Yi Huang

Yi Huang


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
9 June 2019 in BioMed Research International
Verified
Journal Article
Open access
PDF file
CHChen Huang
Chen Huang
JTJunru Tian
Junru Tian
CYChenglang Yuan
Chenglang Yuan
PZPing Zeng
Ping Zeng
XHXueping He
Xueping He
BHBingsheng Huang
Bingsheng Huang
Objective. Deep vein thrombosis (DVT) is a disease caused by abnormal blood clots in deep veins. Accurate segmentation of DVT is important to facilitate the diagnosis and treatment. In the current study, we proposed a fully automatic method of DVT delineation based on deep learning (DL) and contrast enhanced magnetic resonance imaging (CE-MRI) images. Methods. 58 patients (25 males; 28~96 years old) with newly diagnosed lower extremity DVT were recruited. CE-MRI was acquired on a 1.5 T system. The ground truth (GT) of DVT lesions was manually contoured. A DL network with an encoder-decoder architecture was designed for DVT segmentation. 8-Fold cross-validation strategy was applied for training and testing. Dice similarity coefficient (DSC) was adopted to evaluate the network’s performance. Results. It took about 1.5s for our CNN model to perform the segmentation task in a slice of MRI image. The mean DSC of 58 patients was 0.74± 0.17 and the median DSC was 0.79. Compared with other DL models, our CNN model achieved better performance in DVT segmentation (0.74± 0.17 versus 0.66±0.15, 0.55±0.20, and 0.57±0.22). Conclusion. Our proposed DL method was effective and fast for fully automatic segmentation of lower extremity DVT.

4 January 2019 in Drug Delivery and Translational Research
Verified
Journal Article
Open access
PDF file
CHchen huang
chen huang
XHXueping He
Xueping He
WLWenfeng Luo
Wenfeng Luo
HCHanwei Chen
Hanwei Chen
YHYi Huang
Yi Huang
To prospectively study the efficacy of different anti-adhesion agents for the prevention of tubal obstruction after recanalization, this trial was approved by our hospital ethics committee. Four hundred patients with fallopian tube obstruction were randomly assigned to four groups. The control group underwent recanalization alone, whereas the other groups were injected with chitosan, Dan-shen, or combined chitosan and Dan-shen after recanalization. The tubal patency rate in all four groups was recorded after 12 day, 3 months, and 12 months. The pregnancy rates were noted after 12 months. The recanalization rates after 1 day in the control, chitosan, Dan-shen, and combined chitosan and Dan-shen groups were 94.1, 97.1, 96.5, and 98.2%, respectively (p = 0.18, p > 0.05). The rates of tubal patency after 3 months were significantly higher in the combined chitosan and Dan-shen (96.5%), chitosan (88%), and Dan-shen (85.2%) groups compared with the control group (73.9%) (p = 0.0001, p < 0.05). The recanalization rate and intrauterine pregnancy rate after 12 months was significantly higher in the combined chitosan and Dan-shen group (93.8 and 63.9%, respectively) compared with the other groups (control 39 and 30.6%, chitosan 78.4 and 46.9%, and Dan-shen 77.3 and 43.3%) (p = 0.0029 and p = 0.0001, p < 0.05). Chitosan, Dan-shen, or a combination of the two compounds could be effective for preventing tubal obstruction after interventional recanalization, possibly increasing the rate of pregnancy in affected women. The combined chitosan and Dan-shen injection has unique advantages in the interventional recanalization of obstructed fallopian tubes.

4 October 2024
Verified
Book Chapter
Closed access
PDF file
XXXiaotong Xie
Xiaotong Xie
YYYufeng Ye
Yufeng Ye
TYTingting Yang
Tingting Yang
BHBin Huang
Bin Huang
BHBingsheng Huang
Bingsheng Huang
YHYi Huang
Yi Huang