Yankai Meng

Dr. Yankai Meng

orcid

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
27 February 2022 in Journal of Cancer Research and Clinical Oncology
Verified
Journal Article
Closed access
PDF file
CRCheng-Wei Ruan
Cheng-Wei Ruan
YMYankai Meng
Yankai Meng
HSHu Song
Hu Song

19 May 2022 in European Journal of Radiology
Verified
Journal Article
Closed access
MYMiao Yu
Miao Yu
YMYankai Meng
Yankai Meng
HZHe Zhang
He Zhang
WWWei Wang
Wei Wang
SQShenman Qiu
Shenman Qiu
KXKai Xu
Kai Xu

1 June 2020 in European Journal of Radiology
Verified
Journal Article
Closed access
PDPeipei Dou
Peipei Dou
SZShuai Zhang
Shuai Zhang
CWChen Wang
Chen Wang
LCLulu Cai
Lulu Cai
ZLZhongxiao Liu
Zhongxiao Liu
KXKai Xu
Kai Xu


1 June 2025 in Translational Pediatrics
Verified
Journal Article
Open access
PDF file
XLXiaohan Liu
Xiaohan Liu
WXWenbei Xu
Wenbei Xu
LMLingjian Meng
Lingjian Meng
JLJuan Long
Juan Long
XSXiaonan Sun
Xiaonan Sun
YMYankai Meng
Yankai Meng
Background: Mycoplasma pneumoniae pneumonia (MPP) is endemic in China, while Mycoplasma co-infection with other pathogens (Co-MPP) linked to severe outcomes. Despite radiomics and machine learning potential in pneumonia, pediatric Co-MPP differentiation remains underexplored. This study aimed to bridge this gap by evaluating machine learning models, particularly radiomics features derived from high-resolution computed tomography (HRCT) scans, to differentiate between MPP and Co-MPP, and to compare their predictive performance with traditional clinical models. Methods: We conducted a retrospective analysis of hospitalized pediatric pneumonia patients from June to December 2023 at Affiliated Hospital of Xuzhou Medical University. Chest computed tomography (CT) scans were performed using a multi-slice CT scanner with over 64 detectors. Fluorescent quantitative polymerase chain reaction (PCR) was used to detect 14 pathogens in bronchoalveolar lavage (BAL) fluid. The most recent laboratory results prior to BAL were included in multifactorial logistic regression (LR) analysis, selecting variables with P<0.05 for constructing the clinical model. The largest cross-section of the lesion was selected, and image segmentation was performed using ITK-SNAP software. Radiomics features were extracted with Pyradomics. Features were filtered using t-tests, Mann-Whitney U tests, and Spearman rank correlation coefficients. The least absolute shrinkage and selection operator (LASSO) regression and ten-fold cross-validation were used for feature selection and to construct the radiomics model, optimizing the dimensionality of the dataset. Eight different machine learning models [LR, support vector machine (SVM), K-nearest neighbor (KNN), RandomForest, ExtraTrees, eXtreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP)] were trained with the selected features, with five-fold cross-validation yielding the final radiomics model. The clinical and radiomics models were combined to create a nomogram model. Data analysis was performed using R software and SPSS 26.0. Results: A total of 124 cases of MPP and children with Co-MPP were included. The extracted radiomics features consisted of first-order signal intensity features (n=360), morphological features (n=14), and texture features (n=1,460). LASSO regression and ten-fold cross-validation identified 23 non-zero correlation coefficient features for constructing Radscore. The LR model demonstrated superior predictive performance for Co-MPP in the validation cohort, with an area under the curve (AUC) of 0.951, sensitivity of 0.778, and specificity of 0.875. The nomogram model combining clinical and radiomics labels significantly outperformed the clinical model (P=0.004). Calibration curve analysis indicated that the nomogram model exhibited the best agreement with actual values. Both the radiomics and nomogram models provided greater clinical net benefits compared to the clinical model. Conclusions: The radiomics model trained using machine learning effectively predicts Co-MPP in children, while the combined clinical and radiomics nomogram model offers the best predictive performance.

1 July 2020 in Translational Cancer Research
Verified
Journal Article
Open access
PDF file
PDPeipei Dou
Peipei Dou
ZLZhongxiao Liu
Zhongxiao Liu
LXLixiang Xie
Lixiang Xie
CMChong Meng
Chong Meng
CWChen Wang
Chen Wang
KXKai Xu
Kai Xu
Background: To investigate the predictive value of energy spectral CT parameters for Ki-67 expression in lung cancer. Methods: In this retrospective analysis, 27 primary lung cancer patients confirmed by pathological examination were enrolled between December 2018 and February 2019. All patients underwent baseline arterial phase (AP) and venous phase (VP) energy spectral CT scanning followed by surgery in our institution. The iodine concentration (IC), normalized iodine concentration (NIC) and the slope of 40-80 keV energy spectrum curve (λHU) were derived from dual-energy virtual imaging on a Siemens postprocessed workstation. Immunohistochemical examination was performed to analyze Ki-67 expression. The ROC curves were used for predicting the performance of energy spectral parameters for Ki-67 expression. Results: The tumors appeared larger in Ki-67 high expression group than the low expression group (P=0.046). The energy spectral parameters were higher in venous phase when compared to arterial phase, but only the venous phase NIC (vpNIC) was significantly different from that of the arterial phase NIC (apNIC) (P<0.01). There are significant differences in high and low Ki-67 expression groups for vpNIC and venous λHU (vpλHU), (P=0.033 and 0.037 for vpNIC and vpλHU, respectively). vpNIC ROC analysis showed borderline P value (P=0.056) with an AUC, sensitivity (SE), specificity (SP) and cut-off value (0.717, 92.86, 61.54 and ≤0.347), respectively. The AUC, SE, SP and cut-off value of vpλHU were 0.698, 92.86, 53.85 and ≤2.407, respectively. Conclusions: The energy spectral parameters (NIC and λHU) of venous phase might be used for predicting Ki-67 stratification. The venous phase energy spectral parameters were higher than the arterial phase. Furthermore, low expression Ki-67 group showed association with higher IC, NIC and λHU than high expression group.