Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 16 de 16
Filter
1.
Med Phys ; 2022 Jul 15.
Article in English | MEDLINE | ID: covidwho-1929957

ABSTRACT

PURPOSE: Coronavirus disease 2019 (COVID-19) is a recently declared worldwide pandemic. Triaging of patients into severe and non-severe could further help in targeted management. "Potential severe patients" is a category of patients who did not have severe symptoms at their initial diagnosis, but eventually progressed to be severe patients and are easily overlooked in the early stage. This work aimed to develop and evaluate a CT-based radiomics signature for the prediction of these potential severe COVID-19 patients. METHODS: One hundred fifty COVID-19 patients were enrolled and randomly divided into cross-validation and independent test sets. First, their clinical characteristics were screened using the univariate and multivariate logistic regression step by step. Then, radiomics features were extracted from the lesions on their chest CT images. Subsequently, the inter- and intra-class correlation coefficients (ICC) analysis, minimum-redundancy maximum-relevance (mRMR) selection, and the least absolute shrinkage and selection operator (LASSO) algorithm were used step by step for feature selection and construction of a radiomics signature. Finally, the screened clinical risk factors and constructed radiomics signature were combined for the combined model and Radiomics+Clinics nomogram construction. The predictive performance of the Radiomics and Combined models were evaluated and compared using receiver operating characteristic curve (ROC) analysis, Hosmer-Lemeshow test and Delong test. RESULTS: Clinical characteristics analysis resulted in the screening of five clinical risk factors. The combination of ICC, mRMR, and LASSO methods resulted in the selection of ten radiomics features, which made up of the radiomics signature. The differences in the radiomics signature between the potential severe and non-severe groups in cross-validation set and test sets were both p < 0.001. All Radiomics and Combined models showed a very good predictive performance with the accuracy and AUC of nearly or above 0.9. Additionally, we found no significant difference in the predictive performance between these two models. CONCLUSIONS: A CT-based radiomics signature for the prediction of potential severe COVID-19 patients was constructed and evaluated. Constructed Radiomics and Combined model showed good feasibility and accuracy. The Radiomics+Clinical nomogram, acted as a useful tool, may assist clinicians to better identify potential severe cases to target their management in the COVID-19 pandemic prevention and control.

2.
Vaccine ; 40(31): 4211-4219, 2022 Jul 29.
Article in English | MEDLINE | ID: covidwho-1882606

ABSTRACT

Porcine deltacoronavirus (PDCoV) is a novel coronavirus that causes diarrhea in pigs of various ages, especially in suckling piglets, and there are no effective measures to prevent and control PDCoV currently. In this study, two adjuvants Al(OH)3 and ODN2395 working through different mechanisms were used to prepare inactivated PDCoV vaccines, and the immune effects of PDCoV inactivated vaccines were assessed in mice. From the results, we found that both PDCoV/Al(OH)3 vaccine and PDCoV/2395 vaccine could induce IgG and neutralizing antibodies with high levels in mice. At the same time, cytokines of IFN-γ, IL-4 and chemokine ligand of CXCL13 in serum were significantly increased after immunization, and reached the highest levels in PDCoV/2395 vaccine group, which suggested that PDCoV/2395 could promote the production of both Th1 and Th2 polarized cytokines. In addition, histopathological observations showed that vaccination helped mice resist PDCoV infection. These results indicated that both the two inactivated vaccines have good immune effects. Moreover, the PDCoV/2395 vaccine worked better than the PDCoV/Al(OH)3 vaccine for PDCoV/2395 having the good ability to induce both humoral and cellular immunogenicity. The PDCoV/2395 inactivated vaccine developed in this study might be an effective tool for the prevention of PDCoV infection.


