inspiratory phase, the LVin-TL was 4664.6 (4282.7, 5916.2) mL, the WALTL was 4173 (3639.6, 5250.9) mL; both showed excellent correlation with TLC (LVin-TL: r = 0.890, p < 0.001; WALTL: r = 0.879, p < 0.001). From multiple linear regression analysis with lobar CT indexes as variables, the LVin and WAL of these two lobes, LLL and RUL, showed a significant relationship with TLC. At end-expiratory phase, the LVex-TL was 2325.2 (1969.7, 2722.5) mL with good correlation with RV (r = 0.811, p < 0.001), of which the LVex of RUL and RML had a significant relationship with RV. For the volumetric change within breathing, the ∆LVTL was 2485.6 (2169.8, 3078.1) mL with good correlation with FVC (r = 0.719, p < 0.001), moreover, WALTL showed a better correlation with FVC (r = 0.817, p < 0.001) than that of ∆LVTL. Likewise, there was also a strong association between ∆LV, WAL of these two lobes (LLL and RUL), and FVC. CONCLUSIONS: The quantitative indexes derived from paired inspiratory-expiratory chest CT could reflect the clinical pulmonary ventilatory function, LLL, and RUL give greater impact on ventilation. Thus, the pulmonary functional evaluation needs to be more precise and not limited to the total lung level.

CT-Based Radiomics Helps to Predict Residual Lung Lesions in COVID-19 Patients at Three Months after Discharge.

BACKGROUND: In this study, our focus was on pulmonary sequelae of coronavirus disease 2019 (COVID-19). We aimed to develop and validate CT-based radiomic models for predicting the presence of residual lung lesions in COVID-19 survivors at three months after discharge. METHODS: We retrospectively enrolled 162 COVID-19 confirmed patients in our hospital (84 patients with residual lung lesions and 78 patients without residual lung lesions, at three months after discharge). The patients were all randomly allocated to a training set (n = 114) or a test set (n = 48). Radiomic features were extracted from chest CT images in different regions (entire lung or lesion) and at different time points (at hospital admission or at discharge) to build different models, sequentially, or in combination, as follows: (1) Lesion_A model (based on the lesion region at admission CT); (2) Lesion_D model (based on the lesion region at discharge CT); (3) Δlesion model (based on the lesion region at admission CT and discharge CT); (4) Lung_A model (based on the lung region at admission CT); (5) Lung_D model (based on the lung region at discharge CT); (6) Δlung model (based on the lung region at admission CT and discharge CT). The area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were used to evaluate the predictive performances of the radiomic models. RESULTS: Among the six models, the Lesion_D and the Δlesion models achieved better predictive efficacy, with AUCs of 0.907 and 0.927, sensitivity of 0.898 and 0.763, and specificity of 0.855 and 0.964 in the training set, and AUCs of 0.875 and 0.837, sensitivity of 0.920 and 0.680, and specificity of 0.826 and 0.913 in the test set, respectively. CONCLUSIONS: The CT-based radiomic models showed good predictive effects on the presence of residual lung lesions in COVID-19 survivors at three months after discharge, which may help doctors to plan follow-up work and to reduce the psychological burden of COVID-19 survivors.

Characteristics of mental health implications and plasma metabolomics in patients recently recovered from COVID-19.

This study aimed to explore the associations between cerebral white matter (WM) alterations, mental health status, and metabolism in recovered COVID-19 patients. We included 28 recovered COVID-19 patients and 27 healthy controls between April 2020 and June 2020. Demographic data, the mental health scores, diffusion-tensor imaging (DTI) data, and plasma metabolomics were collected and compared between the two groups. Tract-based spatial statistics and graph theory approaches were used for DTI data analysis. Untargeted metabolomics analysis of the plasma was performed. Correlation analyses were performed between these characteristics. Recovered COVID-19 patients showed decreased fractional anisotropy, increased mean diffusivity and radial diffusivity values in widespread brain regions, and significantly lower global efficiency, longer shortest path length, and less nodal local efficiency in superior occipital gyrus (all, P < 0.05, Bonferroni corrected). Our results also demonstrated significantly different plasma metabolic profiling in recovered COVID-19 patients even at 3 months after their hospital discharge, which was mainly related to purine pathways, amino acids, lipids, and amine metabolism. Certain regions with cerebral WM alterations in the recovered patients showed significant correlations with different metabolites and the mental health scores. We observed multiple alterations in both WM integrity and plasma metabolomics that may explain the deteriorated mental health of recovered COVID-19 patients. These findings may provide potential biomarkers for the mental health evaluation for the recovered COVID-19 patients and potential targets for novel therapeutics.

Radiology department preventive and control measures and work plan during COVID-19 epidemic-experience from Wuhan.

Since the outbreak of the coronavirus disease 2019 (COVID-19), it had rapidly spread to the whole world and seriously threatened the global health. Imaging examination plays an important role in the clinical diagnosis of this disease, which leads to the high infection risk of the medical staff in the radiology department. In this review, the authors thoroughly summed up the experience in the management and operation of radiology department and shared their experience of the protective and control strategies and work plan during the epidemic, including but not limited to the management framework of the radiology department, the environment and layout in the department, the requirements for protection of different posts and the equipment, as well as the essential diagnosis of COVID-19. It is worth noting that the main goal of the radiology department in every country is to complete the radiology examination safely and make an accurate diagnosis of COVID-19 patients. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s42058-021-00055-5.

Epidemiological, Clinical, Radiological Characteristics and Outcomes of Medical Staff with COVID-19 in Wuhan, China: Analysis of 101 Cases.

Objectives: As of 11 Feb 2020, a total of 1,716 medical staff infected with laboratory-confirmed the severe acute respiratory syndrome coronavirus 2 (SARS-Cov-2) in China had been reported. The predominant cause of the infection among medical staff remains unclear. We sought to explore the epidemiological, clinical characteristics and prognosis of infected medical staff. Methods: Medical staff who infected with SARS-Cov-2 and admitted to Union Hospital, Wuhan between 16 Jan to 25 Feb, 2020 were included in this single-centered, retrospective study. Data were compared by occupation and analyzed with the Kaplan-Meier and Cox regression methods. Results: A total of 101 medical staff (32 males and 69 females; median age: 33) were included in this study and 74.3% were nurses. A small proportion of the cohort had contact with specimens (3%) as well as patients infected with SARS-Cov-2 in fever clinics (15%) and isolation wards (3%). 80% of medical staff showed abnormal IL-6 levels and 33% had lymphocytopenia. Chest CT mainly manifested as bilateral (62%), septal/subpleural (77%) and groundglass opacities (48%). The major differences between doctors and nurses manifested in laboratory indicators. As of the last observed date, no patient was transferred to intensive care unit or died. Fever (HR=0.57; 95% CI 0.36-0.90) and IL-6 levels greater than 2.9 pg/ml (HR=0.50; 95% CI 0.30-0.86) were unfavorable factors for discharge. Conclusions: Our findings suggested that the infection of medical staff mainly occurred at the early stages of SARS-CoV-2 epidemic in Wuhan, and only a small proportion of infection had an exact mode. Meanwhile, medical staff infected with COVID-19 have relatively milder symptoms and favorable clinical course than ordinary patients, which may be partly due to their medical expertise, younger age and less underlying diseases. The potential risk factors of fever and IL-6 levels greater than 2.9 pg/ml could help to identify medical staff with poor prognosis at an early stage.

Longitudinal changes in COVID-19 clinical measures and correlation with the extent of CT lung abnormalities.

Rationale: To assess the longitudinal changes and relationships of clinical measures and extent of CT lung abnormalities in COVID-19. Methods: 81 patients with COVID-19 were prospectively enrolled and followed until discharge. CT scores were quantified on a basis of a CT scoring system where each lung was divided into 3 zones: upper (above the carina), middle, and lower (below the inferior pulmonary vein) zones; each zone was evaluated for percentage of lung involvement on a scale of 0-4 (0, 0%; 1, 0-24%; 2, 25% - 49%; 3, 50% -74%; 4, >74%).Temporal trends of CT scores and the laboratory parameters characteristic of COVID-19 were analyzed. Correlations between the two were determined at three milestones (initial presentation, worst CT manifestation, and recovery finding before discharge). Their correlations with duration to worst CT manifestation and discharge from symptom onset were evaluated. Results: CT scores peaked during illness days 6-11 (median: 5), and stayed steady. C-reactive protein and lactate dehydrogenase increased, peaked on illness days 6-8 and 8-11 (mean: 23.5 mg/L, 259.9 U/L), and gradually declined. Continual decrease and increase were observed in hemoglobin and lymphocyte count, respectively. Albumin reduced and remained at low levels with a nadir on illness days 12-15 (36.6 g/L). Both initial (r = 0.58, 0.64, p < 0.05) and worst CT scores (r = 0.47, 0.65, p < 0.05) were correlated with C-reactive protein and lactate dehydrogenase; and CT scores before discharge, only with albumin (r = -0.41, p < 0.05). Duration to worst CT manifestation was associated with initial and worst CT scores (r = 0.33, 0.29, p < 0.05). No parameters were related to timespan to discharge. Conclusion: Our results illustrated the temporal changes of characteristic clinical measures and extent of CT lung abnormalities in COVID-19. CT scores correlated with some important laboratory parameters, and might serve as prognostic factors.

A novel deep learning-based quantification of serial chest computed tomography in Coronavirus Disease 2019 (COVID-19).

This study aims to explore and compare a novel deep learning-based quantification with the conventional semi-quantitative computed tomography (CT) scoring for the serial chest CT scans of COVID-19. 95 patients with confirmed COVID-19 and a total of 465 serial chest CT scans were involved, including 61 moderate patients (moderate group, 319 chest CT scans) and 34 severe patients (severe group, 146 chest CT scans). Conventional CT scoring and deep learning-based quantification were performed for all chest CT scans for two study goals: (1) Correlation between these two estimations; (2) Exploring the dynamic patterns using these two estimations between moderate and severe groups. The Spearman's correlation coefficient between these two estimation methods was 0.920 (p < 0.001). predicted pulmonary involvement (CT score and percent of pulmonary lesions calculated using deep learning-based quantification) increased more rapidly and reached a higher peak on 23rd days from symptom onset in severe group, which reached a peak on 18th days in moderate group with faster absorption of the lesions. The deep learning-based quantification for COVID-19 showed a good correlation with the conventional CT scoring and demonstrated a potential benefit in the estimation of disease severities of COVID-19.

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.

AIMS: Increasing 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. METHODS: A 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. RESULTS: Patients 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 (ß = 0.401, p < 0.001), PGV (ß = 0.364, p = 0.001) and PCV (ß = 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. CONCLUSIONS: Increased 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.

CT changes of severe coronavirus disease 2019 based on prognosis.

This study aimed to determine the characteristics of CT changes in patients with severe coronavirus disease 2019 (COVID-19) based on prognosis. Serial CT scans in 47 patients with severe COVID-19 were reviewed. The patterns, distribution and CT score of lung abnormalities were assessed. Scans were classified according to duration in weeks after onset of symptoms. These CT abnormalities were compared between discharged and dead patients. Twenty-six patients were discharged, whereas 21 passed away. Discharged patients were characterized by a rapid rise in CT score in the first 2 weeks followed by a slow decline, presence of reticular and mixed patterns from the second week, and prevalence of subpleural distribution of opacities in all weeks. In contrast, dead patients were characterized by a progressive rise in CT score, persistence of ground-glass opacity and consolidation patterns in all weeks, and prevalence of diffuse distribution from the second week. CT scores of death group were significantly higher than those of discharge group (P < 0.05). The CT changes differed between the discharged and dead patients. An understanding of these differences can be of clinical significance in the assessment of the prognosis of severe COVID-19 patients.

Prognostic value of baseline clinical and HRCT findings in 101 patients with severe COVID-19 in Wuhan, China.

The aim of this study was to assess the prognostic value of baseline clinical and high resolution CT (HRCT) findings in patients with severe COVID-19. In this retrospective, two-center study, we included two groups of inpatients with severe COVID-19 who had been discharged or died in Jin Yin-tan hospital and Wuhan union hospital between January 5, 2020, and February 22, 2020. Cases were confirmed by real-time polymerase chain reaction. Demographic, clinical, and laboratory data, and HRCT imaging were collected and compared between discharged and deceased patients. Univariable and multivariable logistic regression models were used to assess predictors of mortality risk in these patients. 101 patients were included in this study, of whom 66 were discharged and 35 died in the hospital. The mean age was 56.6 ± 15.1 years and 67 (66.3%) were men. Of the 101 patients, hypertension (38, 37.6%), cardiovascular disease (21,20.8%), diabetes (18,17.8%), and chronic pulmonary disease (16,15.8%) were the most common coexisting conditions. The multivariable regression analysis showed older age (OR: 1.142, 95% CI 1.059-1.231, p < 0.001), acute respiratory distress syndrome (ARDS) (OR: 10.142, 95% CI 1.611-63.853, p = 0.014), reduced lymphocyte count (OR: 0.004, 95% CI 0.001-0.306, p = 0.013), and elevated HRCT score (OR: 1.276, 95% CI 1.002-1.625, p = 0.049) to be independent predictors of mortality risk on admission in severe COVID-19 patients. These findings may have important clinical implications for decision-making based on risk stratification of severe COVID-19 patients.

Development and evaluation of an artificial intelligence system for COVID-19 diagnosis.

Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 .

Corrigendum: Online Mental Health Survey in a Medical College in China During the COVID-19 Outbreak.

[This corrects the article DOI: 10.3389/fpsyt.2020.00459.].

Liver injury in patients with COVID-19: clinical profiles, CT findings, the correlation of the severity with liver injury.

