基于局部熵的Active Demons多模医学图像配准
|
摘要
针对Active Demons算法只能配准同模态图像,并且图像的灰度梯度不太明显时形变方向无法确定从而导致误配准的问题,提出了一种基于局部熵改进的Active Demons多模医学图像配准算法.该算法首先将原图像转换为局部熵图像,然后使用改进的Active Demons算法进行配准,该算法在Active Demons分母上分别加入浮动图像与参考图像的灰度梯度值平方.正则化变换时以双边滤波器代替高斯滤波器,使得图像边缘的细节信息保持较好.多模态医学图像配准的实验结果说明该方法精确度高,使图像质量得以提升.
In view of Active Demons algorithm is limited to the same mode image registration, and when the gray gradient information of the image is not obvious, the direction of image deformation can not be determined, an improved Active Demons multi-modality medical image registration based on local entropy image representation is proposed. Firstly, the image is converted into entropy image, and then the improved Active Demons algorithm, which the denominator is added with the square of the gray gradient of the floating image and the reference image, is used for registration. In the regularized transform, the paper use bilateral filter instead of Gauss filter to keep the detail edge information of the image better. The experimental results of multimodal medical image registration show that the proposed method is accurate and improves the image quality.
In view of Active Demons algorithm is limited to the same mode image registration, and when the gray gradient information of the image is not obvious, the direction of image deformation can not be determined, an improved Active Demons multi-modality medical image registration based on local entropy image representation is proposed. Firstly, the image is converted into entropy image, and then the improved Active Demons algorithm, which the denominator is added with the square of the gray gradient of the floating image and the reference image, is used for registration. In the regularized transform, the paper use bilateral filter instead of Gauss filter to keep the detail edge information of the image better. The experimental results of multimodal medical image registration show that the proposed method is accurate and improves the image quality.
引文
[1] 刘松涛,杨绍清.图像配准技术研究进展[J].电光与控制,2007,14(6):100-105.
[2] 申艳平.医学图像配准技术[J].中国医学物理学杂志,2013,30(1):3885-3889.
[3] OLIVEIRA F P M,MANUEL J R S T.Medical image registration:a review[J].Computer Methods in Biomechanics and Biomedical Engineering,2014,17(2):73-93.
[4] 罗述谦,李响.基于最大互信息的多模医学图像配准[J].中国图像图形学报,2000,5(7):551-558.
[5] THIRION J P.Image matching as a difiusion process:an analogy with Maxwell’s demons[J].Medical Image Analysis,1998,2(3):243-260.
[6] HELLIER P,BARILLOT C,COROUGE I,et al.Retrospective evaluation of intersubject brain registration[J].IEEE Transactions on Medical Image,2003,22(9):1120-1130.
[7] VERCAUTEREN T,PENNEC X,PERCHANT A,et al.Non-parametric diffeomorphic image registration with the Demons algorithm[J].Med Image Comput Comput Assist Interv,2007,10(2):319-326.
[8] VERCAUTEREN T,PENNEC X,MALIS E,et al.Insight into efficient image registration techniques and the Demons algorithm[J].Inf Process Med Imaging,2007,20:495-506.
[9] 雷文娟,祝轩,贾义亭,等.梯度与曲率变形力相结合的图像配准方法[J].计算机工程与应用,2012,48(5):204-206.
[10] 李碧草,张俊峰,杨冠羽,等.基于结构图像表示和微分同胚Demons算法的多模态医学图像配准[J].东南大学学报:自然科学版,2015,45(5):851-855.
[11] WANG He,DONG Lei,O’DANIEL J,et al.Validation of an accelerated‘demons’algorithm for deformable image registration in radiation therapy[J].Physics in Medicine and Biology,2005,50(12):2887-2905.
[12] 周雨薇,陈强,孙权森等.结合暗通道原理和双边滤波的遥感图像增强[J].中国图象图形学报,2014,19(2):313-321.
[13] 黄文辉,陈仁雷,张家谋.数字视频图像质量客观测量方法的改进与实现[J].北京邮电大学学报,2005,28(4):87-90.
[14] STUDHOLME C,HILL D L G,HAWKES D J.Multi-resolution voxel similarity measures for MR-PET registration[C]//Proceedings of Information Processing in Medical Imaging Conference.1995:287-298.
[2] 申艳平.医学图像配准技术[J].中国医学物理学杂志,2013,30(1):3885-3889.
[3] OLIVEIRA F P M,MANUEL J R S T.Medical image registration:a review[J].Computer Methods in Biomechanics and Biomedical Engineering,2014,17(2):73-93.
[4] 罗述谦,李响.基于最大互信息的多模医学图像配准[J].中国图像图形学报,2000,5(7):551-558.
[5] THIRION J P.Image matching as a difiusion process:an analogy with Maxwell’s demons[J].Medical Image Analysis,1998,2(3):243-260.
[6] HELLIER P,BARILLOT C,COROUGE I,et al.Retrospective evaluation of intersubject brain registration[J].IEEE Transactions on Medical Image,2003,22(9):1120-1130.
[7] VERCAUTEREN T,PENNEC X,PERCHANT A,et al.Non-parametric diffeomorphic image registration with the Demons algorithm[J].Med Image Comput Comput Assist Interv,2007,10(2):319-326.
[8] VERCAUTEREN T,PENNEC X,MALIS E,et al.Insight into efficient image registration techniques and the Demons algorithm[J].Inf Process Med Imaging,2007,20:495-506.
[9] 雷文娟,祝轩,贾义亭,等.梯度与曲率变形力相结合的图像配准方法[J].计算机工程与应用,2012,48(5):204-206.
[10] 李碧草,张俊峰,杨冠羽,等.基于结构图像表示和微分同胚Demons算法的多模态医学图像配准[J].东南大学学报:自然科学版,2015,45(5):851-855.
[11] WANG He,DONG Lei,O’DANIEL J,et al.Validation of an accelerated‘demons’algorithm for deformable image registration in radiation therapy[J].Physics in Medicine and Biology,2005,50(12):2887-2905.
[12] 周雨薇,陈强,孙权森等.结合暗通道原理和双边滤波的遥感图像增强[J].中国图象图形学报,2014,19(2):313-321.
[13] 黄文辉,陈仁雷,张家谋.数字视频图像质量客观测量方法的改进与实现[J].北京邮电大学学报,2005,28(4):87-90.
[14] STUDHOLME C,HILL D L G,HAWKES D J.Multi-resolution voxel similarity measures for MR-PET registration[C]//Proceedings of Information Processing in Medical Imaging Conference.1995:287-298.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |