首页 > 论文 > 激光与光电子学进展 > 57卷 > 12期(pp:121010--1)

改进SURF在多模MRI乳腺配准算法中的研究

Research on Improved SURF Breast Registration Algorithm in Multi-Mode MRI

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

加速稳健特征算法在多模核磁共振成像(MRI)肿瘤图像配准中,存在特征点偏少且配准精度低等问题。使用Harris角点检测法对参考图像、浮动图像的特征点进行提取和检测,接着使用圆形64维向量法生成特征描述符并进行欧氏距离匹配,来增强特征点的提取。通过设置配准图像初始化参数,确保粒子在最优值附近搜索,利用互信息作为粒子群优化算法的测度函数,增强目标函数全局最优解,通过引入平均最值,防止算法陷入早熟现象。仿真结果表明,与现有的算法相比,所提优化算法可以使多模MRI图像特征点增多且精度更高。

Abstract

For the problem of a few feature points and low registration accuracy in multi-mode magnetic resonance imaging (MRI) tumor image registration by speeded up robust features algorithm. Harris detection method is used to extract and detect the feature points of reference image and floating image, and then circular 64-dimensional vector method is used to generate feature descriptors and carry out Euclidean distance matching to enhance the extraction of feature points. The initial parameters of registration image are set to ensure that particles search near the optimal value. The mutual information is used as the measure function of particle swarm optimization to enhance the global optimal solution of the objective function. The average maximum value is introduced to prevent this algorithm from falling into premature phenomenon. Simulation results show that compared with the existing algorithms, the proposed optimization algorithm can increase the number of multi-mode MRI image feature points with higher accuracy.

广告组6 - 调制器
补充资料

中图分类号:TP391

DOI:10.3788/LOP57.121010

所属栏目:图像处理

收稿日期:2019-09-04

修改稿日期:2019-10-31

网络出版日期:2020-06-01

作者单位    点击查看

李积英:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
杨永红:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
温强:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
王燕:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070
杨宜林:兰州交通大学电子与信息工程学院, 甘肃 兰州 730070

联系人作者:杨永红(476006535@qq.com)

【1】Chu J H, Wu Z R, Lü W, et al. Breast cancer diagnosis system based on transfer learning and deep convolutional neural networks [J]. Laser & Optoelectronics Progress. 2018, 55(8): 081001.
褚晶辉, 吴泽蕤, 吕卫, 等. 基于迁移学习和深度卷积神经网络的乳腺肿瘤诊断系统 [J]. 激光与光电子学进展. 2018, 55(8): 081001.

【2】Shi M X, Zhang X, Zhang T. Key technology and research status of registration methods for pulmonary image [J]. Beijing Biomedical Engineering. 2017, 36(4): 427-432.
史明霞, 张旭, 张涛. 肺部图像配准关键技术及研究现状 [J]. 北京生物医学工程. 2017, 36(4): 427-432.

【3】Wang G Y, Xu X Z, Ding S F. 3D-3D medical image registration method based on 3D-PCNN and mutual information [J]. Journal of Computer Applications. 2017, 37(z1): 215-219, 222.
王观英, 许新征, 丁世飞. 基于3D-PCNN和互信息的3D-3D医学图像配准方法 [J]. 计算机应用. 2017, 37(z1): 215-219, 222.

【4】Gu Z Y, Du C M, Jin L, et al. improved RANSAC algorithm. Applied Mechanics, Materials[J]. 2013, 411/412/413/414: 1233-1237.

【5】Shang M S, Wang K C. Advanced image registration method based on Harris and SIFT algorithm [J]. Microelectronics & Computer. 2018, 35(6): 132-134, 140.
尚明姝, 王克朝. 一种改进的Harris与SIFT算子结合的图像配准算法 [J]. 微电子学与计算机. 2018, 35(6): 132-134, 140.
Shang M S, Wang K C. Advanced image registration method based on Harris and SIFT algorithm [J]. Microelectronics & Computer. 2018, 35(6): 132-134, 140.
尚明姝, 王克朝. 一种改进的Harris与SIFT算子结合的图像配准算法 [J]. 微电子学与计算机. 2018, 35(6): 132-134, 140.

【6】Wang L F, Wang Y L, Lin S Z, et al. Non-rigid multi-modal brain image registration by using improved Zernike moment based local descriptor and graph cuts discreteoptimization [J]. Journal of Computer Applications. 2019, 39(2): 582-588.
王丽芳, 王雁丽, 蔺素珍, 等. 基于改进的Zernike矩的局部描述符与图割离散优化的非刚性多模态脑部图像配准 [J]. 计算机应用. 2019, 39(2): 582-588.

【7】Herbert B, Andreas E, Tinne T, et al. Speeded-up robust features (SURF) Computer Vision & Image Understanding[J]. 0, 110(3): 346-359.

