Ma Wenjie

Ma Wenjie

Auto-generated profile, based on publicly available information

Ma Wenjie

School of Computer and Software, Nanjing University of Information Science & Technology, Nanjing, 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
18 January 2021 in IEEE Access
Verified
Journal Article
Open access
LTLing Tan
Ling Tan
WMWenjie Ma
Wenjie Ma
JXJingming Xia
Jingming Xia
SSSajib Sarker
Sajib Sarker
Medical image segmentation has the significance of research in digital image processing. It can locate and identify the organ cells, which is essential for clinical analysis, diagnosis, and treatment. Since the high heterogeneity of pathological tissues and the inconspicuous resolution in multimodal magnetic resonance images, we propose a multimodal brain tumor image segmentation method based on ACU-Net network. In the beginning, we preprocess brain images to ensure the balanced number of categories. We adopt deep separable convolutional layers to replace the ordinary architecture in the U-Net to distinguish the spatial correlation and appearance correlation of the mapped convolutional channel. We introduce residual skip connection into the ACU-Net to heighten the propagation capacity of features and quicken the convergence speed of the network, to realize the capture of deep abnormal regions. We use the active contour model to against the image noise and edge cracks, come true the tracking of tumor deformation and solve the problem of edge blur in edema area, so as to divide the tumor core and enhanced necrotic parenchymal area exactly in the abnormal area. In this paper,17926 MRI images of 335 patients in the BraTS 2015, BraTS 2018, and BraTS 2019 datasets are used for training and verifying. Our experiments demonstrate that ACU-Net network has better performance than the other segmentation algorithms in subjective vision and objective indicators when applied to brain tumor image segmentation.

1 August 2007
Verified
Conference Paper
Closed access
MWMa Wenjie
Ma Wenjie
ZLZhizeng Luo
Zhizeng Luo
In order to recognize the hand-motions based on the Surface Electromyography(SEMG), a feature extracting algorithm is presented in the paper, which is built by combining Hilbert-Huang Transformation(HHT) with AR-model. According to the frequency-credit of each Intrinsic Mode Function (IMF) after HHT, six frequency-effective IMFs are selected. At the same time, the rectangle window is built based on the motion-start time and the motion-end time to extract motion signal of the six IMFs. The motion-start and motion-end points are decided by the instantaneous amplitude of the IMF with the largest frequency-credit. AR-model is built to extract the SEMG features for each IMF which are selected by frequency-credit and processed by the rectangle window. At last, two SEMG makes up the motion-feature vector. At last, Principal Components of the motion-feature vector are extracted and then put them into the Support Vector Machine (SVM) classifier to do the multi-patterns classification. The experimental results indicate that above method can have a good performance of discriminating four hand-movement patterns namely, palmar dorsiflexion and flexion, hand opening and closing.