http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Yunjie Chen,Qin Xu,Yuhui Zheng,Jin Wang,Jeong-Uk Kim 보안공학연구지원센터 2016 International Journal of Signal Processing, Image Vol.9 No.5
Accurate segmentation for magnetic resonance (MR) images is an essential step in quantitative brain image analysis, and hence has attracted extensive research attention. However, due to the existence of noise and intensity inhomogeneity, also named as bias field, many segmentation methods suffer from limited accuracy. This paper presents a novel variational framework for the registration, segmentation and bias estimation simultaneously. We first presented an improved segmentation model by using the intensity statistic distributions with different means and variances in local regions. The model can estimate the bias field meanwhile segmenting images. We also proposed an anisotropic non-rigid registration method by using the structure tensor information and nonlocal information to contain the information of the image details. Finally, we defined a coupled term to combine the segmentation and registration. The registration term can provide shape information as a prior to guide the segmentation and the segmentation term can provide the edge information to guide the registration. The segmentation and registration can obtain benefit from each other. Our statistical results on both synthetic and clinical images show that the proposed method can overcome the difficulties caused by noise and bias fields and obtain more accurate results.
( Yunjie Chen ),( Yuhang Qin ),( Zilong Jin ),( Zhiyong Fan ),( Mao Cai ) 한국인터넷정보학회 2020 KSII Transactions on Internet and Information Syst Vol.14 No.3
The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).
Brain MRI Segmentation and Bias Estimation Via An Improved Non-Local Fuzzy Method
Yunjie Chen,Zhengkai Wang,Jin Wang,Yuhui Zheng 보안공학연구지원센터 2015 International Journal of Grid and Distributed Comp Vol.8 No.4
Intensity in homogeneities cause considerable difficulties in the quantitative analysis of Magnetic Resonance (MR) images. Thus intensity in homogeneities estimation is a necessary step before quantitative analysis of MR data can be undertaken. This paper proposes a new energy minimization framework for simultaneous estimation of the intensity in homogeneities and segmentation. The intensity in homogeneities is modeled as a linear combination of a set of basis functions, and parameterized by the coefficients of the basis functions. The energy function depends on the coefficients of the basis functions, the membership ratios and the centroids of the tissues in the image. Intensity in homogeneities estimation and image segmentation are simultaneously achieved by calculating the result of minimizing this energy. Furthermore, in order to improve its robustness to noise, the membership ratios are adapted by using nonlocal information. Experimental results on both real MR images and simulated MR data show that our method can obtain more accurate results when segmenting images with bias field and noise.
A New Bias Field Estimation Method based on Adapted PSO Method
Yunjie Chen,Yingying Chu,Jin Wang,Yuhui Zheng 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.8
It is hard to segmentation brain MR images for the bias fields. In this paper, a new fuzzy anisotropic diffusion function is presented to reduce the effect of the noise. We use Legendre polynomial functions to reconstruct the bias field, which make the entropy of the recovered image be smallest. But it needs to compute a lot of parameters to reconstruct the bias. The traditional method uses the gradient descending method to compute the parameters. The method plunges into local best easily. In order to deal with this problem, Particle swarm optimization (PSO) method is analyzed. A new particle swarm technique is proposed that incorporates initial location information and use mutate operation make the particles away from local maxima. The experiments show that the new method can get accurate result robustly.
Chen, Jin,Chen, Qian,Hu, Bo,Wang, Yunji,Song, Jinlin Korean Academy of Periodontology 2016 Journal of Periodontal & Implant Science Vol.46 No.6
Purpose: Alendronate has been proposed as a local and systemic drug treatment used as an adjunct to scaling and root planing (SRP) for the treatment of periodontitis. However, its effectiveness has yet to be conclusively established. The purpose of the present meta-analysis was to assess the effectiveness of SRP with alendronate on periodontitis compared to SRP alone. Methods: Five electronic databases were used by 2 independent reviewers to identify relevant articles from the earliest records up to September 2016. Randomized controlled trials (RCTs) comparing SRP with alendronate to SRP with placebo in the treatment of periodontitis were included. The outcome measures were changes in bone defect fill, probing depth (PD), and clinical attachment level (CAL) from baseline to 6 months. A fixed-effect or random-effect model was used to pool the extracted data, as appropriate. Mean differences (MDs) with 95% confidence intervals (CIs) were calculated. Heterogeneity was assessed using the Cochrane ${\chi}^2$ and $I^2$ tests. Results: After the selection process, 8 articles were included in the meta-analysis. Compared with SRP alone, the adjunctive mean benefits of locally delivered alendronate were 38.25% for bone defect fill increase (95% CI=33.05%-43.45%; P<0.001; $I^2=94.0%$), 2.29 mm for PD reduction (95% CI=2.07-2.52 mm; P<0.001; $I^2=0.0%$) and 1.92 mm for CAL gain (95% CI=1.55-2.30 mm; P<0.001; $I^2=66.0%$). In addition, systemically administered alendronate with SRP significantly reduced PD by 0.36 mm (95% CI=0.18-0.55 mm; P<0.001; $I^2=0.0%$) and increased CAL by 0.39 mm (95% CI=0.11-0.68 mm; P=0.006; $I^2=6.0%$). Conclusions: The collective evidence regarding the adjunctive use of alendronate locally and systemically with SRP indicates that the combined treatment can improve the efficacy of non-surgical periodontal therapy on increasing CAL and bone defect fill and reducing PD. However, precautions must be exercised in interpreting these results, and multicenter studies evaluating this specific application should be carried out.