Subject(s)
COVID-19 , Swine Diseases , Animals , Cytokines , Deltacoronavirus , Mice , Swine , Vaccines, Inactivated
3.
Viruses ; 14(3)2022 02 27.
Article in English | MEDLINE | ID: covidwho-1765944

ABSTRACT

Porcine epidemic diarrhea virus (PEDV) is the major pathogen that causes diarrhea and high mortality in newborn piglets, with devastating impact on the pig industry. To further understand the molecular epidemiology and genetic diversity of PEDV field strains, in this study the complete genomes of four PEDV variants (HN2021, CH-HNYY-2018, CH-SXWS-2018, and CH-HNKF-2016) obtained from immunized pig farms in central China between 2016 to 2021 were characterized and analyzed. Phylogenetic analysis of the genome and S gene showed that the four strains identified in the present study had evolved into the subgroup G2a, but were distant from the vaccine strain CV777. Additionally, it was noteworthy that a new PEDV strain (named HN2021) belonging to the G2a PEDV subgroup was successfully isolated in vitro and it was further confirmed by RT-PCR that this isolate had a large natural deletion at 207-373 nt of the ORF3 gene, which has never been reported before. Particularly, in terms of pathogenicity evaluation, colostrum deprivation piglets challenged with PEDV HN2021 showed severe diarrhea and high mortality, confirming that PEDV HN2021 was a virulent strain. Hence, PEDV strain HN2021 of subgroup G2a presents a promising vaccine candidate for the control of recurring porcine epidemic diarrhea (PED) in China. This study lays the foundation for better understanding of the genetic evolution and molecular pathogenesis of PEDV.


Subject(s)
Coronavirus Infections , Porcine epidemic diarrhea virus , Swine Diseases , Vaccines , Animals , China/epidemiology , Diarrhea , Phylogeny , Swine , Virulence
5.
Int J Environ Res Public Health ; 19(4)2022 02 16.
Article in English | MEDLINE | ID: covidwho-1703016

ABSTRACT

More than 1.75 million COVID-19 infections and 16 thousand associated deaths have been reported in Malaysia. A meta-analysis on the prevalence of COVID-19 in different clinical stages before the National COVID-19 Vaccination Program in Malaysia is still lacking. To address this, the disease severity of a total of 215 admitted COVID-19 patients was initially recorded in the early phase of this study, and the data were later pooled into a meta-analysis with the aim of providing insight into the prevalence of COVID-19 in 5 different clinical stages during the outset of the COVID-19 pandemic in Malaysia. We have conducted a systematic literature search using PubMed, Web of Science, Scopus, ScienceDirect, and two preprint databases (bioRxiv and medRxiv) for relevant studies with specified inclusion and exclusion criteria. The quality assessment for the included studies was performed using the Newcastle-Ottawa Scale. The heterogeneity was examined with an I2 index and a Q-test. Funnel plots and Egger's tests were performed to determine publication bias in this meta-analysis. Overall, 5 studies with 6375 patients were included, and the pooled prevalence rates in this meta-analysis were calculated using a random-effect model. The highest prevalence of COVID-19 in Malaysia was observed in Stage 2 cases (32.0%), followed by Stage 1 (27.8%), Stage 3 (17.1%), Stage 4 (7.6%), and Stage 5 (3.4%). About two-thirds of the number of cases have at least one morbidity, with the highest percentage of hypertension (66.7%), obesity (55.5%), or diabetes mellitus (33.3%) in Stage 5 patients. In conclusion, this meta-analysis suggested a high prevalence of COVID-19 occurred in Stage 2. The prevalence rate in Stage 5 appeared to be the lowest among COVID-19 patients before implementing the vaccination program in Malaysia. These meta-analysis data are critically useful for designing screening and vaccination programs and improving disease management in the country.


