The recent years have witnessed a surge of interests in graph-based semi-supervised learning(GBSSL).In this paper,we will introduce a series of works done by our group on this topic including:1)a method called linear ...The recent years have witnessed a surge of interests in graph-based semi-supervised learning(GBSSL).In this paper,we will introduce a series of works done by our group on this topic including:1)a method called linear neighborhood propagation(LNP)which can automatically construct the optimal graph;2)a novel multilevel scheme to make our algorithm scalable for large data sets;3)a generalized point charge scheme for GBSSL;4)a multilabel GBSSL method by solving a Sylvester equation;5)an information fusion framework for GBSSL;and 6)an application of GBSSL on fMRI image segmentation.展开更多
To evaluate the effect of the positive-indefinite matrix on the diffusion tensor-derived parameters, a modified algorithm is proposed for calculating these parameters. Magnetic resonance (MR) diffusion tensor images...To evaluate the effect of the positive-indefinite matrix on the diffusion tensor-derived parameters, a modified algorithm is proposed for calculating these parameters. Magnetic resonance (MR) diffusion tensor images of five healthy volunteers are collected. The diffusion sensitive gradient magnetic fields are applied along 25 directions and the diffusion weighting value is 1 000 s/mm^2. Many positive-indefinite diffusion tensors can be found in the white matter area, such as the genu and the splenium of corpus callosum. Due to the positive-indefinite matrix, the mean diffusivity (MD) and the fractional anisotropy (FA) are under-estimated and over-estimated by using the conventional algorithm. Thus, the conventional algorithm is modified by using the absolute values of all eigenvalues. Results show that both the robustness and the reliability for deriving these parameters are improved by the modified algorithm.展开更多
In fMRI experiments on object representation in visual cortex, we designed two types of stimuli: one is the gray face image and its line drawing, and the other is the illusion and its corresponding completed illusion....In fMRI experiments on object representation in visual cortex, we designed two types of stimuli: one is the gray face image and its line drawing, and the other is the illusion and its corresponding completed illusion. Both of them have the same global features with different minute details so that the results of fMRI experiments can be compared with each other. The first kind of visual stimuli was used in a block design fMRI experiment, and the second was used in an event-related fMRI experiment. Comparing and analyzing interesting visual cortex activity patterns and blood oxygenation level dependent (BOLD)- fMRI signal, we obtained results to show some invariance of global features of visual images. A plau- sible explanation about the invariant mechanism is related with the cooperation of synchronized re- sponse to the global features of the visual image with a feedback of shape perception from higher cortex to cortex V1, namely the integration of global features and embodiment of sparse representation and distributed population code.展开更多
目的探讨颈动脉狭窄对脑梗死患者恢复期BOLD-fMRI信号变化的影响。方法采用3.0T超导磁共振机对17例急性脑梗死患者(病例组)和13例正常志愿者(对照组)进行BOLD-fMRI研究。病例组颈动脉狭窄者(>50%)8例,无明显颈动脉狭窄者(<50%)9例...目的探讨颈动脉狭窄对脑梗死患者恢复期BOLD-fMRI信号变化的影响。方法采用3.0T超导磁共振机对17例急性脑梗死患者(病例组)和13例正常志愿者(对照组)进行BOLD-fMRI研究。病例组颈动脉狭窄者(>50%)8例,无明显颈动脉狭窄者(<50%)9例,所得结果采用SPM5进行图像后处理。结果功能磁共振显示,激活部位主要分布在主要感觉运动区(primary sensorimotor cortex,SM1),辅助运动区(supplementary motor area,SMA)及小脑等部位。根据Brodmann分区,得出脑梗死患者激活体素为(471.86±396.04)mm3,较正常对照组(278.14±149.36)mm3明显增多(P<0.05),且健侧(253.80±216.33)mm3激活明显(P<0.05)。病例组颈动脉狭窄者(>50%)患侧脑Brodmann4区激活体素为(26.74±23.49)mm3,明显小于无明显颈动脉狭窄者的激活体素(66.23±30.88)mm3(P<0.05)。结论脑梗死患者脑激活总体素明显增多,且健侧激活更为明显;颈动脉明显狭窄可降低脑内BOLD-fMRI激活体素。展开更多
基金supported by the National Natural Science Foundation of China(Grant Nos.60835002,61075004).
