Abstract
Background: Though imaging manifestations of COVID-19 and other types of viral pneumonia are similar, their clinical treatment methods differ. Accurate, non-invasive diagnostic methods using CT imaging can help develop an optimal therapeutic regimen for both conditions.
Objective: To compare the initial CT imaging features in COVID-19 with those in other types of viral pneumonia.
Methods: Clinical and imaging data of 51 patients with COVID-19 and 69 with other types of viral pneumonia were retrospectively studied. All significant imaging features (Youden index >0.3) were included for constituting the combined criteria for COVID-19 diagnosis, composed of two or more imaging features with a parallel model. McNemar's chi-square test or Fisher's exact test was used to compare the validity indices (sensitivity and specificity) among various criteria.
Results: Ground glass opacities (GGO) dominated density, peripheral distribution, unilateral lung, clear margin of lesion, rounded morphology, long axis parallel to the pleura, vascular thickening, and crazy-paving pattern were more common in COVID-19 (p <0.05). Consolidation-dominated density, both central and peripheral distributions, bilateral lung, indistinct margin of lesion, tree-inbud pattern, mediastinal or hilar lymphadenectasis, pleural effusion, and pleural thickening were more common in other types of viral pneumonia (p < 0.05). GGO-dominated density or long axis parallel to the pleura (with the highest sensitivity), and GGO-dominated density or long axis parallel to the pleura or vascular thickening (with the highest specificity) are well combined criteria of COVID-19.
Conclusion: The initial CT imaging features are helpful for the differential diagnosis of COVID-19 and other types of viral pneumonia.
Keywords: Coronavirus disease 2019, tomography, X-ray computed, other types of viral pneumonia, ground glass opacities, differential diagnosis, manifestation.
Graphical Abstract
Call for Papers in Thematic Issues
Intelligent Information Retrieval for Multispectral and Hyperspectral Imaging
Multispectral and hyperspectral imaging is an interdisciplinary research area, widely focuses on spectral, spatial, and temporal data. It offers a plethora of opportunities to efficiently analyze the vast area of the earth's surface. However, there are numerous factors such as dimensionality and size of the hyperspectral data, lesser training samples, ...read more
Machine and Deep Learning in Medical Image Diagnosis
Medical Image Processing regards a set of methodologies that have been developed over recent years with the purpose of improving medical image quality, improving medical data visualization, understanding, and assisting medical diagnosis, and so on. The application of machine and deep learning methods in sensing and imaging can potentially have ...read more
Quantum Machine Learning for Medical Data and Imaging
Quantum computing has promised a significant speedup in certain computationally intensive tasks that are intractable on classical computers. Researchers in quantum machine learning, such as those working in computer vision, image processing, biomedical analysis, and related topics, may play an important role in comprehending and working on complicated medical data, ...read more
21