Subject(s)
COVID-19 , COVID-19/epidemiology , COVID-19/prevention & control , COVID-19 Vaccines , Humans , Malaysia/epidemiology , Pandemics/prevention & control , Prevalence , SARS-CoV-2 , Vaccination
6.
Clin Transl Immunology ; 10(7): e1312, 2021.
Article in English | MEDLINE | ID: covidwho-1321684

ABSTRACT

OBJECTIVE: The COVID-19 pandemic poses an immense need for accurate, sensitive and high-throughput clinical tests, and serological assays are needed for both overarching epidemiological studies and evaluating vaccines. Here, we present the development and validation of a high-throughput multiplex bead-based serological assay. METHODS: More than 100 representations of SARS-CoV-2 proteins were included for initial evaluation, including antigens produced in bacterial and mammalian hosts as well as synthetic peptides. The five best-performing antigens, three representing the spike glycoprotein and two representing the nucleocapsid protein, were further evaluated for detection of IgG antibodies in samples from 331 COVID-19 patients and convalescents, and in 2090 negative controls sampled before 2020. RESULTS: Three antigens were finally selected, represented by a soluble trimeric form and the S1-domain of the spike glycoprotein as well as by the C-terminal domain of the nucleocapsid. The sensitivity for these three antigens individually was found to be 99.7%, 99.1% and 99.7%, and the specificity was found to be 98.1%, 98.7% and 95.7%. The best assay performance was although achieved when utilising two antigens in combination, enabling a sensitivity of up to 99.7% combined with a specificity of 100%. Requiring any two of the three antigens resulted in a sensitivity of 99.7% and a specificity of 99.4%. CONCLUSION: These observations demonstrate that a serological test based on a combination of several SARS-CoV-2 antigens enables a highly specific and sensitive multiplex serological COVID-19 assay.

7.
Clin Infect Dis ; 73(1): 68-75, 2021 07 01.
Article in English | MEDLINE | ID: covidwho-1292116

ABSTRACT

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has spread worldwide and has the ability to damage multiple organs. However, information on serum SARS-CoV-2 nucleic acid (RNAemia) in patients affected by coronavirus disease 2019 (COVID-19) is limited. METHODS: Patients who were admitted to Zhongnan Hospital of Wuhan University with laboratory-confirmed COVID-19 were tested for SARS-COV-2 RNA in serum from 28 January 2020 to 9 February 2020. Demographic data, laboratory and radiological findings, comorbidities, and outcomes data were collected and analyzed. RESULTS: Eighty-five patients were included in the analysis. The viral load of throat swabs was significantly higher than of serum samples. The highest detection of SARS-CoV-2 RNA in serum samples was between 11 and 15 days after symptom onset. Analysis to compare patients with and without RNAemia provided evidence that computed tomography and some laboratory biomarkers (total protein, blood urea nitrogen, lactate dehydrogenase, hypersensitive troponin I, and D-dimer) were abnormal and that the extent of these abnormalities was generally higher in patients with RNAemia than in patients without RNAemia. Organ damage (respiratory failure, cardiac damage, renal damage, and coagulopathy) was more common in patients with RNAemia than in patients without RNAemia. Patients with vs without RNAemia had shorter durations from serum testing SARS-CoV-2 RNA. The mortality rate was higher among patients with vs without RNAemia. CONCLUSIONS: In this study, we provide evidence to support that SARS-CoV-2 may have an important role in multiple organ damage. Our evidence suggests that RNAemia has a significant association with higher risk of in-hospital mortality.


Subject(s)
COVID-19 , Nucleic Acids , Cohort Studies , Humans , RNA, Viral , SARS-CoV-2
8.
Intell Med ; 1(1): 10-15, 2021 May.
Article in English | MEDLINE | ID: covidwho-1263293

ABSTRACT

During the highly infectious pandemic of coronavirus disease 2019 (COVID-19), artificial intelligence (AI) has provided support in addressing challenges and accelerating achievements in controlling this public health crisis. It has been applied in fields varying from outbreak forecasting to patient management and drug/vaccine development. In this paper, we specifically review the current status of AI-based approaches for patient management. Limitations and challenges still exist, and further needs are highlighted.

