A new volume segmentation algorithm for medical image based on improved K_means

作者：Xinwu Li^*

来源：International Journal of Digital Content Technology and Its Applications, 2011, 5(6): 1-7.

DOI：10.4156/jdcta.vol5.issue6.1

• 3D medical data
• Clustering segmentation
• Data fields
• Direct volume segmentation
• K-means
• k-Means algorithm
• K-Means clustering algorithm
• Medical data
• Medical images
• Physical means
• Process speed
• Research fields
• Seed selection
• Segmentation algorithms
• Speed-ups
• Volume segmentation

Direct volume segmentation is one of the difficult and hot research fields in 3D medical data field processing. A new clustering segmentation algorithm is presented through improving K-means clustering algorithm. Firstly, According to the physical means of the medical data, the data field is preprocessed to speed up succeed processing. Secondly, the paper deduces and analyzes the clustering and segmentation algorithm and improvs K-means algorithm principle, cluster seed selection, algorithm flow to increase the process speed. Finally, the experimental results show that the algorithm has high accuracy when used to segment 3D medical tissue and can improve process speed greatly.

• 出版日期2011