Viruses are the most common causes of respiratory infection. The imaging findings of viral pneumonia are diverse and overlap with those of other nonviral infectious and inflammatory conditions. However, identification of the underlying viral pathogens may not always be easy. There are a number of indicators for identifying viral pathogens on the basis of imaging patterns, which are associated with the pathogenesis of viral infections. Viruses in the same viral family share a similar pathogenesis of pneumonia, and the imaging patterns have distinguishable characteristics. Although not all cases manifest with typical patterns, most typical imaging patterns of viral pneumonia can be classified according to viral families. Although a definite diagnosis cannot be achieved on the basis of imaging features alone, recognition of viral pneumonia patterns may aid in differentiating viral pathogens, thus reducing the use of antibiotics. Recently, new viruses associated with recent outbreaks including human metapneumovirus, severe acute respiratory syndrome coronavirus, and Middle East respiratory syndrome coronavirus have been discovered. The imaging findings of these emerging pathogens have been described in a few recent studies. This review focuses on the radiographic and computed tomographic patterns of viral pneumonia caused by different pathogens, including new pathogens. Clinical characteristics that could affect imaging, such as patient age and immune status, seasonal variation and community outbreaks, and pathogenesis, are also discussed. The first goal of this review is to indicate that there are imaging features that should raise the possibility of viral infections. Second, to help radiologists differentiate viral infections, viruses in the same viridae that have similar pathogenesis and can have similar imaging characteristics are shown. By considering both the clinical and radiologic characteristics, radiologists can suggest the diagnosis of viral pneumonia. RSNA, 2018.

Purpose In multiphase coronary CT angiography (CTA), a series of CT images are taken at different levels of radiation dose during the examination. Although this reduces the total radiation dose, the image quality during the low‐dose phases is significantly degraded. Recently, deep neural network approaches based on supervised learning technique have demonstrated impressive performance improvement over conventional model‐based iterative methods for low‐dose CT. However, matched low‐ and routine‐dose CT image pairs are difficult to obtain in multiphase CT. To address this problem, we aim at developing a new deep learning framework. Method We propose an unsupervised learning technique that can remove the noise of the CT images in the low‐dose phases by learning from the CT images in the routine dose phases. Although a supervised learning approach is not applicable due to the differences in the underlying heart structure in two phases, the images are closely related in two phases, so we propose a cycle‐consistent adversarial denoising network to learn the mapping between the low‐ and high‐dose cardiac phases. Results Experimental results showed that the proposed method effectively reduces the noise in the low‐dose CT image while preserving detailed texture and edge information. Moreover, thanks to the cyclic consistency and identity loss, the proposed network does not create any artificial features that are not present in the input images. Visual grading and quality evaluation also confirm that the proposed method provides significant improvement in diagnostic quality. Conclusions The proposed network can learn the image distributions from the routine‐dose cardiac phases, which is a big advantage over the existing supervised learning networks that need exactly matched low‐ and routine‐dose CT images. Considering the effectiveness and practicability of the proposed method, we believe that the proposed can be applied for many other CT acquisition protocols.