9.
Phys Med Biol ; 66(10)2021 05 10.
Article in English | MEDLINE | ID: covidwho-1180464

ABSTRACT

Personalized assessment and treatment of severe patients with COVID-19 pneumonia have greatly affected the prognosis and survival of these patients. This study aimed to develop the radiomics models as the potential biomarkers to estimate the overall survival (OS) for the COVID-19 severe patients. A total of 74 COVID-19 severe patients were enrolled in this study, and 30 of them died during the follow-up period. First, the clinical risk factors of the patients were analyzed. Then, two radiomics signatures were constructed based on two segmented volumes of interest of whole lung area and lesion area. Two combination models were built depend on whether the clinic risk factors were used and/or whether two radiomics signatures were combined. Kaplan-Meier analysis were performed for validating two radiomics signatures and C-index was used to evaluated the predictive performance of all radiomics signatures and combination models. Finally, a radiomics nomogram combining radiomics signatures with clinical risk factors was developed for predicting personalized OS, and then assessed with respect to the calibration curve. Three clinical risk factors were found, included age, malignancy and highest temperature that influence OS. Both two radiomics signatures could effectively stratify the risk of OS in COVID-19 severe patients. The predictive performance of the combination model with two radiomics signatures was better than that only one radiomics signature was used, and became better when three clinical risk factors were interpolated. Calibration curves showed good agreement in both 15 d survival and 30 d survival between the estimation with the constructed nomogram and actual observation. Both two constructed radiomics signatures can act as the potential biomarkers for risk stratification of OS in COVID-19 severe patients. The radiomics+clinical nomogram generated might serve as a potential tool to guide personalized treatment and care for these patients.


Subject(s)
COVID-19/mortality , Image Processing, Computer-Assisted/methods , Lung/pathology , Nomograms , Radiography, Thoracic/methods , Tomography, X-Ray Computed/methods , Aged , COVID-19/diagnostic imaging , COVID-19/pathology , COVID-19/virology , Female , Humans , Lung/diagnostic imaging , Lung/virology , Male , Middle Aged , Prognosis , Retrospective Studies , Risk Factors , SARS-CoV-2/isolation & purification , Survival Rate
10.
Radiol Cardiothorac Imaging ; 2(2): e200126, 2020 Apr.
Article in English | MEDLINE | ID: covidwho-1155978

ABSTRACT

PURPOSE: To compare radiologic characteristics of coronavirus disease 2019 (COVID-19) pneumonia at thin-section CT on admission between patients with mild and severe disease. MATERIALS AND METHODS: Seventy patients with COVID-19 pneumonia who were admitted to Zhongnan Hospital of Wuhan University between January 20, 2020 and January 27, 2020 were enrolled. On the basis of the World Health Organization guidelines, 50 patients were categorized with the mild form and 20 with the severe form based on clinical conditions. Imaging features, clinical, and laboratory data were reviewed and compared. RESULTS: Patients with the severe form (median age, 65 years; interquartile range [IQR]: 54.75-75.00 years) were older than those with the mild form of disease (median age, 42.5 years; IQR: 32.75-58.50 years) (P < .001). Patients with the severe form of disease had more lung segments involved (median number of segments: 17.5 vs 7.5, P ≤ .001) and also larger opacities (median number of segments with opacities measuring 3 cm to less than 50% of the lung segment: 5.5 vs 2.0, P = .006; ≥ 50% of lung segment: 7.5 vs 0.0, P < .001). They also had more interlobular septal thickening (75% vs 28%, P < .001), higher prevalence of air bronchograms (70% vs 32%, P = .004), and pleural effusions (40% vs 14%, P = .017). CONCLUSION: Ground-glass opacities with or without consolidation in a peripheral and basilar predominant distribution were the most common findings in COVID-19 pneumonia. Patients with the severe form of the disease had more extensive opacification of the lung parenchyma than did patients with mild disease. Interlobular septal thickening, air bronchograms, and pleural effusions were also more prevalent in severe COVID-19.© RSNA, 2020.

11.
Appl Soft Comput ; 98: 106897, 2021 Jan.
Article in English | MEDLINE | ID: covidwho-917218

ABSTRACT

The sudden outbreak of novel coronavirus 2019 (COVID-19) increased the diagnostic burden of radiologists. In the time of an epidemic crisis, we hope artificial intelligence (AI) to reduce physician workload in regions with the outbreak, and improve the diagnosis accuracy for physicians before they could acquire enough experience with the new disease. In this paper, we present our experience in building and deploying an AI system that automatically analyzes CT images and provides the probability of infection to rapidly detect COVID-19 pneumonia. The proposed system which consists of classification and segmentation will save about 30%-40% of the detection time for physicians and promote the performance of COVID-19 detection. Specifically, working in an interdisciplinary team of over 30 people with medical and/or AI background, geographically distributed in Beijing and Wuhan, we are able to overcome a series of challenges (e.g. data discrepancy, testing time-effectiveness of model, data security, etc.) in this particular situation and deploy the system in four weeks. In addition, since the proposed AI system provides the priority of each CT image with probability of infection, the physicians can confirm and segregate the infected patients in time. Using 1,136 training cases (723 positives for COVID-19) from five hospitals, we are able to achieve a sensitivity of 0.974 and specificity of 0.922 on the test dataset, which included a variety of pulmonary diseases.

12.
J Cell Mol Med ; 24(24): 14270-14279, 2020 12.
Article in English | MEDLINE | ID: covidwho-907630

ABSTRACT

Recent studies have demonstrated a marked decrease in peripheral lymphocyte levels in patients with coronavirus disease 2019 (COVID-19) caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Few studies have focused on the changes of NK, T- and B-cell subsets, inflammatory cytokines and virus-specific antibodies in patients with moderate COVID-19. A total of 11 RT-PCR-confirmed convalescent patients with COVID-19 and 11 patients with non-SARS-CoV-2 pneumonia (control patients) were enrolled in this study. NK, CD8+ T, CD4+ T, Tfh-like and B-cell subsets were analysed using flow cytometry. Cytokines and SARS-CoV-2-specific antibodies were analysed using an electrochemiluminescence immunoassay. NK cell counts were significantly higher in patients with COVID-19 than in control patients (P = 0.017). Effector memory CD8+ T-cell counts significantly increased in patients with COVID-19 during a convalescent period of 1 week (P = 0.041). TIM-3+ Tfh-like cell and CD226+ Tfh-like cell counts significantly increased (P = 0.027) and decreased (P = 0.022), respectively, during the same period. Moreover, ICOS+ Tfh-like cell counts tended to decrease (P = 0.074). No abnormal increase in cytokine levels was observed. The high expression of NK cells is important in innate immune response against SARS-CoV-2. The increase in effector memory CD8+ T-cell counts, the up-regulation of inhibitory molecules and the down-regulation of active molecules on CD4+ T cells and Tfh-like cells in patients with COVID-19 would benefit the maintenance of balanced cellular and humoural immune responses, may prevent the development of severe cases and contribute to the recovery of patients with COVID-19.


Subject(s)
Antibodies, Viral/biosynthesis , CD8-Positive T-Lymphocytes/immunology , COVID-19/immunology , Cytokines/biosynthesis , Killer Cells, Natural/immunology , SARS-CoV-2/immunology , T Follicular Helper Cells/immunology , Adult , Aged , Antibodies, Viral/immunology , CD4-Positive T-Lymphocytes/immunology , COVID-19/epidemiology , China/epidemiology , Cytokines/immunology , Female , Humans , Male , Middle Aged , Young Adult
13.
IEEE J Biomed Health Inform ; 24(10): 2787-2797, 2020 10.
Article in English | MEDLINE | ID: covidwho-724919

