Wei Liu

Wei Liu

Auto-generated profile, based on publicly available information

Wei Liu

School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
9 October 2019 in IEEE Transactions on Medical Imaging
Verified
Journal Article
Closed access
MHMorteza Heidari
Morteza Heidari
SMSeyedehnafiseh Mirniaharikandehei
Seyedehnafiseh Mirniaharikandehei
WLWei Liu
Wei Liu
AHAlan B. Hollingsworth
Alan B. Hollingsworth
HLHong Liu
Hong Liu
Bin ZhengBin Zheng
Bin Zheng
This study aims to develop and evaluate a new computer-aided diagnosis (CADx) scheme based on analysis of global mammographic image features to predict likelihood of cases being malignant. An image dataset involving 1,959 cases was retrospectively assembled. Suspicious lesions were detected and biopsied in each case. Among them, 737 cases are malignant and 1,222 are benign. Each case includes four mammograms of craniocaudal and mediolateral oblique view of left and right breasts. CADx scheme is applied to pre-process mammograms, generate two image maps in frequency domain using discrete cosine transform and fast Fourier transform, compute bilateral image feature differences from left and right breasts, and apply a support vector machine (SVM) to predict likelihood of the case being malignant. Three sub-groups of image features were computed from the original mammograms and two transformation maps. Four SVMs using three sub-groups of image features and fusion of all features were trained and tested using a 10-fold cross-validation method. The computed areas under receiver operating characteristic curves (AUCs) range from 0.85 to 0.91 using image features computed from one of three sub-groups, respectively. By fusion of all image features computed in three sub-groups, the fourth SVM yields a significantly higher performance with AUC = 0.96±0.01 (p<; 0.01). This study demonstrates feasibility of developing a new global image feature analysis based CADx scheme of mammograms with high performance. By avoiding difficulty and possible errors in breast lesion segmentation, this new CADx approach is more efficient in development and potentially more robust in future application.

14 May 2022 in Computational and Mathematical Methods in Medicine
Verified
Journal Article
Open access
PDF file
XXXuebin Xu
Xuebin Xu
MAMeijuan An
Meijuan An
JZJiada Zhang
Jiada Zhang
WLWei Liu
Wei Liu
LLLongbin Lu
Longbin Lu
Cancer is one of the major causes of human disease and death worldwide, and mammary cancer is one of the most common cancer types among women today. In this paper, we used the deep learning method to conduct a preliminary experiment on Breast Cancer Histopathological Database (BreakHis); BreakHis is an open dataset. We propose a high-precision classification method of mammary based on an improved convolutional neural network on the BreakHis dataset. We proposed three different MFSCNET models according to the different insertion positions and the number of SE modules, respectively, MFSCNet A, MFSCNet B, and MFSCNet C. We carried out experiments on the BreakHis dataset. Through experimental comparison, especially, the MFSCNet A network model has obtained the best performance in the high-precision classification experiments of mammary cancer. The accuracy of dichotomy was 99.05% to 99.89%. The accuracy of multiclass classification ranges from 94.36% to approximately 98.41%.Therefore, it is proved that MFSCNet can accurately classify the mammary histological images and has a great application prospect in predicting the degree of tumor. Code will be made available on http://github.com/xiaoan-maker/MFSCNet.

1 June 2009
Verified
Conference Paper
Closed access
FPFangqing Peng
Fangqing Peng
LLLihua Li
Lihua Li
WXWeidong Xu
Weidong Xu
WLWei Liu
Wei Liu
JZJuan Zhang
Juan Zhang
GSGuoliang Shao
Guoliang Shao
The purpose of this study is to investigate the significance of the multi-agent interactive information fusion algorithm over the matter of identification of breast masses in digitized images. For the lack of enough correlation information between the individual classifiers, the generalization performance of the Bayesian fusion method is sometimes far from the expected level, and thereby the multi-agent fusion method is presented in this paper. The multi-agent interactive information fusion algorithm applies precisely this correlation information to improve the performance, especially the robustness. In this experiment, the presented method is compared with four common fusion algorithms, all of which are applied to the UCI dataset with 569 cases (357 depicting malignant cases and 212 depicting benign cases), and the experimental results show that it does not only circumvent the accuracy and sensitivity need of the breast masses identification in digitized images, but also achieves performance close to the robustness.

