Yanling Zhang

Yanling Zhang

Auto-generated profile, based on publicly available information

Yanling Zhang

Department of Ultrasound, Third affiliated hospital, Sun Yat-sen University, Guangzhou, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
9 December 2022 in Journal of Applied Clinical Medical Physics
Verified
Journal Article
Open access
SZShuai Zhang
Shuai Zhang
MLMei Liao
Mei Liao
JWJing Wang
Jing Wang
YZYongyi Zhu
Yongyi Zhu
YZYanling Zhang
Yanling Zhang
WWWei Wang
Wei Wang
Background: Breast ultrasound (BUS) imaging is one of the most prevalent approaches for the detection of breast cancers. Tumor segmentation of BUS images can facilitate doctors in localizing tumors and is a necessary step for computer‐aided diagnosis systems. While the majority of clinical BUS scans are normal ones without tumors, segmentation approaches such as U‐Net often predict mass regions for these images. Such false‐positive problem becomes serious if a fully automatic artificial intelligence system is used for routine screening.Methods: In this study, we proposed a novel model which is more suitable for routine BUS screening. The model contains a classification branch that determines whether the image is normal or with tumors, and a segmentation branch that outlines tumors. Two branches share the same encoder network. We also built a new dataset that contains 1600 BUS images from 625 patients for training and a testing dataset with 130 images from 120 patients for testing. The dataset is the largest one with pixel‐wise masks manually segmented by experienced radiologists. Our code is available at https://github.com/szhangNJU/BUS_segmentation.Results: The area under the receiver operating characteristic curve (AUC) for classifying images into normal/abnormal categories was 0.991. The dice similarity coefficient (DSC) for segmentation of mass regions was 0.898, better than the state‐of‐the‐art models. Testing on an external dataset gave a similar performance, demonstrating a good transferability of our model. Moreover, we simulated the use of the model in actual clinic practice by processing videos recorded during BUS scans; the model gave very low false‐positive predictions on normal images without sacrificing sensitivities for images with tumors.Conclusions: Our model achieved better segmentation performance than the state‐of‐the‐art models and showed a good transferability on an external test set. The proposed deep learning architecture holds potential for use in fully automatic BUS health screening.

16 April 2019 in Cardiovascular Diabetology
Verified
Journal Article
Open access
PDF file
XTXixiang Tang
Xixiang Tang
JZJunlin Zhong
Junlin Zhong
HZHui Zhang
Hui Zhang
YLYanting Luo
Yanting Luo
兴刘兴 刘
兴 刘
YCYanming Chen
Yanming Chen
Background: To investigate the effect of visit-to-visit fasting plasma glucose (FPG) variability on the left cardiac structure and function in patients with type 2 diabetes mellitus (T2DM). Methods: In this prospective cohort study, 455 T2DM patients were included and follow-up for a median of 4.7 years. FPG measured on every hospital visit was collected. FPG variability was calculated by its coefficient of variation (CV-FPG). Left cardiac structure and function were assessed using echocardiography at baseline and after follow-up. Multivariable linear regression analyses were used to estimate the effect of FPG variability on the annualized changes in left cardiac structure and function. Subgroup analysis stratified by mean HbA1c levels (< 7% and ≥ 7%) were also performed. Result: In multivariable regression analyses, CV-FPG was independently associated with the annualized changes in left ventricle (β = 0.137; P = 0.031), interventricular septum (β = 0.215; P = 0.001), left ventricular posterior wall thickness (β = 0.129; P = 0.048), left ventricular mass index (β = 0.227; P < 0.001), and left ventricular ejection fraction (β = − 0.132; P = 0.030). After additionally stratified by mean HbA1c levels, CV-FPG was still independently associated with the annualized changes in the above parameters in patients with HbA1c ≥ 7%, while not in patients with HbA1c < 7%. Conclusions: Visit-to-visit variability in FPG could be a novel risk factor for the long-term adverse changes in left cardiac structure and systolic function in patients with type 2 diabetes. Trial registration ClinicalTrials.gov (NCT02587741), October 27, 2015, retrospectively registered.

