头脑风暴算法优化的乳腺MR图像软子空间聚类算法

doi:10.3778/j.issn.1673-9418.1909084

摘要/Abstract

摘要：

传统的软子空间聚类算法在对信息量大、强度不均匀、边界模糊的乳腺MR图像进行分割时，易受初始聚类中心和噪声数据的影响，导致算法陷入局部最优，造成误分类。针对该问题，提出一种头脑风暴算法优化的乳腺MR图像软子空间聚类算法。算法首先引入一个放松界约束与广义噪声聚类结合的目标函数，并用隶属度计算方法来寻找簇类所在子空间；然后在子空间聚类时用给定指数来适配聚类任务；最后在聚类过程中运用头脑风暴算法进行优化，有效地平衡局部搜索与全局搜索，从而弥补现有算法易陷入局部最优的不足。对比算法与该算法在Berkeley图像数据集上的实验结果表明该算法具有较高的精度，临床乳腺MR图像聚类的实验结果验证了所提算法的鲁棒性。

关键词: 乳腺MR图像, 头脑风暴算法, 软子空间聚类算法, 图像聚类

Abstract:

The traditional soft subspace clustering algorithm is very susceptible to the initial clustering center and noise data when segmenting breast MR images with large amount of information, uneven intensity and boundary blur, which results in that algorithm falls into local optimum and causes serious misclassification. Aiming at solving this problem, a soft subspace clustering algorithm improved by brain storm algorithm for breast MR images cluster-ing is proposed in this paper. Firstly, a new objective function combines relaxation criterion and generalized noise clustering, and the membership degree calculation method is used to find the subspace where the cluster class is located. Then, the clustering task in the subspace is adapted with a given index. Finally, the brain storm algorithm is used in the clustering process to balance local search and global search and overcomes the disadvantages that the existing algorithms are easy to fall into local optimum. The experimental results of the comparison algorithms and the proposed algorithm in Berkeley image dataset show that the proposed algorithm has higher precision, and the clustering results of clinical breast MR images verify the strong robustness of the proposed algorithm.

Key words: breast MR image, brain storm algorithm, soft subspace clustering algorithm, image clustering

范虹，史肖敏，姚若侠. 头脑风暴算法优化的乳腺MR图像软子空间聚类算法[J]. 计算机科学与探索, 2020, 14(8): 1348-1357.

FAN Hong, SHI Xiaomin, YAO Ruoxia. Soft Subspace Clustering Algorithm Optimized by Brain Storm Algorithm for Breast MR Image[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(8): 1348-1357.