ABSTRACT

Coronavirus Disease 2019 (COVID-19) has rapidly spread worldwide since first reported. Timely diagnosis of COVID-19 is crucial both for disease control and patient care. Non-contrast thoracic computed tomography (CT) has been identified as an effective tool for the diagnosis, yet the disease outbreak has placed tremendous pressure on radiologists for reading the exams and may potentially lead to fatigue-related mis-diagnosis. Reliable automatic classification algorithms can be really helpful; however, they usually require a considerable number of COVID-19 cases for training, which is difficult to acquire in a timely manner. Meanwhile, how to effectively utilize the existing archive of non-COVID-19 data (the negative samples) in the presence of severe class imbalance is another challenge. In addition, the sudden disease outbreak necessitates fast algorithm development. In this work, we propose a novel approach for effective and efficient training of COVID-19 classification networks using a small number of COVID-19 CT exams and an archive of negative samples. Concretely, a novel self-supervised learning method is proposed to extract features from the COVID-19 and negative samples. Then, two kinds of soft-labels ('difficulty' and 'diversity') are generated for the negative samples by computing the earth mover's distances between the features of the negative and COVID-19 samples, from which data 'values' of the negative samples can be assessed. A pre-set number of negative samples are selected accordingly and fed to the neural network for training. Experimental results show that our approach can achieve superior performance using about half of the negative samples, substantially reducing model training time.


Subject(s)
Betacoronavirus , Clinical Laboratory Techniques/statistics & numerical data , Coronavirus Infections/diagnostic imaging , Coronavirus Infections/diagnosis , Pandemics , Pneumonia, Viral/diagnostic imaging , Pneumonia, Viral/diagnosis , Radiographic Image Interpretation, Computer-Assisted/statistics & numerical data , Supervised Machine Learning , Tomography, X-Ray Computed/statistics & numerical data , Algorithms , COVID-19 , COVID-19 Testing , Cohort Studies , Computational Biology , Coronavirus Infections/classification , Deep Learning , Diagnostic Errors/statistics & numerical data , Humans , Neural Networks, Computer , Pandemics/classification , Pneumonia, Viral/classification , Retrospective Studies , SARS-CoV-2
14.
Korean J Radiol ; 21(7): 919-924, 2020 07.
Article in English | MEDLINE | ID: covidwho-593300

ABSTRACT

OBJECTIVE: The current study reported a case series to illustrate the early computed tomography (CT) findings of coronavirus disease 2019 (COVID-19) in pediatric patients. MATERIALS AND METHODS: All pediatric patients who were diagnosed with COVID-19 and who underwent CT scan in Zhongnan Hospital of Wuhan University from January 20, 2020 to February 28, 2020 were included in the current study. Data on clinical and CT features were collected and analyzed. RESULTS: Four children were included in the current study. All of them were asymptomatic throughout the disease course (ranging from 7 days to 15 days), and none of them showed abnormalities in blood cell counts. Familial cluster was the main transmission pattern. Thin-section CT revealed abnormalities in three patients, and one patient did not present with any abnormal CT findings. Unilateral lung involvement was observed in two patients, and one patient showed bilateral lung involvement. In total, five small lesions were identified, including ground-glass opacity (n = 4) and consolidation (n = 1). All lesions had ill-defined margins with peripheral distribution and predilection of lower lobe. CONCLUSION: Small patches of ground-glass opacity with subpleural distribution and unilateral lung involvement were common findings on CT scans of pediatric patients in the early stage of the disease.