1 May 2020 in RSC Advances
Verified
Journal Article
Open access
PDF file
WLWenqiang Li
Wenqiang Li
AHAnfei Huang
Anfei Huang
YZYanheng Zhong
Yanheng Zhong
LHLin Huang
Lin Huang
JYJing Yang
Jing Yang
GFGuo Fu
Guo Fu
The reconstruction of peripheral nerves has lately received great attention as many patients suffer from peripheral nerve injury every year around the world. However, the damage to human nerve cells has different degrees of irreversibility due to a slow growth speed and low adhesion with the surrounding tissues. In an effort to overcome this challenge, we applied novel laminin (LN)-modified thiolated gellan gum (TGG) and loaded the nerve growth factor (NGF) as a tissue engineering scaffold for facilitating neuronal stem cell proliferation via a synergy effect for the ERK–MAPK pathway. TGG was characterized by 1H NMR spectroscopy and scanning electron microscopy, and its rheological behavior was also studied. The NGF release curve fitted the Korsmeyer–Peppas model and belonged to a Fickian diffusion-controlled release mechanism. The neuronal stem cells from newborn SD rats could adhere tightly and proliferate at a relatively rapid speed, showing excellent biocompatibility and the ability to promote growth in the modified TGG. LN and NGF could decrease the apoptosis effects of neuronal stem cells, as shown via the flow cytometry results. In a three-dimensional culture environment, LN and NGF could facilitate neuronal stem cells to differentiate into neurons, as proved by immunofluorescence, q-PCR, and western blot analyses. Therefore, the rational design of the TGG gel loaded with NGF has promising applications in the reconstruction of peripheral nerves.

1 January 2007 in American Journal of Ophthalmology
Verified
Journal Article
Closed access
SCSuqin Chen
Suqin Chen
YZYanling Zhang
Yanling Zhang
Yiming WangYiming Wang
Yiming Wang
WLWeili Li
Weili Li
SHShuang Huang
Shuang Huang
ZLZuguo Liu
Zuguo Liu

13 April 2017 in Experimental and Therapeutic Medicine
Verified
Journal Article
Open access
PDF file
HCHui Cheng
Hui Cheng
YZYanling Zhang
Yanling Zhang
BZBei Zhang
Bei Zhang
JCJie Cheng
Jie Cheng
WWWeiqi Wang
Weiqi Wang
YLYanyu Li
Yanyu Li
In this study, we investigated the rejection of the synthetic patch and human tissues in the host. We observed the growth of adipose-derived stem cells (ADSCs) cultured with polypropylene mesh in vitro. The results of flow cytometry showed that the expression of CD44, CD73, CD90, CD45, CD14 and CD34 was 98.54, 95.32, 98.49, 1.21, 3.01 and 2.14%, respectively. ADSCs were isolated from rabbit subcutaneous adipose tissue after collagenase digestion, filtration and centrifugation. The ADSCs of passage 3 were seeded onto the polypropylene mesh scaffolds. New Zealand White female breeder rabbits were implanted with polypropylene mesh, ADSC-fixed polypropylene mesh in the abdomen. After 4 weeks, adhesion was performed and the erosion of the mesh was evaluated. It was found that polypropylene mesh, ADSC-fixed polypropylene mesh all had different degrees of corrosion, and adhesion, but polypropylene mesh was more corroded. ADSC-fixed polypropylene mesh induced a milder chronic inflammation response compared with polypropylene, had significantly lower scores for inflammation (t=11.083), and had significantly higher scores for neovascularization (t=14.362) and fibroblastic proliferation (t=15.979). The relative amount of VEGF mRNA was significantly lower for ADSC-fixed polypropylene compared with the other polypropylene meshes (t=94.6). In conclusion, polypropylene mesh scaffold with ADSCs exhibit excellent cellular compatibility and are promising in clinical practice.

5 February 2022 in Journal of NeuroEngineering and Rehabilitation
Verified
Journal Article
Open access
PDF file
JCJunyan Cao
Junyan Cao
YXYang Xiao
Yang Xiao
WQWeihong Qiu
Weihong Qiu
YZYanling Zhang
Yanling Zhang
ZDZulin Dou
Zulin Dou
ZCZhaocong Chen
Zhaocong Chen
Background: To explore the feasibility of corrected slack angle acquired from two-dimensional shear wave elastography (2D-SWE) for quantitating the spasticity of medial gastrocnemius (MG) in stroke patients. Methods: Consecutive stroke patients with spastic MG and matched healthy controls were recruited. Intra- and interobserver reliability of 2D-SWE measurement were evaluated, and the correlation between corrected slack angle and modified Ashworth scale (MAS) score was examined. The corrected slack angle before and after botulinum toxin A (BoNT-A) injection was compared and its diagnostic performance in classifying the severity of spasticity were assessed with receiver operating characteristic (ROC) curve analysis. Results: The intra- (0.791 95% CI 0.432–0.932) and interobserver (0.751 95% CI 0.382–0.916) reliability of slack angle acquired with 2D-SWE were good. Significant correlation was found between corrected slack angle and MAS score (R = − 0.849, p < 0.001). The corrected slack angle increased after BoNT-A injection. The cutoff value of MAS ≥ 3 had the highest sensitivity (100%) and specificity (93.33%). The positive predictive value (PPV) for classification of MAS ≥ 1+ and the negative predictive value (NPV) for classification of MAS ≥ 3 were greater than 90%. Conclusion: 2D-SWE was a reliable method to quantitate the post-stroke spasticity. The corrected slack angle had advantage in classifying the severity of spasticity, especially in early identification of mild spasticity and confirmation of severe spasticity.