CAJ | 학술논문

为了提高医学图像分割性能，针对传统模糊聚类算法存在的缺陷，提出了一种改进模糊均值聚类算法的医学图像分割方法。首先采用粒子群算法选择模糊均值聚类算法的聚类中心，然后利用空间邻域信息设定聚类样本空间，最后采用具体的医学图像数据进行仿真实验，测试其有效性。仿真结果表明，相对于传统模糊聚类算法，本文算法不仅提高了医学图像分割精度，而且提高了医学图像分割效率。
위료제고의학도상분할성능，침대전통모호취류산법존재적결함，제출료일충개진모호균치취류산법적의학도상분할방법。수선채용입자군산법선택모호균치취류산법적취류중심，연후이용공간린역신식설정취류양본공간，최후채용구체적의학도상수거진행방진실험，측시기유효성。방진결과표명，상대우전통모호취류산법，본문산법불부제고료의학도상분할정도，이차제고료의학도상분할효솔。
In order to improve the segmentation performance of medical image, aiming at the defects of the tradi-tional fuzzy clustering algorithm, a new medical image segmentation method is proposed an improved fuzzy c-means clustering algorithm in this paper. First of all, the clustering center of fuzzy c-means clustering algorithm is obtain by particle swarm optimization algorithm, and then the spatial neighborhood information set is used to get clustering sam-ple space, finally the simulation experiment is carried out on the medical image data to test effectiveness. The simula-tion results show that, compared with traditional fuzzy clustering algorithm, the proposed algorithm not only improves the segmentation accuracy, but also improve the segmentation efficiency of medical image.