부산대학교 도서관

Magnetic resonance imaging (MRI) is a widely used method to obtain high quality medical image of the brain. Post-processing MR images with segmentation algorithms enhances the visualization and measurement of soft tissues and lesions. However, the conventional algorithms are not perfect and there are still some regions which are not partitioned accurately. In this paper, a new ant colony algorithm is presented in accordance with the defect of previous variety and stagnation. The contrast experimental results show that the new algorithm is not only of higher segmentation quality but also of higher computational speed, and prove that the algorithm is efficient and superior.