Abstract：Objective To evaluate the value of 2D-3D registration method which combines improved mutual information and image pyramid. Methods The continuous image representation of the cubic B-spline curve and Parzen histogram estimation were fused into the algorithm. The chest was used as the research object. The reconstruction of the orthogonal X-ray image generated by the radiographic image and the image after a certain transformation with itself were used for registration experiments to study the registration accuracy and time. Results After 50 sets of controlled experiments, compared with the traditional registration method, the displacement accuracy of this method in the X and Y directions was improved by 53.39% and 21.33%, and the registration time was shortened by 91.93%. Compared with the modified algorithms in recent years, the displacement accuracy of the improved algorithm in the X and Y directions was increased by 17.65% and 13.79%. And the registration time was further increased by 19.64%. Conclusions This method can effectively improve the registration accuracy and efficiency of 2D and 3D images, and both meet the requirements of image registration within 2 mm during surgery. The high efficiency and accuracy of this method provide beneficial information for clinical diagnosis and radiotherapy automation, which also lays the foundation for tumor position error correction and automatic positioning of medical robotic arms.
Qiu Yingchi,Yao Yunping,Zhang Peng. Research on 2D-3D registration method combining improved mutual information and image pyramid[J]. Chinese Journal of Radiation Oncology, 2021, 30(5): 486-491.
[1] 殷蔚伯. 肿瘤放射治疗学[M]. 北京:中国协和医科大学出版社,2008. Yin WB. Radiation Oncology[M]. Beijing:Peking Union Medical College Press, 2008. [2] 王秋实. 基于归一化互信息和遗传算法的医学图像配准研究[D]. 长春:吉林大学,2012. Wang QS. Research on medical image registration based on normalized mutual information and genetic algorithm[D]. Changchun:Jilin University,2012. [3] Dang H, Otake Y, Schafer S, et al. Robust methods for automatic image-to-world registration in cone-beam CT interventional guidance[J]. Med Phys, 2012, 39(10):6484-6498. DOI:10.1118/1.4754589. [4] Guan SY, Wang TM, Meng C, et al. A review of point feature based medical image registration[J]. Chin J Mechan Engin, 2018, 31(4):21-36. DOI:10.1186/s10033-018-0275-9. [5] Selmi SY, Promayon E, Troccaz J. Hybrid 2D-3D ultrasound registration for navigated prostate biopsy[J]. Int J Comput Assist Radiol Surg, 2018, 13(7):987-995. DOI:10.1007/s11548-018-1736-4. [6] 杨海龙. 基于超像素的交互式机场目标分割方法[D]. 西安:西安电子科技大学, 2016. DOI:10.7666/d. D01068723. Yang HL. Interactive airport target segmentation method[D]. Xi′an:Xi′an University of Electronic Science and Technology, 2016. DOI:10.7666/d. D01068723. [7] 赵夫群. 基于灰度信息的图像配准方法研究[J]. 计算机与数字工程,2019, 47(10):2568-2572. Zhao FQ. Image registration method based on gray information[J]. Comput Digit Engine, 2019, 47(10):2568-2572. [8] 杨昆. 基于计算机辅助手术导航系统的2D-三维图像配准的研究[D]. 南京:东南大学,2016. DOI:10.7666/d. Y3141335. Yang K. Study on 2D-3D image registration based on computer-aided surgical navigation system[D]. Nanjing:Southeast University, 2016. DOI:10.7666/d. Y3141335. [9] 王杨. 基于迭代回归的2D/3D多模态医学图像配准[D]. 成都:电子科技大学,2020. DOI:10.27005/d.cnki.gdzku.2020.000496. Wang Y. Two 2D/3D multimodal medical image registration[D]. Chengdu:University of Electronic Science and Technology, 2020. DOI:10.27005/d.cnki.gdzku.2020.000496. [10] 闫锋. 数字重建放射影像生成方法及其应用研究[D]. 合肥:合肥工业大学,2013. DOI:10.7666/d.y1700591. Yan F. Study on the methods and applications of digital reconstruction radiography[D]. Hefei:Hefei University of Technology, 2013. DOI:10.7666/d.y1700591. [11] 刘达,谢永召,倪自强,等. 基于局部方差采样的2D/3D医学图像配准技术[J]. 高技术通讯,2013, 23(8):827-832. DOI:10.11834/jig.20160109. Liu D, Xie YZ, Ni ZQ, et al. 2D/3D medical image registration based on local variance sampling[J]. High Technol Lett, 2013, 23(8):827-832. DOI:10.11834/jig.20160109. [12] 刘坤,吕晓琪,谷宇,等. 快速数字影像重建的2维/3维医学图像配准[J]. 中国图象图形学报,2016,21(1):69-77. DOI:10.11834/jig.20160109. Liu K, Lyu XQ, Gu Y, et al. The 2D/3D medical image registration algorithm based on rapid digital image reconstruction[J]. J Imag Graph, 2016, 21(1):69-77. DOI:10.11834/jig.20160109. [13] 张薇,黄毓瑜,栾胜,等. 基于灰度的二维/三维图像配准方法及其在骨科导航手术中的实现[J]. 中国医学影像技术,2007, 23(7):1080-1084. DOI:10.3321/j.issn:1003-3289.2007.07.038. Zhang W, Huang YY, Luan S, et al. Implementation of intensity-based 2D/3D image registration in orthopaedic navigation system[J]. Chin J Med Imag Technol, 2007, 23(7):1080-1084. DOI:10.3321/j.issn:1003-3289.2007.07.038. [14] Maes F, Collignon A, Vandermeulen D, et al. Multimodality image registration by maximization of mutual information[J]. IEEE Trans Med Imaging,1997, 16(2):187-198. DOI:10.1109/42.563664. [15] 吕晓琪,李娜,张宝华,等. 基于体素相似性的三维多模脑图像配准研究[J]. 中国医学影像学杂志,2013, 21(2):146-151. DOI:10.3969/j.issn.1005-5185.2013.02.020. Lyu XQ, Li N, Zhang BH, et al. Three-dimensional multi-modality brain image registration based on voxel similarity[J]. Chin J Med Imag, 2013, 21(2):146-151. DOI:10.3969/j.issn.1005-5185.2013.02.020. [16] 吕凯,吴军. 基于B样条和水平集方法的医学图像联合分割与配准[J]. 激光与光电子学进展,2020, 57(10):78-88. DOI:10.3788/LOP57.101007. Lyu K, Wu J. Joint segmentation and registration of medical image based on b-spline and level set method[J]. Laser Optoelect Prog, 2020, 57(10):78-88. DOI:10.3788/LOP57.101007. [17] Thevenaz P, Unser MA. Spline pyramids for intermodal image registration using mutual information[J]. Int Soci Opt Engin,1997,3169(3169):236-247. DOI:10.1117/12.292794. [18] Kurtz C, Stumpf A, Malet JP, et al. Hierarchical extraction of landslides from multiresolution remotely sensed optical images[J]. Isprs J Photogram Remo Sens, 2014, 87(1):122-136. DOI:10.1016/j.isprsjprs.2013.11.003. [19] Li G, Gao J, Kafka OL, et al. Implementation and application of the multiresolution continuum theory[J]. Computat Mech, 2019, 63(4):631-647. DOI:10.1007/s00466-018-1613-6.
2021, Vol. 30 
