Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add filters

Clinical aspect
Year range
1.
Radiology ; 296(2): E65-E71, 2020 08.
Article in English | MEDLINE | ID: covidwho-657750

ABSTRACT

Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.


Subject(s)
Artificial Intelligence , Betacoronavirus , Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Adult , Aged , Clinical Laboratory Techniques/methods , Community-Acquired Infections/diagnostic imaging , Coronavirus Infections/diagnosis , Deep Learning , Diagnosis, Differential , Female , Humans , Imaging, Three-Dimensional/methods , Male , Middle Aged , Pandemics , ROC Curve , Radiographic Image Interpretation, Computer-Assisted/methods , Retrospective Studies , Sensitivity and Specificity , Tomography, X-Ray Computed/methods
2.
Chin. J. Radiol. ; 5(54): 435-439, 20200510.
Article in Chinese | ELSEVIER | ID: covidwho-478480

ABSTRACT

Objective: To explore the imaging changes of lung lesions in patients with imported COVID-19 when reaching the discharge standard. Methods: The clinical and CT imaging data of 60 cured patients with imported COVID-19 and discharged from January to February 2020 in Anhui Province were retrospectively collected. At the initial diagnosis, 5 cases were mild, 53 were ordinary, and 2 were severe. The clinical characteristics of the patients and the characteristics of chest CT images at discharge were analyzed. Results: Fever (57 cases) and cough (55 cases) were the main symptoms in 60 patients. In 5 mild patients, 3 cases were negative in the whole course of CT examination, 2 cases were negative in the first time and abnormal in the second time. The first CT imaging features of 55 patients (53 common type and 2 severe type) were mainly bilateral lung involvement (51 cases), multiple lesions (33 cases), more common under the pleura (40 cases), and ground glass opacities were the most common (55 cases). The features of chest CT in clinical outcomes were that the ground glass shadow in the lung gradually faded and was completely absorbed (19 cases); the scope of ground glass shadow in the lung expanded and progressed to crazy-paving, consolidation shadow, and the lesion gradually absorbed again followed by fibrous cord shadows (27 cases); ground-glass opacities in the lungs quickly progressed to a consolidation and then slowly absorbed. Most of the lesions were accompanied by more residual fibrous cord shadows (4 cases). In 2 severe patients, the lesions in the lungs were larger ground glass, and a large amount of fibrous foci remained after slow absorption. Conclusions: Chest CT plays an important role in the diagnosis and treatment of imported COVID-19, and the degree of lung involvement seen on CT images is in good agreement with clinical outcome.

3.
Radiology ; 296(2): E65-E71, 2020 08.
Article in English | MEDLINE | ID: covidwho-10509

ABSTRACT

Background Coronavirus disease 2019 (COVID-19) has widely spread all over the world since the beginning of 2020. It is desirable to develop automatic and accurate detection of COVID-19 using chest CT. Purpose To develop a fully automatic framework to detect COVID-19 using chest CT and evaluate its performance. Materials and Methods In this retrospective and multicenter study, a deep learning model, the COVID-19 detection neural network (COVNet), was developed to extract visual features from volumetric chest CT scans for the detection of COVID-19. CT scans of community-acquired pneumonia (CAP) and other non-pneumonia abnormalities were included to test the robustness of the model. The datasets were collected from six hospitals between August 2016 and February 2020. Diagnostic performance was assessed with the area under the receiver operating characteristic curve, sensitivity, and specificity. Results The collected dataset consisted of 4352 chest CT scans from 3322 patients. The average patient age (±standard deviation) was 49 years ± 15, and there were slightly more men than women (1838 vs 1484, respectively; P = .29). The per-scan sensitivity and specificity for detecting COVID-19 in the independent test set was 90% (95% confidence interval [CI]: 83%, 94%; 114 of 127 scans) and 96% (95% CI: 93%, 98%; 294 of 307 scans), respectively, with an area under the receiver operating characteristic curve of 0.96 (P < .001). The per-scan sensitivity and specificity for detecting CAP in the independent test set was 87% (152 of 175 scans) and 92% (239 of 259 scans), respectively, with an area under the receiver operating characteristic curve of 0.95 (95% CI: 0.93, 0.97). Conclusion A deep learning model can accurately detect coronavirus 2019 and differentiate it from community-acquired pneumonia and other lung conditions. © RSNA, 2020 Online supplemental material is available for this article.


Subject(s)
Artificial Intelligence , Betacoronavirus , Coronavirus Infections/diagnostic imaging , Pneumonia, Viral/diagnostic imaging , Adult , Aged , Clinical Laboratory Techniques/methods , Community-Acquired Infections/diagnostic imaging , Coronavirus Infections/diagnosis , Deep Learning , Diagnosis, Differential , Female , Humans , Imaging, Three-Dimensional/methods , Male , Middle Aged , Pandemics , ROC Curve , Radiographic Image Interpretation, Computer-Assisted/methods , Retrospective Studies , Sensitivity and Specificity , Tomography, X-Ray Computed/methods
SELECTION OF CITATIONS
SEARCH DETAIL