20 October 2023
Verified
Conference Paper
Closed access
LWLiu Wei
Liu Wei
WSWang Shan
Wang Shan
LWLiu Weihong
Liu Weihong
A high gain and low noise front-end readout mix chip has been designed to address the temperature stability issue of the radiation detector front-end readout circuit. The chip integrates an analog to digital converter after each readout circuit channel, resulting in high overall signal processing efficiency. Improvements have been made to the key module charge sensitive amplifier circuit, proposing a multi-stage high temperature compensation charge sensitive amplifier circuit. This overcomes the temperature stability problem of using MOS transistors operating in the subthreshold region as feedback resistors, ensures that the amplifier maintains a basically constant discharge time over a wide temperature range, and ensures that the overall circuit has good temperature stability. A new type of peak detection hold circuit is used to eliminate the traditional RC delay unit and improve the stability and accuracy of the front end readout circuit. The simulation results show that the equivalent input noise charge of the front-end readout system chip is 29.52e - , gain is 200V/pC, power consumption is 5.52mW, the maximum nonlinear error is 7%.

23 September 2022
Verified
Conference Paper
Open access
WLWei Liu
Wei Liu
YWYan Wang
Yan Wang
LQLang-Chao Qiao
Lang-Chao Qiao
JWJin-Lu Wang
Jin-Lu Wang
YWYi-Ran Wei
Yi-Ran Wei
WFWen-Tao Feng
Wen-Tao Feng
In the tobacco industry, the acquisition sheet is a kind of document used by the tobacco monopoly administration to record the information about the acquisition of fake and illicit cigarettes when the tobacco crime is seized by the "Internet Plus Express". To automatically identify the information helps to realize the automation of information management of tobacco monopoly administration department, and then build delivering for smoke crime management and prediction system, thus to deliver smoke involved crime effectively, and realize the wisdom of the tobacco industry monopoly, so to handwriting recognition research of the acquisition sheet image is very necessary. In this paper, an improved CRNN network text recognition method is proposed. Firstly, the acquisition sheet image with interference such as shadow and seal is preprocessed based on color channel separation method. Then, in the presence of printed text, the YoloX model is used to detect the handwritten text in the image, and the handwritten text line dataset is obtained. Then, the CNN network is improved by adding Swish activation function and attention mechanism to obtain the depth image features of handwritten text line data. BiLSTM network predicts the input feature sequence and finally realizes the recognition of handwritten text. Through the algorithm in this paper, the detection of handwritten text in the acquisition sheet image reaches an average accuracy of 0.983. The experimental results show that, compared with the CRNN model, the improved CRNN model in this paper has a better effect on the recognition of handwritten text in the acquisition sheet image.

23 September 2022
Verified
Conference Paper
Open access
WLWei Liu
Wei Liu
RXRong-Yao Xu
Rong-Yao Xu
LQLang-Chao Qiao
Lang-Chao Qiao
JWJin-Lu Wang
Jin-Lu Wang
BGBao-Hong Gao
Bao-Hong Gao
WFWen-Tao Feng
Wen-Tao Feng
The number of cigarette-related packages and normal packages is often extremely unbalanced in practice, this characteristic must be considered in the express-related counterfeit cigarette crime prediction, otherwise the performance of prediction model on unknown packages will be affected badly. In this paper, an approach of using SMOTE-ENN technology to deal with imbalanced express data and establish the express-related counterfeit cigarette crime prediction model is proposed. In the preprocessing stage, original data sets are structured by Chinese word segmentation method. In feature calculation and analysis stage, the spatio-temporal features of express data are calculated and analyzed, and the optimal features are further obtained by feature reduction algorithm named PCA. Next, based on optimal features, balanced data are obtained by mixed sampling. Finally, the classifier model was trained and optimized to predict the probability of a package containing counterfeit cigarettes in express data including 2851 normal samples and 285 cigarette-related samples randomly selected from 3077 cigarette-related samples. The performance of all classifiers is improved after using the SMOTE_ENN to balance datasets, and the indicators are above 98%. Experimental results demonstrate feasibility, effectiveness of the proposed approach.