Auxiliary Diagnosis for COVID-19 with Deep Transfer Learning.

To assist physicians identify COVID-19 and its manifestations through the automatic COVID-19 recognition and classification in chest CT images with deep transfer learning. In this retrospective study, the used chest CT image dataset covered 422 subjects, including 72 confirmed COVID-19 subjects (260 studies, 30,171 images), 252 other pneumonia subjects (252 studies, 26,534 images) that contained 158 viral pneumonia subjects and 94 pulmonary tuberculosis subjects, and 98 normal subjects (98 studies, 29,838 images). In the experiment, subjects were split into training (70%), validation (15%) and testing (15%) sets. We utilized the convolutional blocks of ResNets pretrained on the public social image collections and modified the top fully connected layer to suit our task (the COVID-19 recognition). In addition, we tested the proposed method on a finegrained classification task; that is, the images of COVID-19 were further split into 3 main manifestations (ground-glass opacity with 12,924 images, consolidation with 7418 images and fibrotic streaks with 7338 images). Similarly, the data partitioning strategy of 70%-15%-15% was adopted. The best performance obtained by the pretrained ResNet50 model is 94.87% sensitivity, 88.46% specificity, 91.21% accuracy for COVID-19 versus all other groups, and an overall accuracy of 89.01% for the three-category classification in the testing set. Consistent performance was observed from the COVID-19 manifestation classification task on images basis, where the best overall accuracy of 94.08% and AUC of 0.993 were obtained by the pretrained ResNet18 (P < 0.05). All the proposed models have achieved much satisfying performance and were thus very promising in both the practical application and statistics. Transfer learning is worth for exploring to be applied in recognition and classification of COVID-19 on CT images with limited training data. It not only achieved higher sensitivity (COVID-19 vs the rest) but also took far less time than radiologists, which is expected to give the auxiliary diagnosis and reduce the workload for the radiologists.

Early prediction of severity in coronavirus disease (COVID-19) using quantitative CT imaging.

PURPOSE: To evaluate whether the extent of COVID-19 pneumonia on CT scans using quantitative CT imaging obtained early in the illness can predict its future severity. METHODS: We conducted a retrospective single-center study on confirmed COVID-19 patients between January 18, 2020 and March 5, 2020. A quantitative AI algorithm was used to evaluate each patient's CT scan to determine the proportion of the lungs with pneumonia (VR) and the rate of change (RAR) in VR from scan to scan. Patients were classified as being in the severe or non-severe group based on their final symptoms. Penalized B-splines regression modeling was used to examine the relationship between mean VR and days from onset of symptoms in the two groups, with 95% and 99% confidence intervals. RESULTS: Median VR max was 18.6% (IQR 9.1-32.7%) in 21 patients in the severe group, significantly higher (P < 0.0001) than in the 53 patients in non-severe group (1.8% (IQR 0.4-5.7%)). RAR was increasing with a median RAR of 2.1% (IQR 0.4-5.5%) in severe and 0.4% (IQR 0.1-0.9%) in non-severe group, which was significantly different (P < 0.0001). Penalized B-spline analyses showed positive relationships between VR and days from onset of symptom. The 95% confidence limits of the predicted means for the two groups diverged 5 days after the onset of initial symptoms with a threshold of 11.9%. CONCLUSION: Five days after the initial onset of symptoms, CT could predict the patients who later developed severe symptoms with 95% confidence.

Chest computed tomography in children with COVID-19 respiratory infection.

BACKGROUND: Infection with COVID-19 is currently rare in children. OBJECTIVE: To describe chest CT findings in children with COVID-19. MATERIALS AND METHODS: We studied children at a large tertiary-care hospital in China, during the period from 28 January 2019 to 8 February 2020, who had positive reverse transcriptase polymerase chain reaction (RT-PCR) for COVID-19. We recorded findings at any chest CT performed in the included children, along with core clinical observations. RESULTS: We included five children from 10 months to 6 years of age (mean 3.4 years). All had had at least one CT scan after admission. Three of these five had CT abnormality on the first CT scan (at 2 days, 4 days and 9 days, respectively, after onset of symptoms) in the form of patchy ground-glass opacities; all normalised during treatment. CONCLUSION: Compared to reports in adults, we found similar but more modest lung abnormalities at CT in our small paediatric cohort.

