Pan Zhang

Dr. Pan Zhang

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2019 in Clinical Laboratory
Verified
Journal Article
Closed access
HZHai Zhang
Hai Zhang
YGYan Ge
Yan Ge
Hong WangHong Wang
Hong Wang
QZQian Zhang
Qian Zhang
WLWen Li
Wen Li
PZPan Zhang
Pan Zhang
The pneumonia severity index (PSI) scoring system is one of the tools used to evaluate and predict the prognosis of patients with community-acquired pneumonia (CAP). Although PSI has been widely used in clinical studies of pneumonia, it is still rare to combine it with blood indexes to predict the prognosis of pneumonia. Neutrophil-to-lymphocyte ratio (NLR) is a promising candidate predictor of mortality in CAP patients. The aim of this study was to investigate the efficacy of pneumonia severity index combined with NLR in predicting 30-day mortality in CAP patients. We conducted a retrospective study. We analyzed data on 400 non-immune individuals over the age of 18 in this study. All patients received blood routine measurement and PSI score calculation after admission. The primary outcome measures were mortality and survival in CAP patients. The sensitivity and specificity of PSI score, NLR, and the combination of PSI score and NLR in predicting 30-day mortality were assessed using the subject operating characteristic curve (ROC). Data from 400 patients were analyzed, in which the 30-day mortality was 10.5% (42/400). The AUC of NLR and PSI in predicting 30-day mortality of CAP patients were 0.81 (95% CI 0.73 - 0.89) and 0.94 (95% CI 0.90 - 0.98), respectively, with statistically significant differences (p = 0.00). The sensitivity and specificity of NLR were 0.80 and 0.7, respectively. The sensitivity and specificity of PSI were 0.78 and 0.94, respectively. The combined AUC of the two indicators for predicting death in CAP patients was 0.95 (95% CI 0.92 - 0.99), and the sensitivity and specificity were 0.85 and 0.94, respectively. Neutrophil-to-lymphocyte ratio improves the accuracy and sensitivity of the pneumonia severity index in predicting 30-day mortality of CAP patients.

27 May 2025 in Symmetry
Verified
Journal Article
Open access
PDF file
PZPan Zhang
Pan Zhang
JLJiangtao Luo
Jiangtao Luo
XLXupeng Liang
Xupeng Liang
The homography matrix is essential for perspective transformation across consecutive video frames. While existing methods are effective when the visual content between paired images remains largely unchanged, they rely on substantial, high-quality annotated data for a multi-frame court sequence with content variation. To address this limitation and enhance homography matrix predictions in competitive sports images, a new symmetric stacked neural network model is proposed. The model first leverages the mutual invertibility of bidirectional homography matrices to improve prediction accuracy between paired images. Secondly, by theoretically validating and leveraging the decomposability of the homography matrix, the model significantly reduces the amount of data annotation required for continuous frames within the same shooting direction. Experimental evaluations on datasets for court homography transformations in sports, such as ice hockey, basketball, and handball, show that the proposed symmetric model achieves superior accuracy in predicting homography matrices, even when only one-third of the frames are annotated. Comparisons with seven related methods further highlight the exceptional performance of the proposed model.

1 January 2025 in IET Image Processing
Verified
Journal Article
Open access
PZPan Zhang
Pan Zhang
JLJiangtao Luo
Jiangtao Luo
GXGuoliang Xu
Guoliang Xu
XLXupeng Liang
Xupeng Liang
Homography estimation is a fundamental topic in computer vision, especially in scenarios that require perspective changes for intelligent analysis of sports fields, where it plays a crucial role. Existing methods predict the homography matrix either indirectly by evaluating the 4‐key‐point coordinate deviation in paired images with the same visual content or directly by fine‐tuning the 8 degrees of freedom numerical values that define the matrix. However, these approaches often fail to effectively incorporate coordinate positional information and overlook optimal application scenarios, leading to significant accuracy bottlenecks, particularly for paired images with differing visual content. To address these issues, we propose an approach that integrates both methods in a staged manner, leveraging their respective advantages. In the first stage, positional information is embedded to enhance convolutional computations, replacing serial concatenation in traditional feature fusion with parallel concatenation, while using 4‐key‐point coordinate deviation to predict the macroscopic homography matrix. In the second stage, positional information is further integrated into the input images to refine the direct 8 degrees of freedom numerical predictions, improving matrix fine‐tuning accuracy. Comparative experiments with state‐of‐the‐art methods demonstrate that our approach achieves superior performance, yielding a root mean square error as low as 1.25 and an average corner errror as low as 14.1 in homography transformation of competitive sports image pairs.