Xia Zhang

Xia Zhang

Auto-generated profile, based on publicly available information

Xia Zhang

Department of Ultrasound Medicine The First Affiliated Hospital of Wannan Medical College Wuhu City Anhui Province China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 August 2023 in Quantitative Imaging in Medicine and Surgery
Verified
Journal Article
Open access
PDF file
WWWei Wei
Wei Wei
QMQiang Ma
Qiang Ma
HFHuijun Feng
Huijun Feng
TWTianjun Wei
Tianjun Wei
FJFeng Jiang
Feng Jiang
XZXia Zhang
Xia Zhang
Background: This study investigates whether deep learning radiomics of conventional ultrasound images can predict preoperative axillary lymph node (ALN) status in patients with clinical stages T1–2 breast cancer (BC). Methods: This study retrospectively analyzed the preoperative ultrasound data of 892 patients with BC, who were classified into training (n=535), validation (n=178), and test (n=179) cohorts. Linear combinations of the selected features were weighted by their coefficients to obtain the predicted score. Then, deep learning radiomic features were extracted from the ultrasound images to evaluate the ALN status. Receiver-operating characteristic curves were drawn, followed by the calculation of the area under the curve (AUC) to assess the accuracy of the prediction model in predicting axillary lymph node metastasis (ALNM) in the three cohorts. Results: Deep learning radiomics combined with radiomics and clinical parameters was the optimal diagnostic predictor of the ALN status in the absence and presence of ALNM, with the AUC of 0.920 (95% confidence interval: 0.872 and 0.968, respectively). Additionally, this combination could also differentiate low-load ALNM [N + (1–2)] from heavy-load ALNM with ≥3 positive nodes [N + (≥3)] in the test cohort, with the AUC of 0.819 (95% confidence interval: 0.568 and 1.00, respectively). Conclusions: Conclusively, deep learning radiomics of ultrasound images is a non-invasive approach to predicting preoperative ALNM in BC.

3 July 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
QMQiang Ma
Qiang Ma
CDCaiyun Ding
Caiyun Ding
WWWei Wei
Wei Wei
CSChencheng Su
Chencheng Su
BLBozheng Li
Bozheng Li
JWJingyi Wu
Jingyi Wu
The outcomes of patients with sepsis are influenced by the contractile function of the right ventricle (RV), but the impact of cardiopulmonary interaction in ICU-mortality of sepsis patients remains unclear. This study aims to investigate the ICU-mortality impact of right ventricular-pulmonary artery (RV-PA) coupling in patients with sepsis. We employed echocardiography to assess patients with sepsis within the initial 24 h of their admission to the ICU. RV-PA coupling was evaluated using the tricuspid annular plane systolic excursion (TAPSE) to pulmonary artery systolic pressure (PASP) ratio. A total of 92 subjects were enrolled, with 55 survivors and 37 non-survivors. TAPSE/PASP ratio assessed mortality with an area under the curve (AUC) of 0.766 (95% CI 0.670–0.862) and the optimal cutoff value was 0.495 mm/mmHg. We constructed a nomogram depicting the TAPSE/PASP in conjunction with IL-6 and Lac for the joint prediction of sepsis prognosis, and demonstrated the highest predictive capability (AUC = 0.878, 95% CI 0.809–0.948). In conclusion, the TAPSE/PASP ratio demonstrated prognostic value for ICU mortality in sepsis patients. The nomogram, which combines the TAPSE/PASP, IL-6, and LAC, demonstrated enhanced predictive efficacy for the prognosis of sepsis patients.

9 August 2024 in Frontiers in Oncology
Verified
Journal Article
Open access
PDF file
WWWei Wei
Wei Wei
JXJingya Xu
Jingya Xu
FXFei Xia
Fei Xia
JLJun Liu
Jun Liu
ZZZekai Zhang
Zekai Zhang
XZXia Zhang
Xia Zhang
Objectives: To construct deep learning-assisted diagnosis models based on automatic segmentation of ultrasound images to facilitate radiologists in differentiating benign and malignant parotid tumors.Methods: A total of 582 patients histopathologically diagnosed with PGTs were retrospectively recruited from 4 centers, and their data were collected for analysis. The radiomics features of six deep learning models (ResNet18, Inception_v3 etc) were analyzed based on the ultrasound images that were obtained under the best automatic segmentation model (Deeplabv3, UNet++, and UNet). The performance of three physicians was compared when the optimal model was used and not. The Net Reclassification Index (NRI) and Integrated Discrimination Improvement (IDI) were utilized to evaluate the clinical benefit of the optimal model.Results: The Deeplabv3 model performed optimally in terms of automatic segmentation. The ResNet18 deep learning model had the best prediction performance, with an area under the receiver-operating characteristic curve of 0.808 (0.694−0.923), 0.809 (0.712−0.906), and 0.812 (0.680−0.944) in the internal test set and external test sets 1 and 2, respectively. Meanwhile, the optimal model-assisted clinical and overall benefits were markedly enhanced for two out of three radiologists (in internal validation set, NRI: 0.259 and 0.213 [p = 0.002 and 0.017], IDI: 0.284 and 0.201 [p = 0.005 and 0.043], respectively; in external test set 1, NRI: 0.183 and 0.161 [p = 0.019 and 0.008], IDI: 0.205 and 0.184 [p = 0.031 and 0.045], respectively; in external test set 2, NRI: 0.297 and 0.297 [p = 0.038 and 0.047], IDI: 0.332 and 0.294 [p = 0.031 and 0.041], respectively).Conclusions: The deep learning model constructed for automatic segmentation of ultrasound images can improve the diagnostic performance of radiologists for PGTs.