Subject(s)
Asymptomatic Infections , Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Tomography, X-Ray Computed , Adolescent , Betacoronavirus , COVID-19 , Child , China/epidemiology , Disease Progression , Female , Humans , Image Processing, Computer-Assisted , Lung/diagnostic imaging , Lung/pathology , Male , Pandemics , Retrospective Studies , SARS-CoV-2
15.
Korean J Radiol ; 21(6): 746-755, 2020 06.
Article in English | MEDLINE | ID: covidwho-262130

ABSTRACT

OBJECTIVE: To identify predictors of pulmonary fibrosis development by combining follow-up thin-section CT findings and clinical features in patients discharged after treatment for COVID-19. MATERIALS AND METHODS: This retrospective study involved 32 confirmed COVID-19 patients who were divided into two groups according to the evidence of fibrosis on their latest follow-up CT imaging. Clinical data and CT imaging features of all the patients in different stages were collected and analyzed for comparison. RESULTS: The latest follow-up CT imaging showed fibrosis in 14 patients (male, 12; female, 2) and no fibrosis in 18 patients (male, 10; female, 8). Compared with the non-fibrosis group, the fibrosis group was older (median age: 54.0 years vs. 37.0 years, p = 0.008), and the median levels of C-reactive protein (53.4 mg/L vs. 10.0 mg/L, p = 0.002) and interleukin-6 (79.7 pg/L vs. 11.2 pg/L, p = 0.04) were also higher. The fibrosis group had a longer-term of hospitalization (19.5 days vs. 10.0 days, p = 0.001), pulsed steroid therapy (11.0 days vs. 5.0 days, p < 0.001), and antiviral therapy (12.0 days vs. 6.5 days, p = 0.012). More patients on the worst-state CT scan had an irregular interface (59.4% vs. 34.4%, p = 0.045) and a parenchymal band (71.9% vs. 28.1%, p < 0.001). On initial CT imaging, the irregular interface (57.1%) and parenchymal band (50.0%) were more common in the fibrosis group. On the worst-state CT imaging, interstitial thickening (78.6%), air bronchogram (57.1%), irregular interface (85.7%), coarse reticular pattern (28.6%), parenchymal band (92.9%), and pleural effusion (42.9%) were more common in the fibrosis group. CONCLUSION: Fibrosis was more likely to develop in patients with severe clinical conditions, especially in patients with high inflammatory indicators. Interstitial thickening, irregular interface, coarse reticular pattern, and parenchymal band manifested in the process of the disease may be predictors of pulmonary fibrosis. Irregular interface and parenchymal band could predict the formation of pulmonary fibrosis early.


Subject(s)
Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Pulmonary Fibrosis/diagnostic imaging , Pulmonary Fibrosis/virology , Adult , Aged , Betacoronavirus/isolation & purification , COVID-19 , Coronavirus Infections/epidemiology , Coronavirus Infections/pathology , Female , Humans , Male , Microtomy/methods , Middle Aged , Pandemics , Patient Discharge , Pleural Effusion/pathology , Pleural Effusion/virology , Pneumonia, Viral/epidemiology , Pneumonia, Viral/pathology , Predictive Value of Tests , Pulmonary Fibrosis/pathology , Retrospective Studies , SARS-CoV-2 , Tomography, X-Ray Computed/methods
16.
Preprint in English | medRxiv | ID: ppmedrxiv-20039354

ABSTRACT

The sudden outbreak of novel coronavirus 2019 (COVID-19) increased the diagnostic burden of radiologists. In the time of an epidemic crisis, we hoped artificial intelligence (AI) to help reduce physician workload in regions with the outbreak, and improve the diagnosis accuracy for physicians before they could acquire enough experience with the new disease. Here, we present our experience in building and deploying an AI system that automatically analyzes CT images to detect COVID-19 pneumonia features. Different from conventional medical AI, we were dealing with an epidemic crisis. Working in an interdisciplinary team of over 30 people with medical and / or AI background, geographically distributed in Beijing and Wuhan, we were able to overcome a series of challenges in this particular situation and deploy the system in four weeks. Using 1,136 training cases (723 positives for COVID-19) from five hospitals, we were able to achieve a sensitivity of 0.974 and specificity of 0.922 on the test dataset, which included a variety of pulmonary diseases. Besides, the system automatically highlighted all lesion regions for faster examination. As of today, we have deployed the system in 16 hospitals, and it is performing over 1,300 screenings per day.

SELECTION OF CITATIONS
SEARCH DETAIL