Segmentation of 3D MRI Image of Children Brain / 医疗卫生装备

ABSTRACT

Objective To study a semi-automatic segmentation framework for children's brain MRI image ( weighted), which is capable of identifying the different structures of children's MRI images by using the histogram analysis and morphological operations. Methods The framework consisted of four-step segmentation procedures. First, the non-brain structures removal was addressed to obtain the mask of encephalon, then the brain stem and cerebellum were separated respectively from the encephalon mask, and finally, two hemispheres were separated. Results The method behaved well in the segmentation of MRI images of the brain stem, cerebel and two brain hemispheres. Conclusion The method gave the good segmentation results in the children MRI image aging from 5 to 15 years old.