【8】Xu J J. Fast image registration method based on Harris and SIFT algorithm [J]. Chinese Journal of Optics. 2015, 8(4): 574-581.
Harris 与 SIFT 算子的图像快速配准算法 [J]. 中国光学. 2015, 8(4): 574-581.

【9】Zhou H H, Yi W N, Du L L, et al. Convolutional neural network-based dimensionality reduction method for image feature descriptors extracted using scale-invariant feature transform [J]. Laser & Optoelectronics Progress. 2019, 56(14): 141008.
周宏浩, 易维宁, 杜丽丽, 等. 基于卷积神经网络的SIFT特征描述子降维方法 [J]. 激光与光电子学进展. 2019, 56(14): 141008.

【10】Zheng F, Li Y, Lu X S, et al. Research on ultrasound image registration method based on improved SIFT algorithm Modern Scientific Instruments[J]. 0, 2012(1): 31-35.
郑芳, 李颖, 陆雪松, 等. 基于改进SIFT算法的超声图像配准研究 现代科学仪器[J]. 0, 2012(1): 31-35.

【11】Weng F, Hou W G, Zeng M P. A‘coarse and fine'''' hybrid algorithm for three-dimensional medical image registration [J]. Beijing Biomedical Engineering. 2016, 35(1): 12-17.
翁飞, 侯文广, 曾明平. 用于三维医学图像配准的“粗精”混合算法研究 [J]. 北京生物医学工程. 2016, 35(1): 12-17.

【12】Xie Y R, Xie M Y, Yang L. The application of medical image registration based on ITK [J]. Computer Simulation. 2010, 27(3): 240-242, 257.
谢昱锐, 谢明元, 杨玲. 基于ITK的医学图像配准的应用 [J]. 计算机仿真. 2010, 27(3): 240-242, 257.

【13】Yang Y Q, Wei N, Dong F M. Accelerated multimodal images joint non-localfiltering [J]. Journal of Graphics. 2016, 37(1): 74-78.
杨元琴, 魏宁, 董方敏. 多模图像联合非局部滤波快速算法 [J]. 图学学报. 2016, 37(1): 74-78.

【14】Long L Y, Zhang G Y, Zhang L. Bibliometric analysis of clinical application of MRI on breast cancer [J]. Chinese Journal of Medical Imaging. 2012, 20(12): 940-947.
龙莉艳, 张桂云, 张磊. 乳腺癌的MRI应用研究文献的计量分析 [J]. 中国医学影像学杂志. 2012, 20(12): 940-947.

【15】Zhao Y. The application of three-dimensional arterial spin labeling images and contrast-enhanced images indiagnosis for the diagnosis and evaluation of brain tumors [D]. Nanning: Guangxi Medical University. 2016.
赵妍. 3DASL在脑肿瘤术前诊断分级及术后评估中的应用价值 [D]. 南宁: 广西医科大学. 2016.

【16】Zhao Y Q, Liu B X, Li G Y. Multimodal image registration based on PSO and gradient descent method [J]. Journal of Optoelectronics. Laser. 2011, 22(6): 940-944.
赵于前, 刘彬旭, 李桂源. 基于粒子群优化与梯度下降法的多模图像配准 [J]. 光电子.激光. 2011, 22(6): 940-944.

【17】Wang Z G. Binary particle swarm optimization using average information of swarm [J]. Science Technology and Engineering. 2012, 12(19): 4686-4690.
王志刚. 利用种群平均信息的二进制粒子群优化算法 [J]. 科学技术与工程. 2012, 12(19): 4686-4690.

【18】Liu D W, Han L, Han X Y. High spatial resolution remote sensing image classification based on deeplearning [J]. Acta Optica Sinica. 2016, 36(4): 0428001.
刘大伟, 韩玲, 韩晓勇. 基于深度学习的高分辨率遥感影像分类研究 [J]. 光学学报. 2016, 36(4): 0428001.

【19】Cheng X J, Guo W, Li Q, et al. Joint classification method for terrestrial LiDAR point cloud based on intensity and color information [J]. Chinese Journal of Lasers. 2017, 44(10): 1010007.
程效军, 郭王, 李泉, 等. 基于强度与颜色信息的地面LiDAR点云联合分类方法 [J]. 中国激光. 2017, 44(10): 1010007.

引用该论文

Li Jiying,Yang Yonghong,Wen Qiang,Wang Yan,Yang Yilin. Research on Improved SURF Breast Registration Algorithm in Multi-Mode MRI[J]. Laser & Optoelectronics Progress, 2020, 57(12): 121010

李积英,杨永红,温强,王燕,杨宜林. 改进SURF在多模MRI乳腺配准算法中的研究[J]. 激光与光电子学进展, 2020, 57(12): 121010

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF