Detection and 3D Reconstruction of Brain from MR Images / 대한의료정보학회지

In this paper, we propose a brain detection algorithm of cross-sectional images through a 3D volume. The proposed brain detection algorithm uses several steps. They are as follows; In the first step, the standard value and downward from input image data are removed. in the second step, the pixels with maximum intensity are removed but undesirable many small areas were appeared as by-products. In order to detect brain, these small areas need to be removed. In the third step, many small areas are removed by masking but some small areas still remained. In the fourth step, they are removed using three-dimensional connectivity. The proposed algorithm was applied to real human MRI data and the brain area was successfully detected.

Image Segmentation Method of Gibbs Random Field Accelerated by GPU / 医疗卫生装备

Objective To propose an improved C-means segment method based on Gibbs random field accelerated by GPU.Methods The parallel computation of pixel shades was used to take the place of the classical point-by-point method of CPU.By this way,the efficiency was higher than merely using the CPU computation.Results The efficiency of computation was improved over 400%.The load of CPU was reduced and the effect of accelerator was obvious.Conclusion The improved C-means segment method based on Gibbs random field accelerated by GPU enhances the clinical application of image segmentation,the computer rate of which is improved distinctly and closely to real time.[Chinese Medical Equipment Journal,2008,29(2):6-9]