Adaptive k-means clustering algorithm for MR breast image segmentation

被引：90

作者：

Moftah, Hossam M. ^{[1
,2
]}

Azar, Ahmad Taher ^{[2
,3
]}

Al-Shammari, Eiman Tamah ^{[4
]}

Ghali, Neveen I. ^{[2
,5
]}

Hassanien, Aboul Ella ^{[2
,6
]}

Shoman, Mahmoud ^{[6
]}

机构：

[1] Beni Suef Univ, Fac Comp & Informat, Bani Suwayf, Egypt

[2] SRGE, Cairo, Egypt

[3] Benha Univ, Fac Comp & Informat, Banha, Egypt

[4] Kuwait Univ, Fac Comp Sci & Engn, Kuwait, Kuwait

[5] Al Azhar Univ, Fac Sci, Cairo, Egypt

[6] Cairo Univ, Fac Comp & Informat, Cairo, Egypt

来源：

NEURAL COMPUTING & APPLICATIONS | 2014年 / 24卷 / 7-8期

关键词：

K-means clustering; Image segmentation; Magnetic resonance (MR) image; Breast cancer; Adaptive segmentation; SCREENING MAMMOGRAPHY; NEURAL-NETWORK;

D O I：

10.1007/s00521-013-1437-4

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Image segmentation is vital for meaningful analysis and interpretation of the medical images. The most popular method for clustering is k-means clustering. This article presents a new approach intended to provide more reliable magnetic resonance (MR) breast image segmentation that is based on adaptation to identify target objects through an optimization methodology that maintains the optimum result during iterations. The proposed approach improves and enhances the effectiveness and efficiency of the traditional k-means clustering algorithm. The performance of the presented approach was evaluated using various tests and different MR breast images. The experimental results demonstrate that the overall accuracy provided by the proposed adaptive k-means approach is superior to the standard k-means clustering technique.

引用

页码：1917 / 1928

页数：12