Clinical and CT features of the COVID-19 infection: comparison among four different age groups.

PURPOSE: To compare and analyze the clinical and CT features of coronavirus disease 2019 (COVID-19) among four different age groups. METHODS: 97 patients (45 males, 52 females, mean age, 66.2 ± 5.0) with chest CT examination and positive reverse transcriptase-polymerase chain reaction test (RT-PCR) from January 17, 2020 to February 21, 2020 were retrospectively studied. The patients were divided into four age groups (children [0-17 years], young adults [18-44 years], middle age [45-59 years], and senior [≥ 60 years]) according to their age after the diagnosis was made based on PCR test and clinical symptoms. RESULTS: Comorbidities such as hypertension, diabetes mellitus, and heart disease are more common in the senior group. Cluster onset (two or more confirmed cases in a small area) is more common in the children group and senior group. Older patients were found to have a higher incidence of the highest clinical classification (severe or critical) in these four groups. Senior patients have a higher incidence of large/multiple ground-glass opacity (GGO). Child patients are mostly negative for chest CT or with involvement of only one lobe of the lung; while in older patients, there was a higher incidence of involvement of four or five lung lobes. The frequency of lobe involvement was also found to have significant differences in the four age groups. CONCLUSION: The clinical and imaging features of patients in different age groups were found to be significantly different. A better understanding of the age differences in comorbidities, cluster onset, highest clinical classification, large/multiple GGO, numbers of lobes affected, and frequency of lobe involvement can be useful in the diagnosis of COVID-19 patients of different ages.

CT image visual quantitative evaluation and clinical classification of coronavirus disease (COVID-19).

OBJECTIVES: To explore the relationship between the imaging manifestations and clinical classification of COVID-19. METHODS: We conducted a retrospective single-center study on patients with COVID-19 from Jan. 18, 2020 to Feb. 7, 2020 in Zhuhai, China. Patients were divided into 3 types based on Chinese guideline: mild (patients with minimal symptoms and negative CT findings), common, and severe-critical (patients with positive CT findings and different extent of clinical manifestations). CT visual quantitative evaluation was based on summing up the acute lung inflammatory lesions involving each lobe, which was scored as 0 (0%), 1 (1-25%), 2 (26-50%), 3 (51-75%), or 4 (76-100%), respectively. The total severity score (TSS) was reached by summing the five lobe scores. The consistency of two observers was evaluated. The TSS was compared with the clinical classification. ROC was used to test the diagnosis ability of TSS for severe-critical type. RESULTS: This study included 78 patients, 38 males and 40 females. There were 24 mild (30.8%), 46 common (59.0%), and 8 severe-critical (10.2%) cases, respectively. The median TSS of severe-critical-type group was significantly higher than common type (p < 0.001). The ICC value of the two observers was 0.976 (95% CI 0.962-0.985). ROC analysis showed the area under the curve (AUC) of TSS for diagnosing severe-critical type was 0.918. The TSS cutoff of 7.5 had 82.6% sensitivity and 100% specificity. CONCLUSIONS: The proportion of clinical mild-type patients with COVID-19 was relatively high; CT was not suitable for independent screening tool. The CT visual quantitative analysis has high consistency and can reflect the clinical classification of COVID-19. KEY POINTS: • CT visual quantitative evaluation has high consistency (ICC value of 0.976) among the observers. The median TSS of severe-critical type group was significantly higher than common type (p < 0.001). • ROC analysis showed the area under the curve (AUC) of TSS for diagnosing severe-critical type was 0.918 (95% CI 0.843-0.994). The TSS cutoff of 7.5 had 82.6% sensitivity and 100% specificity. • The proportion of confirmed COVID-19 patients with normal chest CT was relatively high (30.8%); CT was not a suitable screening modality.