Purpose/Objectives
To examine the performance of radiologists in differentiating COVID-19 pneumonia from the most common non-COVID-19 atypical pneumonias in a study cohort including viral, fungal and atypical bacterial pathogens. To perform an analysis of CT features in order to identify those, which can possibly allow radiologists to make the right diagnosis.
Methods & Materials
Patients with positive RT-PCR tests for SARS-CoV-2 (n=90) and for the most common atypical pathogens causing pneumonia (n=294) were retrospectively included. Five radiologists with different level of experience in thoracic imaging, who were blinded to the pathogen test results, assessed the CT scans independently and classified them as COVID-19 or non-COVID-19 pneumonia. All included CT scans, both of the COVID-19 and of the non-COVID-19 group, were reviewed and specific CT features were recorded. The recorded CT features were included in a multivariate logistic regression model in order to calculate their ability to predict COVID-19 pneumonia and in a cluster analysis (by Gower’s distance) in order to identify the atypical pneumonias most similar/dissimilar to COVID-19 pneumonia.
Results
The radiologists differentiated COVID-19 from non-COVID-19 pneumonia with an overall accuracy, sensitivity, and specificity of 88% ± 4 (SD), 79% ± 6 (SD), and 90% ± 6 (SD), respectively. The percentage of correct ratings was lower in the early and late CT stage of COVID-19 pneumonia compared to the progressive and peak stage (68 and 71% vs 85 and 89%). The CT features which were associated with the most increased risk of COVID-19 pneumonia were band like subpleural opacities (OR 5.55, p<0.001), vascular dilatation in areas of pulmonary abnormalities (OR 2.63, p=0.071), and subpleural curvilinear lines (OR 2.52, p=0.021). CT features primarily indicating airway disease, namely bronchial wall thickening and centrilobular nodules, were associated with decreased risk of COVID-19 pneumonia with OR of 0.30 (p=0.013) and 0.10 (p<0.001), respectively. When identifying two clusters in the data (silhouette width = 0.30), most of the pneumonias in Cluster 1 (“COVID-19-cluster”) were cases of COVID-19 pneumonia (86/90=96%). Furthermore, PJP, HSV1 and CMV pneumonia were often assigned to this cluster (86%, 81% and 74%, respectively).
Conclusion
Although COVID-pneumonia shares similar imaging characteristics to other non-COVID-19 atypical pneumonias on chest CT, radiologists can accurately differentiate between these two entities based on specific CT-features.

Differentiating COVID-19 pneumonia from atypical bacterial, fungal and non-COVID-19 viral pneumonia on Chest-CT: Is it possible?

The Winter Course 2021 covers a variety of topics from basics in interstitial lung disease, infections including Covid-19, malignancies, lung cancer screening, and artificial intelligence. The combination of topics is aimed to serve as a good introduction to radiologists embarking on a career in thoracic imaging as well as a solid refresher for experienced thoracic radiologists.

[ESTI Winter Course 2021 Evaluation Form](https://www.surveymonkey.com/r/PP9WFTJ?sid=%5Bsid_value%5D&uid=%5Buid_value%5D&tkn=%5Btkn_value%5D&cgrid=%5Bcgrid_value)

ESTI Winter Course 2021

A Computed Tomography-based Radiomics Model for Patient Prognostic Stratification in Non-Small Cell Lung Cancer

Break Video

CT-Guided Microcoil placement for VATS Resection of Pulmonary Nodules

Development of a risk prediction model for pneumothorax in percutaneous CT guided lung biopsy

Evaluation of an AI program in thoracic imaging: Performance in detection of thoracic aorta ectasia

A Single Centre Institutional Study on 2295 patients for COVID-19 Detection from Radiographs Using a Deep Learning Model - Our Experience and Insights

Evaluation of AI applications in thoracic imaging: Performance in the detection of vertebral body alterations

Can inclusion of the combination of chemical shift ratio and signal intensity increase the number of patient’s classified as definitively benign on thymic MRI beyond use of chemical shift ratio alone? Experience from a UK thoracic tertiary referral centre

Relative contribution of emphysema and airway disease to disease severity in COPD patients GOLD stages I to IV using quantitative computed tomography

Lung Thermal Ablation: Comparison between an Augmented Reality Computed Tomography (CT) 3D Navigation System (SIRIO) and Standard CT-Guided Technique

Reliability of Ultra-Short Echo Time MRI sequence in the assessment of Interstitial Lung Disease related to Systemic Sclerosis

Assessing longitudinal changes in lung gas transfer in dyspnoeic post-COVID-19 patients using hyperpolarized Xenon-129 Magnetic Resonance Imaging

Session Introduction