BACKGROUND: Early warning of severe coronavirus disease 2019 (COVID?19) pneumonia on admission is critical for reducing mortality. PURPOSE: The purpose of this study was to identify the risk factors for predicting sev...
BACKGROUND: Early warning of severe coronavirus disease 2019 (COVID?19) pneumonia on admission is critical for reducing mortality. PURPOSE: The purpose of this study was to identify the risk factors for predicting severe COVID?19 pneumonia on admission. MATERIALS AND METHODS: Computed tomography (CT) scans on admission and initial clinical data were collected from 213 patients with COVID?19 pneumonia. Semi?quantitative CT scoring was performed, multiplying the CT patterns by their extent. CT patterns were graded on a four?point scale: 0, normal attenuation;1, ground?glass opacities (GGOs);2, mixed patterns of GGO and consolidation;and 3, consolidation. The extent of patterns was visually estimated as the percentage (to the nearest 10％) of the affected pulmonary lobe. Inter?observer agreement was evaluated using the inter?class correlation coefficient. CT scores and clinical data were compared between severe and nonsevere patients using parametric and nonparametric statistics, as appropriate. The least absolute shrinkage and selection operator (LASSO) with 10?fold cross?validation and logistic regression was used to select the risk factors and construct a predictive model. RESULTS: Age, respiratory rate, hypertension, procalcitonin, D?dimer, lactate dehydrogenase, high?sensitivity C?reactive protein (hs?CRP), cystatin C, brain natriuretic peptide (pro?BNP), and CT score were higher in severe COVID?19 infection. LASSO analysis revealed that the CT score coupled with hs?CRP was optimal for predicting progression to severe pneumonia. The areas under the curves for validation and testing data were 0.85 and 0.82, respectively, with sensitivity of 89.5％ and 75.0％, specificity of 75.4％ and 98.1％, and accuracy of 77.2％ and 95.3％. CONCLUSION: The CT score combined with hs?CRP on admission predicted severe COVID?19 pneumonia.
The performance of face recognition is significantly affected by variations of illumination, pose, and facial expression in the image. To solve this problem, a novel method for face feature extraction and recognition ...
详细信息
The performance of face recognition is significantly affected by variations of illumination, pose, and facial expression in the image. To solve this problem, a novel method for face feature extraction and recognition is proposed, which is based on a compact local face descriptor (CLFD). Firstly, steerable magnitude maps (SMM) are obtained by computing the convolution of the original face image with steerable filters. Then, original face image is represented by a histogram sequence that concatenates all LBP features obtained from each SMM respectively. PCA dimension reduction is also adopted to reduce length of the feature vectors. Besides, statistical distance is applied to calculate the similarity between two face images. Experimental results demonstrate that the proposed face recognition method is highly robust to illumination and expression variations. Moreover, compared with other algorithms based on Gabor, our method has lower computational cost and higher recognition rate.
A new objective quality metric without reference for color fused image is proposed in this paper. This measurement combines the color similarity with the structural similarity between the source images and the fused i...
详细信息
ISBN:
(纸本)9781424442133
A new objective quality metric without reference for color fused image is proposed in this paper. This measurement combines the color similarity with the structural similarity between the source images and the fused image. The color similarity is directly computed in RGB color space and is compose of the hue and saturation similarity and intensity similarity. The value of image quality is obtained by weighted average of the color similar coefficients between the source images and the fused image. The weighing factor is decided by the structural similarity index between the source images and the fused image. Compared to other measures, this quality metric is easier to compute. Experiments show that the metric is consistent with the subjective evaluations and outperforms other objective evaluation metrics.
An automatic defogging method based on the dichromatic atmospheric scattering model is presented in this paper to avoid the inconvenience by using interactive method. At first, the vanishing point is detected automati...
详细信息
An automatic defogging method based on the dichromatic atmospheric scattering model is presented in this paper to avoid the inconvenience by using interactive method. At first, the vanishing point is detected automatically using the Hough transform. The pixel value at the vanishing point is a threshold to segment the sky region. The final defogged image is obtained by using the depth heuristics. The result of many experiments shows that this method prior to the histogram equalization and multi-scale Retinex in the restraining noise and producing good color rendition.
A novel fusion method is proposed for image sequence which based on the non-Gaussian statistical modeling of wavelet coefficients. Firstly, the source images are decomposed by dual tree complex wavelet transform (DT-C...
详细信息
A novel fusion method is proposed for image sequence which based on the non-Gaussian statistical modeling of wavelet coefficients. Firstly, the source images are decomposed by dual tree complex wavelet transform (DT-CWT) respectively. Then, the wavelet coefficients are modeled using the generalized Gaussian distribution (GGD). Saliency measure, the weighted coefficient, is calculated by estimating distribution parameters. The pair of coefficients is fused through weighted average. Finally, the fused coefficients are reconstructed into a single fused image. The quality of the fused image is evaluated by three metric: entropy, mutual information and QAB/*** experimental results demonstrate that performance of the proposed method is prior to other two fusion approaches for infrared and visible dynamic image sequence.
暂无评论