1 August 2020 in Radiology
Background Chest CT is used for diagnosis of 2019 novel coronavirus disease (COVID-19), as an important complement to the reverse-transcription polymerase chain reaction (RT-PCR) tests. Purpose To ...
24 November 2020 in Frontiers in Medicine
Objectives: To analyze follow-up CTs of patients recovering from COVID-19 in Wuhan, focusing on fibrotic change and its relevant risk factors.Methods: From January 13 to February 27, 2020, 166 hospitalized patients meeting our criteria were included. The scores of fibrotic patterns on follow-up CT were evaluated. Patients were designated as group 1 (with CT evidence of fibrotic pattern) and group 2 (without CT evidence of fibrotic pattern). Multivariate logistic regression was performed to explore risk factors for fibrotic change in patients with COVID-19.Results: The follow-up CTs were obtained on 56 days (median, IQR 51–63 days) after symptom onset. Of the 166 patients (mean age, 57 ± 15 years; 69/166 male), 46% (76/166) had CT evidence of fibrotic change and 77% (127/166) were severe or critical cases. Among patients with fibrotic change on CT, 84% (64/76) got a minimal or mild score of fibrosis. The high total score on peak CT, peak eosinophils, erythrocyte sedimentation rate (ESR) and advancing age were related to lung fibrotic change in patients with COVID-19.Conclusion: Forty six percentages of patients (mainly severe or critical cases) with COVID-19 showed fibrotic change on follow-up CT at early recovery phase, while the extent of fibrosis was not large. The advancing age, high total score on peak CT, peak eosinophils and ESR were associated with fibrotic change depicted by CT in patients recovering from COVID-19. An extended follow up by CT imaging and pulmonary function testing is necessary to fully assess the sequela of COVID-19.
24 May 2022 in IEEE Access
Automatic longitudinal assessment of the disease progression of coronavirus disease 2019 (COVID-19) is invaluable to ensure timely treatment for severe or critical patients. An artificial intelligence system that combines chest computed tomography (CT) and laboratory examinations may provide a more accurate diagnosis. To explore an artificial intelligence solution to longitudinally assess the condition of COVID-19 using CT imaging and laboratory findings, from January 27, 2020, to April 3, 2020, multiple follow-up examinations of COVID-19 inpatients were retrospectively collected. CT imaging features were automatically extracted using a deep learning method and combined with laboratory tests. The progression sequences were generated with two follow-ups, each of which contained 60 imaging and 24 laboratory features. Pearson’s correlation was conducted to rank the importance of each univariate feature, and multivariate logistic regression was adopted for feature selection. The selected features were used to train a 2-layer long short-term memory network (LSTM) with pulse oxygen saturation (SpO2) as an indicator of disease progression in three classes: alleviated, stable, and aggravated. The performance of models trained on various feature subsets was compared with five-fold cross validation.559 patients with 1734 examinations were collected, and 1450 progression sequences were generated. Of the 559 patients, 262 (46.9%) were male. The mean age of the patients was 60 ± 14 years. The mean hospitalization duration was 31 ± 12 days. Based on the ranking of importance, 26 features from the imaging and laboratory tests were selected, achieving the best accuracy of 0.85 for progression assessment. The comparisons demonstrated that CT features outperformed laboratory features. The best sensitivities for alleviated and aggravated obtained with CT features alone were 0.83 and 0.85, respectively, while laboratory features improved the assessment precision by about 3%. Longitudinal assessment using deep learning with combined features from CT imaging and laboratory tests better predicts the progression of COVID-19 than either of them.