Non-model segmentation of brain glioma tissues with the combination of DWI and fMRI signals.

For quantitative analysis of glioma, multimodal Magnetic Resonance Imaging (MRI) signals are required in combination to perform a complementary analysis of morphological, metabolic, and functional changes. Most of the morphological analyses are based on T1-weighted and T2-weighted signals, called traditional MRI. But more detailed information about tumorous tissues could not be explained. An information combination scheme of Diffusion-Weighted Imaging (DWI) and Blood-Oxygen-Level Dependent (BOLD) contrast Imaging is proposed in this paper. This is a non-model segmentation scheme of brain glioma tissues in a particular perspective of combining multi-parameters of DWI and BOLD contrast functional Magnetic Resonance Imaging (fMRI). Compared with traditional MRI, a promising advantage of our work is to provide an effective and adequate subdivision of the related pathological regions with glioma, by incorporating both knowledge of image graylevel and spatial structure. Furthermore, it is an automatic segmentation method without needs of parameter selection and model fitting for the extracted tissues. By the experiments in patients with glioma, the proposed method has achieved the average overlap ratios of 83.6% in the whole tumor region and 82.5% in the peritumoral edema region with the manual segmentation as "ground truth".