参考文献

[1] Siegel R L, Miller K D, Fedewa S A, et al. Colorectal cancer statistics[J]. CA: A Cancer Journal for Clinicians, 2017, 67(3): 177-193.
[2] Du J S, Gao Y, Bi X, et al. S-band microwave-induced thermo-acoustic tomography system[J]. Acta Physica Sinica, 2015, 64(3): 437-442.杜劲松, 高扬, 毕欣, 等. S波段微波热致超声成像系统研究[J]. 物理学报, 2015, 64(3): 437-442.
[3] Chen B Y, Zhang Y R, Wang L, et al. Microwave tomography for early breast cancer detection based on the alternating direction implicit finite-difference time-domain method[J]. Acta Physica Sinica, 2016, 65(14): 101-109.陈碧云, 张业荣, 王磊, 等. 基于交替隐式有限差分法的快速早期乳腺癌时域微波断层成像[J]. 物理学报, 2016, 65(14): 101-109.
[4] McKenzie F, Zietsman A, Galukande M, et al. Drivers of adv-anced stage at breast cancer diagnosis in the multicountry African breast cancer-disparities in outcomes (ABC-DO) study[J]. International Journal of Cancer, 2018, 142(8): 1568-1579.
[5] Bezdek J C, Ehrlich R, Full W. FCM: the fuzzy C-means clus-tering algorithm[J]. Computers & Geosciences, 1984, 10(2/3): 191-203.
[6] Zhang D Q, Chen S C. A novel kernelized fuzzy C-means algorithm with application in medical image segmentation[J]. Artificial Intelligence in Medicine, 2004, 32(1): 37-50.
[7] Krinidis S, Chatzis V. A robust fuzzy local information C-means clustering algorithm[J]. IEEE Transactions on Image Processing, 2010, 19(5): 1328-1337.
[8] Agrawal R, Gehrke J, Gunopulos D, et al. Automatic subs-pace clustering of high dimensional data for data mining app-lications[J]. ACM SIGMOD Record, 1998, 27(2): 94-105.
[9] Parsons L, Haque E, Liu H. Subspace clustering for high di-mensional data: a review[J]. ACM SIGKDD Explorations Newsletter, 2004, 6(1): 90-105.
[10] Deng Z H, Choi K S, Jiang Y Z, et al. A survey on soft subspace clustering[J]. Information Sciences, 2016, 348(1): 84-106.
[11] Wang Q, Chen G L. Fuzzy soft subspace clustering method for gene co-expression network analysis[J]. International Journal of Machine Learning and Cybernetics, 2017, 8(4): 1157-1165.
[12] Cheng L F, Yang T P, Chen L F. Soft subspace clustering al-gorithm for imbalanced data[J]. Journal of Computer Appli-cations, 2017, 37(10): 2952-2957.程铃钫, 杨天鹏, 陈黎飞. 不平衡数据的软子空间聚类算法[J]. 计算机应用, 2017, 37(10): 2952-2957.
[13] Zhao K F, Jiang Y Z, Xia K J, et al. View-collaborative fuzzy soft subspace clustering for automatic medical image segmentation[J]. Multimedia Tools and Applications, 2020, 79(13/14): 9523-9542.
[14] De Amorim R C, Mirkin B G. Minkowski metric, feature weighting and anomalous cluster initializing in [K-means]clustering[J]. Pattern Recognition, 2012, 45(3): 1061-1075.
[15] Fan H, Hou C C, Zhu Y C, et al. Soft subspace algorithm for MR image clustering based on fireworks optimization algorithm[J]. Journal of Software, 2017, 28(11): 3080-3093.范虹, 侯存存, 朱艳春, 等. 烟花算法优化的软子空间MR图像聚类算法[J]. 软件学报, 2017, 28(11): 3080-3093.
[16] Li S, Yuan Z G, Wang C, et al. Optimization of support vec-tor machine parameters based on group intelligence algori-thm[J]. CAAI Transactions on Intelligent Systems, 2018, 13(1): 70-84.李素, 袁志高, 王聪, 等. 群智能算法优化支持向量机参数综述[J]. 智能系统学报, 2018, 13(1): 70-84.
[17] Shi Y H. Brain storm optimization algorithm[C]//LNCS 6728: Proceedings of the 2nd International Conference Adv-ances in Swarm Intelligence, Chongqing, Jun 12-15, 2011. Berlin, Heidelberg: Springer, 2011: 303-309.
[18] Zhang H W, He J J, Han J H, et al. Fuzzy soft subspace clus-tering method based on intelligent optimization algorithm [J]. Computer Science, 2016, 43(3): 256-261.张恒巍, 何嘉婧, 韩继红, 等. 基于智能优化算法的模糊软子空间聚类方法[J]. 计算机科学, 2016, 43(3): 256-261.
[19] Lu Y P, Wang S R, Li S Z, et al. Particle swarm optimizer for variable weighting in clustering high-dimensional data[J]. Machine Learning, 2011, 82(1): 43-70.
[20] Bi Z S, Wang J H, Yin J. Subspace clustering based on diff-erential evolution[J]. Chinese Journal of Computers, 2012, 35(10): 2116-2128.毕志升, 王甲海, 印鉴. 基于差分演化算法的软子空间聚类[J]. 计算机学报, 2012, 35(10): 2116-2128.
[21] Dave R N, Sen S. Generalized noise clustering as a robust fuzzy c-M-estimators model[C]//Proceedings of the 1998 Con-ference of the North American Fuzzy Information Processing Society-NAFIPS, Pensacola, Aug 20-21, 1998. Piscataway: IEEE, 1998: 256-260.
[22] Yang Y T, Shi Y H, Xia S R. Discussion mechanism based brain storm optimization algorithm[J]. Journal of Zhejiang University (Engineering Science), 2013, 47(10): 1705-1711.杨玉婷, 史玉回, 夏顺仁. 基于讨论机制的头脑风暴优化算法[J]. 浙江大学学报(工学版), 2013, 47(10): 1705-1711.
[23] Fan H, Zhu Y C, Wang F M, et al. Segmentation of breast MR images based on multiresolution level set algorithm[J]. Acta Physica Sinica, 2014, 63(11): 118701.范虹, 朱艳春, 王芳梅, 等. 多分辨率水平集算法的乳腺MR图像分割[J]. 物理学报, 2014, 63(11): 118701.