The chest CT findings of patients with 2019 Novel Coronavirus (2019-nCoV) pneumonia have not previously been described in detail. To investigate the clinical, laboratory, and imaging findings of emerging 2019-nCoV pneumonia in humans. Fifty-one patients (25 men and 26 women; age range 16–76 years) with laboratory-confirmed 2019-nCoV infection by using real-time reverse transcription polymerase chain reaction underwent thin-section CT. The imaging findings, clinical data, and laboratory data were evaluated. Fifty of 51 patients (98%) had a history of contact with individuals from the endemic center in Wuhan, China. Fever (49 of 51, 96%) and cough (24 of 51, 47%) were the most common symptoms. Most patients had a normal white blood cell count (37 of 51, 73%), neutrophil count (44 of 51, 86%), and either normal (17 of 51, 35%) or reduced (33 of 51, 65%) lymphocyte count. CT images showed pure ground-glass opacity (GGO) in 39 of 51 (77%) patients and GGO with reticular and/or interlobular septal thickening in 38 of 51 (75%) patients. GGO with consolidation was present in 30 of 51 (59%) patients, and pure consolidation was present in 28 of 51 (55%) patients. Forty-four of 51 (86%) patients had bilateral lung involvement, while 41 of 51 (80%) involved the posterior part of the lungs and 44 of 51 (86%) were peripheral. There were more consolidated lung lesions in patients 5 days or more from disease onset to CT scan versus 4 days or fewer (431 of 712 lesions vs 129 of 612 lesions; P < .001). Patients older than 50 years had more consolidated lung lesions than did those aged 50 years or younger (212 of 470 vs 198 of 854; P < .001). Follow-up CT in 13 patients showed improvement in seven (54%) patients and progression in four (31%) patients. Patients with fever and/or cough and with conspicuous ground-glass opacity lesions in the peripheral and posterior lungs on CT images, combined with normal or decreased white blood cells and a history of epidemic exposure, are highly suspected of having 2019 Novel Coronavirus (2019-nCoV) pneumonia. © RSNA, 2020

Objective: Computed tomography (CT) provides rich diagnosis and severity information of COVID‐19 in clinical practice. However, there is no computerized tool to automatically delineate COVID‐19 infection regions in chest CT scans for quantitative assessment in advanced applications such as severity prediction. The aim of this study was to develop a deep learning (DL)‐based method for automatic segmentation and quantification of infection regions as well as the entire lungs from chest CT scans.Methods: The DL‐based segmentation method employs the “VB‐Net” neural network to segment COVID‐19 infection regions in CT scans. The developed DL‐based segmentation system is trained by CT scans from 249 COVID‐19 patients, and further validated by CT scans from other 300 COVID‐19 patients. To accelerate the manual delineation of CT scans for training, a human‐involved‐model‐iterations (HIMI) strategy is also adopted to assist radiologists to refine automatic annotation of each training case. To evaluate the performance of the DL‐based segmentation system, three metrics, that is, Dice similarity coefficient, the differences of volume, and percentage of infection (POI), are calculated between automatic and manual segmentations on the validation set. Then, a clinical study on severity prediction is reported based on the quantitative infection assessment.Results: The proposed DL‐based segmentation system yielded Dice similarity coefficients of 91.6% ± 10.0% between automatic and manual segmentations, and a mean POI estimation error of 0.3% for the whole lung on the validation dataset. Moreover, compared with the cases with fully manual delineation that often takes hours, the proposed HIMI training strategy can dramatically reduce the delineation time to 4 min after three iterations of model updating. Besides, the best accuracy of severity prediction was 73.4% ± 1.3% when the mass of infection (MOI) of multiple lung lobes and bronchopulmonary segments were used as features for severity prediction, indicating the potential clinical application of our quantification technique on severity prediction.Conclusions: A DL‐based segmentation system has been developed to automatically segment and quantify infection regions in CT scans of COVID‐19 patients. Quantitative evaluation indicated high accuracy in automatic infection delineation and severity prediction.

Purpose: Neuroimaging elucidations have shown structural and functional brain alterations in HIV-infected (HIV+) individuals when compared to HIV-negative (HIV–) controls. However, HIV− groups used in previous studies were not specifically considered for sexual orientation, which also affects the brain structures and functions. The current study aimed to characterize the brain alterations associated with HIV infection while controlling for sexual orientation.Methods: Forty-three HIV+ and 40 HIV– homosexual men (HoM) were recruited and underwent resting-state MRI scanning. Group differences in gray matter volume (GMV) were assessed using a voxel-based morphometry analysis. Brain regions with the altered GMV in the HIV+ HoM group were then taken as regions of interest in a seed-based analysis to identify altered functional connectivity. Furthermore, the amplitude of low-frequency fluctuation (ALFF) and regional homogeneity values were compared between the two groups to evaluate the HIV-associated functional abnormalities in local brain regions.Results: HIV+ HoM showed significantly increased GMV in the bilateral parahippocampal gyrus and amygdala, and decreased GMV in the right inferior cerebellum, compared with the HIV– HoM. The brain regions with increased GMV were hyper-connected with the left superior cerebellum, right lingual gyrus, and left precuneus in the HIV+ HoM. Moreover, the ALFF values of the right fusiform gyrus, and left parahippocampal gyrus were increased in the HIV+ HoM. The regional homogeneity values of the right anterior cingulate and paracingulate gyri, and left superior cerebellum were decreased in the HIV+ HoM.Conclusion: When the study population was restricted to HoM, HIV+ individuals exhibited structural alterations in the limbic system and cerebellum, and functional abnormalities in the limbic, cerebellum, and visual network. These findings complement the existing knowledge on the HIV-associated neurocognitive impairment from the previous neuroimaging studies by controlling for the potential confounding factor, sexual orientation. Future studies on brain alternations with the exclusion of related factors like sexual orientation are needed to understand the impact of HIV infection on neurocognitive function more accurately.

Background: Cumulative CT radiation damage was positively correlated with increased tumor risks. Although it has recently been known that non-radiation MRI is alternative for pulmonary imaging. There is little known about the value of MRI T1-mapping in the diagnosis of pulmonary nodules. This article aimed to investigate the value of native T1-mapping-based radiomics features in differential diagnosis of pulmonary lesions. Methods: 73 patients underwent 3 T-MRI examination in this prospective study. The 99 pulmonary lesions on native T1-mapping images were segmented twice by one radiologist at indicated time points utilizing the in-house semi-automated software, followed by extraction of radiomics features. The inter-class correlation coefficient (ICC) was used for analyzing intra-observer’s agreement. Dimensionality reduction and feature selection were performed via univariate analysis, and least absolute shrinkage and selection operator (LASSO) analysis. Then, the binary logical regression (LR), support vector machine (SVM) and decision tree classifiers with the input of optimal features were selected for differentiating malignant from benign lesions. The receiver operative characteristics (ROC) curve, area under the curve (AUC), sensitivity, specificity and accuracy were calculated. Z-test was used to compare differences among AUCs. Results: 107 features were obtained, of them, 19.5% (n = 21) had relatively good reliability (ICC ≥ 0.6). The remained 5 features (3 GLCM, 1 GLSZM and 1 shape features) by dimensionality reduction were useful. The AUC of LR was 0.82(95%CI: 0.67–0.98), with sensitivity, specificity and accuracy of 70%, 85% and 80%. The AUC of SVM was 0.82(95%CI: 0.67–0.98), with sensitivity, specificity and accuracy of 70, 85 and 80%. The AUC of decision tree was 0.69(95%CI: 0.49–0.87), with sensitivity, specificity and accuracy of 50, 85 and 73.3%. Conclusions: The LR and SVM models using native T1-mapping-based radiomics features can differentiate pulmonary malignant from benign lesions, especially for uncertain nodules requiring long-term follow-ups.

Objective: Previous studies on HIV-infected (HIV+) individuals have revealed brain structural alterations underlying HIV-associated neurocognitive disorders. Most studies have adopted the widely used voxel-based morphological analysis of T1-weighted images or tracked-based analysis of diffusion tensor images. In this study, we investigated the HIV-related morphological changes using the deformation-based morphometry (DBM) analysis of T1-weighted images, which is another useful tool with high regional sensitivity.Materials and Methods: A total of 157 HIV+ (34.7 ± 8.5 years old) and 110 age-matched HIV-uninfected (HIV-) (33.7 ± 10.1 years old) men were recruited. All participants underwent neurocognitive assessments and brain scans, including high-resolution structural imaging and resting-state functional imaging. Structural alterations in HIV+ individuals were analyzed using DBM. Functional brain networks connected to the deformed regions were further investigated in a seed-based connectivity analysis. The correlations between imaging and cognitive or clinical measures were examined.Results: The DBM analysis revealed decreased values (i.e., tissue atrophy) in the bilateral frontal regions in the HIV+ group, including bilateral superior frontal gyrus, left middle frontal gyrus, and their neighboring white matter tract, superior corona radiata. The functional connectivity between the right superior frontal gyrus and the right inferior temporal region was enhanced in the HIV+ group, the connectivity strength of which was significantly correlated with the global deficit scores (r = 0.214, P = 0.034), and deficits in learning (r = 0.246, P = 0.014) and recall (r = 0.218, P = 0.031). Increased DBM indexes (i.e., tissue enlargement) of the right cerebellum were also observed in the HIV+ group.Conclusion: The current study revealed both gray and white matter volume changes in frontal regions and cerebellum in HIV+ individuals using DBM, complementing previous voxel-based morphological studies. Structural alterations were not limited to the local regions but were accompanied by disrupted functional connectivity between them and other relevant regions. Disruptions in neural networks were associated with cognitive performance, which may be related to HIV-associated neurocognitive disorders.