Technical Program

Paper Detail

Paper:	TH-PM-PS2.3
Session:	Diffusion Tensor Imaging
Time:	Thursday, April 6, 15:20 - 16:40
Presentation:	Poster
Title:	Brain Tissue Segmentation Based on DWI/DTI Data
Authors:	Hai Li; Northwestern Polytechnic University
	Tianming Liu; Harvard Medical School
	Geoffrey Young; Harvard Medical School
	Lei Guo; Northwestern Polytechnic University
	Stephen T. C. Wong; Harvard Medical School
Abstract:	We present a method for brain tissue classification based on diffusion-weighted imaging (DWI)/diffusion tensor imaging (DTI) data. Our motivation is that independent tissue segmentation based on DWI/DTI images provides complementary information to the tissue segmentation result using structural MRI data alone. We classify the brain into two compartments by utilizing the tissue contrast exiting in a single channel, e.g., Apparent Diffusion Coefficient (ADC) image can be used to separate CSF and non-CSF, and the Fractional Anisotropy (FA) image can be used to separate WM from non-WM tissues. Other channels, such as eigen values of the tensor, relative anisotropy (RA), and volume ratio (VR), can also be used to separate tissues. We employ the STAPLE algorithm [8] to combine these two-class maps to obtain a complete segmentation of CSF, GM, and WM.

ISBI 2006 is sponsored by

and organized in cooperation with