Image Segmentation And 3D Reconstruction Based On MRI Image Of The Brain

Medical image segmentation and 3D reconstruction are important in medical image research field. The major goal of this dissertation is to explore an algorithm for medical image segmentation and 3D reconstruction based on MRI images of the brain. We analyzed the background and status in quo of these algorithms, especially the medical image segmentation algorithm. Medical image segmentation is one of the classical problems in image segmentation field, but to this day, there is no method that had good result for general images and no impersonal criterion for deciding whether the segmentation is success. In this dissertation, we did a thorough survey to the original image segmentation methods and propose an algorithm for the segmentation of the image series combining the thresholding image segmentation and the active contour model. We first segment one image of the series using optimal threshold determined by the class variance, and then segment the others using active contour model. A further research has been done in detail at theory , energy function and optimization algorithm about active contour model. Because the original model is less universal, so a new model is applied to segment the MRI images. Experimental results show that the new model is efficient and flexible. Direct volume rendering has been done with the volume date that came from the 2D image series. Finally we displayed the truly 3D image by the computer graphic technology of eliminating the hide surface and the light.