BACKGROUND AND AIMS: Liver injury is found in some of patients with COVID-19. Liver injury of COVID-19 patients based on severity grading and abdominal radiological signs have not been reported until now. The aim of our study is to determine clinical profiles of the patients based on severity grading, describe abdominal radiological signs, and investigate the correlations of the severity with clinical profiles and radiological signs. METHODS: This retrospective cohort study included 115 patients with COVID-19 from Jan 2020 to Feb 2020. Medical records of the patients were collected and CT images were reviewed. RESULTS: Common clinical manifestations of patients with COVID-19 were fever (68.70%), cough (56.52%), fatigue (31.30%); some of them had gastrointestinal symptoms (diarrhea, 12.17%; nausea or vomiting 7.83%; inappetence, 7.83%). Abnormal liver function was observed in some of patients with COVID-19. Significant differences in the levels of AST, albumin,CRP were observed among different groups classified by the severity. Common findings of upper abdominal CT scan were liver hypodensity (26.09%) and pericholecystic fat stranding (21.27%); liver hypodensity was more frequently found in critical cases (58.82%). The severity of COVID-19 correlated with semi-quantitative CT score of pulmonary lesions, CT-quantified liver/spleen attenuation ratio in patients with COVID-19. CONCLUSIONS: Some of the patients with COVID-19 displayed liver damage revealed by liver functional tests and upper abdominal CT imaging, and the severity of COVID-19 patients correlated with some of liver functional tests and CT signs; thus, it will allow an earlier identification of high-risk patients for early effective intervention.

A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization From Chest CT.

Accurate and rapid diagnosis of COVID-19 suspected cases plays a crucial role in timely quarantine and medical treatment. Developing a deep learning-based model for automatic COVID-19 diagnosis on chest CT is helpful to counter the outbreak of SARS-CoV-2. A weakly-supervised deep learning framework was developed using 3D CT volumes for COVID-19 classification and lesion localization. For each patient, the lung region was segmented using a pre-trained UNet; then the segmented 3D lung region was fed into a 3D deep neural network to predict the probability of COVID-19 infectious; the COVID-19 lesions are localized by combining the activation regions in the classification network and the unsupervised connected components. 499 CT volumes were used for training and 131 CT volumes were used for testing. Our algorithm obtained 0.959 ROC AUC and 0.976 PR AUC. When using a probability threshold of 0.5 to classify COVID-positive and COVID-negative, the algorithm obtained an accuracy of 0.901, a positive predictive value of 0.840 and a very high negative predictive value of 0.982. The algorithm took only 1.93 seconds to process a single patient's CT volume using a dedicated GPU. Our weakly-supervised deep learning model can accurately predict the COVID-19 infectious probability and discover lesion regions in chest CT without the need for annotating the lesions for training. The easily-trained and high-performance deep learning algorithm provides a fast way to identify COVID-19 patients, which is beneficial to control the outbreak of SARS-CoV-2. The developed deep learning software is available at https://github.com/sydney0zq/covid-19-detection.

Novel Coronavirus Disease 2019 (COVID-19) Pneumonia Progression Course in 17 Discharged Patients: Comparison of Clinical and Thin-Section Computed Tomography Features During Recovery.

BACKGROUND: Our objective was to retrospectively analyze the evolution of clinical features and thin-section computed tomography (CT) imaging of novel coronavirus disease 2019 (COVID-19) pneumonia in 17 discharged patients. METHODS: Serial thin-section CT scans of 17 discharged patients with COVID-19 were obtained during recovery. Longitudinal changes of clinical parameters and a CT pattern were documented in all patients during the 4 weeks after admission. A CT score was used to evaluate the extent of the disease. RESULTS: There were marked improvements of fever, lymphocyte counts, C-reactive proteins, and erythrocyte sedimentation rates within the first 2 weeks after admission. However, the mean CT score rapidly increased from the first to the third week, with a top score of 8.2 obtained in the second week. During the first week, the main CT pattern was ground-glass opacities (GGO; 76.5%). The frequency of GGO (52.9%) decreased in the second week. Consolidation and mixed patterns (47.0%) were noted in the second week. Thereafter, consolidations generally dissipated into GGO, and the frequency of GGO increased in the third week (76.5%) and fourth week (71.4%). Opacities were mainly located in the peripheral (76.5%) and subpleural (47.1%) zones of the lungs; they presented as focal (35.3%) or multifocal (29.4%) in the first week and became more diffuse in the second (47.1%) and third weeks (58.8%), then showed a reduced extent in fourth week (50%). CONCLUSIONS: The progression course of the CT pattern was later than the progression of the clinical parameters within the first 2 weeks after admission; however, there were synchronized improvements in both the clinical and radiologic features in the fourth week.