Chinese Academy of Sciences

Yong Fan

Hongming Li

Di Jiang

Tianzi Jiang

A method for analyzing fMRI brain data, comprising: collecting the fMRI data including spatial information and temporal information from subjects; preprocessing the fMRI data; computing independent components (ICs) and their corresponding time course for each individual subjects; constructing an initial functional connectivity pattern; constructing a classifier based on the functional connectivity pattern; and applying the classifier to functional connectivity patterns of individual subjects for statistical analysis or diagnosis. The method may be used in fMRI based studies of a brain function and brain disorder diagnosis.

Method for analyzing functional MRI brain images

A method for brain tumor segmentation in multi-parametric 3D MR images. The method comprises: pre-processing an input multi-parametric 3D MR image; classifying each voxel in the pre-processed multi-parametric 3D MR image, determining the probability that the voxel is part of a brain tumor, and obtaining an initial label information for the image segmentation based on the classification probability; constructing a graph based representation for the pre-processed image to be segmented; and generating the segmented brain tumor image using the initial label information and graph based representation. This method tries to exploit the local and global consistency of the image to be segmented for the tumor segmentation and can alleviate partially the performance degradation caused by the inter-subject image variability and insufficient statistical information from training.

Method and system for brain tumor segmentation in multi-parameter 3D MR images via robust statistic information propagation

A method for registering functional MRI data, comprising: computing the functional connectivity pattern for every voxel in its given spatial neighborhood for every fMRI image; extracting features invariant to spatial location of the neighboring voxels based on the functional connectivity patterns; constructing similarity metric between voxels of different images based on the extracted features, and using fluid-like demons registration model to spatial normalize the fMRI data. The present invention tries to exploit the multi-range functional connectivity information of the fMRI data, and to register functional MR images based on the extracted spatial-location-invariant features. The present invention is robust against local spatial perturbations and does not depend on the assumption that functional signals of different subjects are synchronic, hence can be applied to resting-state fMRI data, and can achieve a statistically significant improvement in functional consistency across subjects.

Method for registering functional MRI data

A method for brain tumor segmentation in multi-parametric 3D magnetic resonance (MR) images, comprising: determining, for each voxel in the multi-parametric 3D MR image sequence, a probability that the voxel is part of brain tumor; extracting multi-scale structure information of the image; generating multi-scale tumor probability map based on initial tumor probability at voxel level and multi-scale structure information; determining salient tumor region based on multi-scale tumor probability map; obtaining robust initial tumor and non-tumor label based on tumor probability map at voxel level and salient tumor region; and generating a segmented brain tumor image using graph based label information propagation. The present invention is capable of achieving statistical reliable, spatially compact, and robust tumor label initialization, which is helpful to the accurate and reliable tumor segmentation. And the label information propagation framework could partially alleviate the performance degradation caused by image inconsistency between images to be segmented and training images.

Growing community of inventors

Beijing, China

Yong Fan