The World Health Organization (WHO) 2017 classification of head and neck tumors has been just published and has reorganized tumors of the nasal cavity and paranasal sinuses. In this classification, three new entities (seromucinous hamartoma, NUT carcinoma, and biphenotypic sinonasal sarcoma) were included, while the total number of tumors has been reduced by excluding tumors if they did not occur exclusively or predominantly in this region. Among these entities, benign tumors were classified as sinonasal papillomas, respiratory epithelial lesions, salivary gland tumors, benign soft tissue tumors, or other tumors. In contrast, inflammatory diseases often show tumor-like appearances. The imaging features of these benign tumors and tumor-like inflammatory diseases often resemble malignant tumors, and some benign lesions should be given attention in the follow-up period and before surgery to avoid recurrence, malignant transformation, or massive bleeding. Understanding the CT and MR imaging features of various benign mass lesions is clinically important for appropriate therapy. The purpose of this article is to describe the clinical characteristics and imaging features of each of clinically important nasal and paranasal benign mass lesions, as classified according to the WHO 2017 classification of head and neck tumors, along with some inflammatory diseases.

BACKGROUND AND PURPOSE:Both clinical and imaging criteria must be met to diagnose neuromyelitis optica spectrum disorders and multiple sclerosis. However, neuromyelitis optica spectrum disorders are often misdiagnosed as MS because of an overlap in MR imaging features. The purpose of this study was to confirm imaging differences between neuromyelitis optica spectrum disorders and MS with visually detailed quantitative analyses of large-sample data.

No abstract

Recent advances in deep learning (DL) (4,5) have led to several radiologic applications (6), specifically Background: Digital subtraction angiography (DSA) generates an image by subtracting a mask image from a dynamic angiogram. However, patient movement-caused misregistration artifacts can result in unclear DSA images that interrupt procedures. Purpose:To train and to validate a deep learning (DL)-based model to produce DSA-like cerebral angiograms directly from dynamic angiograms and then quantitatively and visually evaluate these angiograms for clinical usefulness. Materials and Methods:A retrospective model development and validation study was conducted on dynamic and DSA image pairs consecutively collected from January 2019 through April 2019. Angiograms showing misregistration were first separated per patient by two radiologists and sorted into the misregistration test data set. Nonmisregistration angiograms were divided into development and external test data sets at a ratio of 8:1 per patient. The development data set was divided into training and validation data sets at ratio of 3:1 per patient. The DL model was created by using the training data set, tuned with the validation data set, and then evaluated quantitatively with the external test data set and visually with the misregistration test data set. Quantitative evaluations used the peak signal-to-noise ratio (PSNR) and the structural similarity (SSIM) with mixed liner models. Visual evaluation was conducted by using a numerical rating scale. Results:The training, validation, nonmisregistration test, and misregistration test data sets included 10 751, 2784, 1346, and 711 paired images collected from 40 patients (mean age, 62 years  11 [standard deviation]; 33 women). In the quantitative evaluation, DL-generated angiograms showed a mean PSNR value of 40.2 dB  4.05 and a mean SSIM value of 0.97  0.02, indicating high coincidence with the paired DSA images. In the visual evaluation, the median ratings of the DL-generated angiograms were similar to or better than those of the original DSA images for all 24 sequences. Conclusion:The deep learning-based model provided clinically useful cerebral angiograms free from clinically significant artifacts directly from dynamic angiograms.

PURPOSE To identify correlations of gliomas between 18 F-fluorodihydroxyphenylalanine (FDOPA) uptake and physiological magnetic resonance imaging (MRI) including relative cerebral blood volume (rCBV) and apparent diffusion coefficient (ADC) with different molecular subtypes, and to evaluate their prognostic values. METHODSSixty-eight treatment-naïve glioma patients who underwent FDOPA positron emission tomography (PET) and physiological MRI were retrospectively selected (isocitrate dehydrogenase wild-type [IDH wt ], 36; mutant 1p/19q non-codeleted [IDH m-non-codel ], 16; mutant codeleted [IDH m-codel ], 16). Fluid-attenuated inversion recovery hyperintense areas were segmented and used as regions-of-interest. For voxel-wise and patient-wise analyses,Pearson's correlation coefficients (r voxel-wise and r patient-wise ) between the normalized standardized uptake value (nSUV), rCBV, and ADC were evaluated. Cox regression analysis was performed to investigate the associations between the overall survival (OS) and r voxel-wise , max/median nSUV, median CBV, or median ADC. RESULTSFor IDH wt and IDH m-non-codel gliomas, nSUV demonstrated significant positive correlations with rCBV