Xuefei Deng

Dr. Xuefei Deng


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
1 July 2021 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
YLYu Liu
Yu Liu
QFQiong Fang
Qiong Fang
AJAnhong Jiang
Anhong Jiang
QMQingling Meng
Qingling Meng
GPGang Pang
Gang Pang
XDXuefei Deng
Xuefei Deng

25 September 2024 in Sensors
Verified
Journal Article
Open access
PDF file
LWLuyao Wang
Luyao Wang
CWChengjie Wang
Chengjie Wang
XDXuefei Deng
Xuefei Deng
YLYan Li
Yan Li
WZWang Zhou
Wang Zhou
CCChen yong Chao
Chen yong Chao
This study included 468 patients and aimed to use multimodal ultrasound radiomic technology to predict the malignancy of TI-RADS 4-5 thyroid nodules. First, radiomic features are extracted from conventional two-dimensional ultrasound (transverse ultrasound and longitudinal ultrasound), strain elastography (SE), and shear-wave-imaging (SWE) images. Next, the least absolute shrinkage and selection operator (LASSO) is used to screen out features related to malignant tumors. Finally, a support vector machine (SVM) is used to predict the malignancy of thyroid nodules. The Shapley additive explanation (SHAP) method was used to intuitively analyze the specific contributions of radiomic features to the model’s prediction. Our proposed model has AUCs of 0.971 and 0.856 in the training and testing sets, respectively. Our proposed model has a higher prediction accuracy compared to those of models with other modal combinations. In the external validation set, the AUC of the model is 0.779, which proves that the model has good generalization ability. Moreover, SHAP analysis was used to examine the overall impacts of various radiomic features on model predictions and local explanations for individual patient evaluations. Our proposed multimodal ultrasound radiomic model can effectively integrate different data collected using multiple ultrasound sensors and has good diagnostic performance for TI-RADS 4-5 thyroid nodules.

20 March 2018 in BioMedical Engineering OnLine
Verified
Journal Article
Open access
PDF file
YZYouyu Zhu
Youyu Zhu
FWFeng Wang
Feng Wang
XDXuefei Deng
Xuefei Deng
The physiological and hemodynamic features of bridging veins involve wall shear stress (WSS) of the cerebral venous system. Based on the data of cadavers and computational fluid dynamics software pack, the hemodynamic physical models of bridging veins (BVs) connecting superior sagittal sinus (SSS) were established. A total of 137 BVs formed two clusters along the SSS: anterior group and posterior group. The diameters of the BVs in posterior group were larger than of the anterior group, and the entry angle was smaller. When the diameter of a BV was greater than 1.2 mm, the WSS decreased in the downstream wall of SSS with entry angle less than 105°, and the WSS also decreased in the upstream wall of BVs with entry angle less than 65°. The minimum WSS in BVs was only 63% of that in SSS. Compared with the BVs in anterior group, the minimum WSS in the posterior group was smaller, and the distance from location of the minimum WSS to the dural entrance was longer. The cerebral venous thrombosis occurs more easily when the diameter of a BV is greater than 1.2 mm and the entry angle is less than 65°. The embolus maybe form earlier in the upstream wall of BVs in the posterior part of SSS.

29 July 2024 in Journal of Bone Oncology
Verified
Journal Article
Open access
QZQian Zhang
Qian Zhang
FZFanfan Zhao
Fanfan Zhao
YZYu Zhang
Yu Zhang
MHMan Huang
Man Huang
XGXiangyang Gong
Xiangyang Gong
XDXuefei Deng
Xuefei Deng
Purpose: This study aims to devise and assess an automated measurement framework for lumbar pedicle screw parameters leveraging preoperative computed tomography (CT) scans and a deep learning algorithm. Methods: A deep learning model was constructed employing a dataset comprising 1410 axial preoperative CT images of lumbar pedicles sourced from 282 patients. The model was trained to predict several screw parameters, including the axial angle and width of pedicles, the length of pedicle screw paths, and the interpedicular distance. The mean values of these parameters, as determined by two radiologists and one spinal surgeon, served as the reference standard. Results: The deep learning model achieved high agreement with the reference standard for the axial angle of the left pedicle (ICC = 0.92) and right pedicle (ICC = 0.93), as well as for the length of the left pedicle screw path (ICC = 0.82) and right pedicle (ICC = 0.87). Similarly, high agreement was observed for pedicle width (left ICC = 0.97, right ICC = 0.98) and interpedicular distance (ICC = 0.91). Overall, the model's performance paralleled that of manual determination of lumbar pedicle screw parameters. Conclusion: The developed deep learning-based model demonstrates proficiency in accurately identifying landmarks on preoperative CT scans and autonomously generating parameters relevant to lumbar pedicle screw placement. These findings suggest its potential to offer efficient and precise measurements for clinical applications.

