A Parameter-Automatically-Optimized Graph-Based Segmentation Method for Breast Tumors in Ultrasound Images

摘要：

This paper introduces a parameter-automatically-optimized robust graph-based image segmentation method (PAORGB) for segmenting breast tumors in ultrasonic images. The robust graph-based (RGB) segmentation algorithm is based on the minimum spanning trees in a graph generated from an image. However, the values of k and α, which are two significant parameters in the RGB algorithm, are empirically selected in the reported studies. In this paper, we propose the PAORGB method, based on the particle swarm optimization algorithm to suitably set k and α, so as to overcome the problem of under-segmentation or over-segmentation in the RGB segmentation algorithm. Experimental results have shown that the proposed segmentation algorithm can successfully and more accurately detect tumors and extract lesions in ultrasound images in comparison with the RGB with default parameter settings and the Fuzzy C means clustering.

关键词： ultrasound image segmentation particle swarm optimization graph-based theory Fuzzy C means breast tumor

作者: Yingguang LI Qinghua HUANG Lianwen JIN

作者单位: School of Electronic and Information Engineering, South China University of Technology, Guangzhou, 510641

会议类型: 国际会议

会议名称: The 31st Chinese Control Conference(第三十一届中国控制会议)

会议地点: 合肥

会议语种:英文

页码: 4006-4011

在线出版日期: 2012-07-01（万方平台首次上网日期，不代表论文的发表时间）