文摘The recent years have witnessed a surge of interests in graph-based semi-supervised learning(GBSSL).In this paper,we will introduce a series of works done by our group on this topic including:1)a method called linear neighborhood propagation(LNP)which can automatically construct the optimal graph;2)a novel multilevel scheme to make our algorithm scalable for large data sets;3)a generalized point charge scheme for GBSSL;4)a multilabel GBSSL method by solving a Sylvester equation;5)an information fusion framework for GBSSL;and 6)an application of GBSSL on fMRI image segmentation.
基金Supported by the Research Project of Dongguan Higher Education (200910815252)the Beijing Natural Science Foundation(7102102)the Scientific Research Key Program of Beijing Municipal Commission of Ed-ucation(KZ200810025011)~~
文摘To evaluate the effect of the positive-indefinite matrix on the diffusion tensor-derived parameters, a modified algorithm is proposed for calculating these parameters. Magnetic resonance (MR) diffusion tensor images of five healthy volunteers are collected. The diffusion sensitive gradient magnetic fields are applied along 25 directions and the diffusion weighting value is 1 000 s/mm^2. Many positive-indefinite diffusion tensors can be found in the white matter area, such as the genu and the splenium of corpus callosum. Due to the positive-indefinite matrix, the mean diffusivity (MD) and the fractional anisotropy (FA) are under-estimated and over-estimated by using the conventional algorithm. Thus, the conventional algorithm is modified by using the absolute values of all eigenvalues. Results show that both the robustness and the reliability for deriving these parameters are improved by the modified algorithm.
基金Supported by the National Natural Science Foundation of China (Grant Nos. 60371045 & 60628101)the National High Technology Research and Development Program of China (Grant No. 2006AA01Z132)
文摘In fMRI experiments on object representation in visual cortex, we designed two types of stimuli: one is the gray face image and its line drawing, and the other is the illusion and its corresponding completed illusion. Both of them have the same global features with different minute details so that the results of fMRI experiments can be compared with each other. The first kind of visual stimuli was used in a block design fMRI experiment, and the second was used in an event-related fMRI experiment. Comparing and analyzing interesting visual cortex activity patterns and blood oxygenation level dependent (BOLD)- fMRI signal, we obtained results to show some invariance of global features of visual images. A plau- sible explanation about the invariant mechanism is related with the cooperation of synchronized re- sponse to the global features of the visual image with a feedback of shape perception from higher cortex to cortex V1, namely the integration of global features and embodiment of sparse representation and distributed population code.
文摘目的探讨颈动脉狭窄对脑梗死患者恢复期BOLD-fMRI信号变化的影响。方法采用3.0T超导磁共振机对17例急性脑梗死患者(病例组)和13例正常志愿者(对照组)进行BOLD-fMRI研究。病例组颈动脉狭窄者(>50%)8例,无明显颈动脉狭窄者(<50%)9例,所得结果采用SPM5进行图像后处理。结果功能磁共振显示,激活部位主要分布在主要感觉运动区(primary sensorimotor cortex,SM1),辅助运动区(supplementary motor area,SMA)及小脑等部位。根据Brodmann分区,得出脑梗死患者激活体素为(471.86±396.04)mm3,较正常对照组(278.14±149.36)mm3明显增多(P<0.05),且健侧(253.80±216.33)mm3激活明显(P<0.05)。病例组颈动脉狭窄者(>50%)患侧脑Brodmann4区激活体素为(26.74±23.49)mm3,明显小于无明显颈动脉狭窄者的激活体素(66.23±30.88)mm3(P<0.05)。结论脑梗死患者脑激活总体素明显增多,且健侧激活更为明显;颈动脉明显狭窄可降低脑内BOLD-fMRI激活体素。