Wenjian Qin

Dr. Wenjian Qin


Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

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

Representative Publications

View All Publications
21 June 2018 in BioMed Research International
Verified
Journal Article
Open access
PDF file
TXTing Xiao
Ting Xiao
LLLei Liu
Lei Liu
KLKai Li
Kai Li
WQWenjian Qin
Wenjian Qin
Shaode YuShaode Yu
Shaode Yu
ZLZhicheng Li
Zhicheng Li
This research aims to address the problem of discriminating benign cysts from malignant masses in breast ultrasound (BUS) images based on Convolutional Neural Networks (CNNs). The biopsy-proven benchmarking dataset was built from 1422 patient cases containing a total of 2058 breast ultrasound masses, comprising 1370 benign and 688 malignant lesions. Three transferred models, InceptionV3, ResNet50, and Xception, a CNN model with three convolutional layers (CNN3), and traditional machine learning-based model with hand-crafted features were developed for differentiating benign and malignant tumors from BUS data. Cross-validation results have demonstrated that the transfer learning method outperformed the traditional machine learning model and the CNN3 model, where the transferred InceptionV3 achieved the best performance with an accuracy of 85.13% and an AUC of 0.91. Moreover, classification models based on deep features extracted from the transferred models were also built, where the model with combined features extracted from all three transferred models achieved the best performance with an accuracy of 89.44% and an AUC of 0.93 on an independent test set.

30 December 2018 in Medical Physics
Verified
Journal Article
Closed access
PDF file
YYYixuan Yuan
Yixuan Yuan
WQWenjian Qin
Wenjian Qin
MBMark Buyyounouski
Mark Buyyounouski
BIBulat Ibragimov
Bulat Ibragimov
SHSteve Hancock
Steve Hancock
Lei XingLei Xing
Lei Xing

1 May 2018 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
PDF file
WQWenjian Qin
Wenjian Qin
Jia WuJia Wu
Jia Wu
FHFei Han
Fei Han
YYYixuan Yuan
Yixuan Yuan
WZWei Zhao
Wei Zhao
Lei XingLei Xing
Lei Xing
Segmentation of liver in abdominal computed tomography (CT) is an important step for radiation therapy planning of hepatocellular carcinoma. Practically, a fully automatic segmentation of liver remains challenging because of low soft tissue contrast between liver and its surrounding organs, and its highly deformable shape. The purpose of this work is to develop a novel superpixel-based and boundary sensitive convolutional neural network (SBBS-CNN) pipeline for automated liver segmentation. The entire CT images were first partitioned into superpixel regions, where nearby pixels with similar CT number were aggregated. Secondly, we converted the conventional binary segmentation into a multinomial classification by labeling the superpixels into three classes: interior liver, liver boundary, and non-liver background. By doing this, the boundary region of the liver was explicitly identified and highlighted for the subsequent classification. Thirdly, we computed an entropy-based saliency map for each CT volume, and leveraged this map to guide the sampling of image patches over the superpixels. In this way, more patches were extracted from informative regions (e.g. the liver boundary with irregular changes) and fewer patches were extracted from homogeneous regions. Finally, deep CNN pipeline was built and trained to predict the probability map of the liver boundary. We tested the proposed algorithm in a cohort of 100 patients. With 10-fold cross validation, the SBBS-CNN achieved mean Dice similarity coefficients of 97.31 ± 0.36% and average symmetric surface distance of 1.77 ± 0.49 mm. Moreover, it showed superior performance in comparison with state-of-art methods, including U-Net, pixel-based CNN, active contour, level-sets and graph-cut algorithms. SBBS-CNN provides an accurate and effective tool for automated liver segmentation. It is also envisioned that the proposed framework is directly applicable in other medical image segmentation scenarios.

22 August 2018 in IEEE Access
Verified
Journal Article
Open access
JLJingzhen Li
Jingzhen Li
TITobore Igbe
Tobore Igbe
YLYuhang Liu
Yuhang Liu
NZNie Zedong
Nie Zedong
WQWenjian Qin
Wenjian Qin
YHYang Hao
Yang Hao
Noninvasive blood glucose monitoring (NBGM) provides a promising solution for patients with diabetes with the advantages of painless and continuous monitoring. To better characterize the response of glucose to radio-frequency (RF) signals at low frequencies, the conductivity and relative permittivity of aqueous solutions with different glucose concentrations were obtained by the use of an impedance analyzer in the frequency range of 1 kHz to 1 MHz. Furthermore, considering the blood volume pulsation in cardiac cycle, a new approach based on measuring bioimpedance was presented for NBGM in this paper. For this purpose, an inhomogeneous arm model, which consists of three tissue layers (i.e., blood, blood vessel, and other relevant tissues), was proposed to validate the aforementioned approach. Furthermore, the measurements were carried out by means of in vitro experiment and in vivo studies, respectively. The results showed that as the glucose concentration increased, the conductivity of aqueous solutions decreased when the frequency of RF signal was below 1 MHz. However, the relative permittivity was almost insensitive to glucose concentration. The simulation result of the arm model showed that as the glucose concentration increased, the bioimpedance difference of blood volume decreased. This was supported by both in vitro and in vivo experiments. We therefore suggest that the proposed approach for NBGM has potentials in practical applications.

26 March 2022 in Radiotherapy and Oncology
Verified
Journal Article
Closed access
MYMeiyan Yue
Meiyan Yue
XXXiaoguang Xue
Xiaoguang Xue
ZWZhanyu Wang
Zhanyu Wang
RLRicardo Lewis Lambo
Ricardo Lewis Lambo
WZWei Zhao
Wei Zhao
WQWenjian Qin
Wenjian Qin

1 November 2013 in Biomedical Signal Processing and Control
Verified
Journal Article
Open access
TWTiexiang Wen
Tiexiang Wen
QZQingsong Zhu
Qingsong Zhu
WQWenjian Qin
Wenjian Qin
LLLing Li
Ling Li
FYFan Yang
Fan Yang
JGJia Gu
Jia Gu
Freehand three-dimensional ultrasound imaging is a highly attractive research area because it is capable of volumetric visualization and analysis of tissues and organs. The reconstruction algorithm plays a key role to the construction of three-dimensional ultrasound volume data with higher image quality and faster reconstruction speed. However, a systematic approach to such problem is still missing. A new fast marching method (FMM) for three-dimensional ultrasound volume reconstruction using the tracked and hand-held probe is proposed in this paper. Our reconstruction approach consists of two stages: bin-filling stage and hole-filling stage. Each pixel in the B-scan images is traversed and its intensity value is assigned to its nearest voxel in the bin-filling stage. For the efficient and accurate reconstruction, we present a new hole-filling algorithm based on the fast marching method. Our algorithm advances the interpolation boundary along its normal direction and fills the area closest to known voxel points in first, which ensure that the structural details of image can be preserved. Experimental results on both ultrasonic abdominal phantom and in vivo urinary bladder of human subject and comparisons with some popular algorithms are used to demonstrate its improvement in both reconstruction accuracy and efficiency