6 February 2016 in BioMedical Engineering OnLine
Verified
Journal Article
Open access
PDF file
CCChen yong Chao
Chen yong Chao
YZYouzhi Zhu
Youzhi Zhu
YZYu Zhang
Yu Zhang
ZZZixuan Zhang
Zixuan Zhang
JLJuan Lian
Juan Lian
Kelvin WongKelvin Wong
Kelvin Wong
Double injection of blood into cisterna magna using a rabbit model results in cerebral vasospasm. An unacceptably high mortality rate tends to limit the application of model. Ultrasound guided puncture can provide real-time imaging guidance for operation. The aim of this paper is to establish a safe and effective rabbit model of cerebral vasospasm after subarachnoid hemorrhage with the assistance of ultrasound medical imaging. A total of 160 New Zealand white rabbits were randomly divided into four groups of 40 each: (1) manual control group, (2) manual model group, (3) ultrasound guided control group, and (4) ultrasound guided model group. The subarachnoid hemorrhage was intentionally caused by double injection of blood into their cisterna magna. Then, basilar artery diameters were measured using magnetic resonance angiography before modeling and 5 days after modeling. The depth of needle entering into cisterna magna was determined during the process of ultrasound guided puncture. The mortality rates in manual control group and model group were 15 and 23 %, respectively. No rabbits were sacrificed in those two ultrasound guided groups. We found that the mortality rate in ultrasound guided groups decreased significantly compared to manual groups. Compared with diameters before modeling, the basilar artery diameters after modeling were significantly lower in manual and ultrasound guided model groups. The vasospasm aggravated and the proportion of severe vasospasms was greater in ultrasound guided model group than that of manual group. In manual model group, no vasospasm was found in 8 % of rabbits. The ultrasound guided double injection of blood into cisterna magna is a safe and effective rabbit model for treatment of cerebral vasospasm.

1 January 2022 in Journal of Clinical Neuroscience
Verified
Journal Article
Open access
XLXiangwei Luo
Xiangwei Luo
YZYouzhi Zhu
Youzhi Zhu
YZYu ZHANG
Yu ZHANG
QZQian Zhang
Qian Zhang
XWXiao Wang
Xiao Wang
XDXuefei Deng
Xuefei Deng
To investigate the effectiveness of dynamic susceptibility contrast-perfusion weighted imaging (DSCPWI) in predicting the progression-free survival (PFS) and chemotherapeutic responsiveness of primary central nervous system lymphoma (PCNSL) before high-dose methotrexate-based chemotherapy. DSCPWI was used to analyze 35 patients who had pathology-confirmed PCNSL. Relative cerebral blood volume (rCBV), relative cerebral blood flow (rCBF), relative mean transit time (rMTT) and relative time to peak (rTTP) were measured on parameter maps. The 5th, 50th and 95th percentile values of every parameter were recorded for enhanced tumors and compared with the parameters of the normally contralateral hemisphere. The ratio of each PWI parameter (rrCBV, rrCBF, rrMTT, rrTTP) was obtained. The influence of parameters on responsiveness and PFS was investigated by univariate Kaplan-Meier analysis and logistic regression and Cox regression for multivariate analysis with a stepwise method. Differences in PWI parameters between the higher and lower vascular endothelial growth factor (VEGF) groups were assessed by the Mann-Whitney U test. Eighteen patients achieved a complete response (CRi) after four initial cycles of chemotherapy. Patients with lower age (p = 0.011), higher VEGF (p < 0.001), higher Karnofsky Performance Status (KPS) (p < 0.001), higher rrCBV(95%) (p < 0.001), higher rrCBV(50%) (p = 0.016), higher rrCBF(95%) (p < 0.001), higher rrCBF(50%) (p = 0.002) showed better PFS; there was difference on age(p = 0.044), KPS (p < 0.001), VEGF (p < 0.001), rrCBV(95%) (p = 0.018), rrCBF(95%) (p = 0.018), rrCBF(50%) (p = 0.007) between CRi and nonCR(i). Multivariate analysis demonstrated that rrCBF(95%) (p = 0.037, 95% confidence interval: 1.065-7.206) was significantly associated with PFS. rCBV and rCBF may be used to assess the responsiveness and prognosis of PCNSL, and rCBF(95%) may be a better predictor. (C) 2021 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).