摘要
为了提高甲状腺肿瘤检出的准确率,提出一种基于人工蜂群算法的SPECT和B超甲状腺图像配准。首先,针对来自两个不同成像设备的SPECT和B超甲状腺图像灰度差异大的特点,使用NSCT和GCBAC相结合的方法提取B超图像感兴趣的轮廓特征,用KFCM的方法提取SPECT图像的轮廓特征;然后以互信息作为相似性测度,建立仿射变换模型,并以改进的人工蜂群算法作为优化策略来优化配准所需的空间变换参数。实验结果表明,该方法可以有效提高配准速度,具有较好的配准效果。
In order to improve the accuracy in thyroid tumor detection, a registration of SPECT image and B-type ultrasound image based on artificial bee colony algorithm is improved. First, NSCT-GCBAC segmentation and KFCM segmentation are used respectively to extract the contours, according to the different characteristics of thyroid SPECT image and B-type ultrasound image from two imaging devices. Second, mutual information is used for similarity measure, and affine transform model is adopted to solve the space transform parameters. Finally, an improved artificial bee colony algorithm is used to optimize the space registration transform parameters. The experimental results show that the method can effectively improve the speed and the effect of registration.
引文
[1]田文,罗晋.中国与美国甲状腺结节与分化型甲状腺癌诊治指南比较[J].中国实用外科杂志,2013,33(6):475-479.TIAN Wen,LUO Jin.Comparison of thyroid nodules and differentiated thyroid cancer guidelines form American and Chinese[J].Chinese Journal of Practical Surgery,2013,33(6):475-479.
[2]倪国强,刘琼.多源图像配准技术分析与展望[J].光电工程,2004,33(9):1-6.NI Guoqiang,LIU Qiong.Analysis and prospect of multi-source image registration techniques[J].Opto-Electronic Engineering,2004,33(9):1-6.
[3]LIU Haitao,WANG Yinlong,YAO Huifen.A new normalized-cut image segmentation algorithm based on watershed transforms[C]//4th International Conference on Intelligent Information Technology Application(IITA),Hebei,Qin Huangdao,Nov5,2010:5-7.
[4]Jignesh Sarvaiya,Suprava Patnaik,Hemant Goklani.Image registration using NSCT and invariant moment[J].International Journal of Image Processing(S2419-1724),2010,4(2):119-130.
[5]李超,李光耀,谭云兰,等.基于Powell算法与改进遗传算法的医学图像配准方法[J].计算机应用,2013,33(3):640-644.LI Chao,LI Guangyao,TAN Yunlan,et al.Medical image registration algorithm based on Powell algorithm and improved genetic algorithm[J].Journal of Computer Applications,2013,33(3):640-644.
[6]Ayatollahi,Fatemeh,Shokouhi.A new hybrid particle swarm optimization for multimodal brain image registration[J].Journal of Biomedical Science and Engineering(S1937-6871),2012,5(4):157-165.
[7]Arthur L da Cunha,ZHOU Jianping,Minh N Do A.The nonsubsampled contourlet transform:theory,design,and applications[J].IEEE Transactions on Image Processing(S1057-7149),2006,15(10):3089-3101.
[8]XU Ning,Ahujan,Bansal R.Object segmentation using graph cuts based active contours[J].Computer Vision and Image Understanding(S1077-3142),2007,107(3):210-224.
[9]Anan Banharnsakun,Tiranee Achalakul,Booncharoen Sirinaovakul.The best-so-far selection in artificial bee colony algorithm[J].Applied Soft Computing(S1568-4946),2011,11(2):2888-2901.
[10]阿里木-赛买提,杜培军,柳思聪.基于人工蜂群优化的二维最大熵图像分割[J].计算机工程,2012,38(9):223-225,243.ALIM Samat,DU Peijun,LIU Sicong.Maxmum 2D entrop image segmentation based on artificial bee colony optimization[J].Computer Engineering,2012,38(9):223-225,243.
[11]田莹,苑玮琦.遗传算法在图像处理中的应用[J].中国图象图形学报,2007,12(3):389-396.TIAN Ying,YUAN Weiqi.Application of the genetic algorithm in image processing[J].Journal of Image and Graphics,2007,12(3):389-396.
[12]唐红梅,宋培姣,王霞,等.基于改进粒子群优化算法的互信息图像配准[J].电视技术,2011,35(23):8-11.TANG Hongmei,SONG Peijiao,WANG Xia,et al.Mutual information image registration based on improved particle swarm optimization algorithm[J].Ideo Engineering,2011,35(23):8-11.
[13]郑伟,孟繁婧,田华,等.基于混合蛙跳算法的SPECT-B超甲状腺图像配准[J].河北大学学报:自然科学版,2013,33(3):305-311.ZHENG Wei,MENG Fanjing,TIAN Hua,et al.Registration of SPECT image and B-type ultrasound image based on shuffled frog leaping algorithm[J].Journal of Hebei University:Natural Science Edition,2013,33(3):305-311.