4 January 2018 in Journal of Surgical Research
Verified
Journal Article
Closed access
PDF file
JWJingyi Wu
Jingyi Wu
ZWZhen Wang
Zhen Wang
TWTao Wang
Tao Wang
TYTao Yu
Tao Yu
JYJing Yuan
Jing Yuan
XZXia Zhang
Xia Zhang

26 September 2021 in World Journal of Clinical Cases
Verified
Journal Article
Open access
BPBo Pang
Bo Pang
JPJing-Jing Pan
Jing-Jing Pan
QLQin Li
Qin Li
XZXia Zhang
Xia Zhang
Prenatal examination is an important measure for the screening and diagnosis of fetal malformations. To investigate the accuracy of ultrasonography in the diagnosis of fetal central nervous system (CNS) malformations. One hundred and thirteen pregnant women suspected of having fetal CNS malformations were examined at our hospital from December 2018 to October 2020 using two-dimensional ultrasonography and three-dimensional ultrasonography, respectively. According to the pathological results, there were 79 cases of CNS malformations and 34 cases of non-CNS malformations among the 113 pregnant women suspected of having fetal CNS malformation. Fifty-one cases of CNS malfor mation and 26 cases of non-CNS malformation were detected by two-dimensional ultrasonography, and 73 cases of CNS malformation and 30 cases of non-CNS malformation were detected by three-dimensional ultrasonography. The diagnostic sensitivity (92.41%) and accuracy (91.15%) of three-dimensional ultrasonography were higher than those of two-dimensional ultrasonography (64.56% and 68.14%, respectively) (P = 0.000). The specificity of three-dimensional ultrasonography (88.24%) was higher than that of two-dimensional ultrasonography (76.47%); however, the difference was not significant (P = 0.203). Three-dimensional ultrasonography has high application value in the diagnosis of fetal CNS malformations. In addition, the image quality is clear, and the diagnostic sensitivity and accuracy are high.

12 September 2024 in Annals of Noninvasive Electrocardiology
Verified
Journal Article
Open access
TYTianhui Yan
Tianhui Yan
QMQiang Ma
Qiang Ma
XLXin Li
Xin Li
QSQing Shen
Qing Shen
XLXiuxiu Liu
Xiuxiu Liu
XZXia Zhang
Xia Zhang
Objective: This study aims to assess the tricuspid annular plane systolic excursion (TAPSE)/PASP ratio as a potential indicator for predicting the probability of developing pulmonary arterial hypertension (PAH) in hyperthyroidism patients. A nomogram model will be developed based on our findings, as well as the receiver operating characteristic (ROC) curve.Methods: The study involved 166 hyperthyroid patients treated at Yijishan Hospital, and the period covered August 2021 to August 2022. Patients were divided into two groups according to pulmonary artery systolic pressure ≥35 mmHg. Univariate and multivariate logistic analyses were performed on the two groups' demographic and laboratory data to identify potential diagnostic markers. These parameters were evaluated using ROC curves to determine their precision in forecasting PAH. The findings were validated by plotting a calibration curve based on a line chart model.Results: In the study, eventually, 80 patients were enrolled: 30 in the PAH group and 50 in the No PAH group. Multipleistic regression analysis predicted the occurrence risk of developing PAH. When paired with other conventional echocardiographic parameters (such as TAPSE, MPI, and SV) and serological markers (such as FT3 and FT4), the developed model demonstrated outstanding predictive performance with an area under the ROC curve of 0.985, a Youden index of 0.971, a sensitivity of 100%, and a specificity of 97.1%.Conclusions: The nomogram model constructed by combining the TAPSE/PASP ratio with FT3 and FT4 serum markers, as well as conventional ultrasound parameters SV and MPI in hyperthyroidism patients, demonstrates robust discriminatory ability and consistency.