Preoperative CT angiography and intraoperative X-ray image registration algorithm for thoracic aortic endovascular repair

doi:10.3969/j.issn.2095-4344.1901

Abstract

Abstract:

BACKGROUND: Thoracic aortic endovascular repair is an important method for treating aortic dissection and thoracic aortic aneurysm. The success of the operation depends on whether the stent graft is placed in the correct position. However, when the stent is implanted, the aorta in the intraoperative X-ray image is invisible, so the operation is difficult and the risk is high. Registration of preoperative CT angiography and intraoperative X-ray images can help doctors place stents and increase success rates.
OBJECTIVE: To propose a preoperative CT angiography and intraoperative X-ray image registration algorithm for thoracic aortic endovascular repair.
METHODS: Firstly, digital reconstruction images of CT angiography and bone CT were performed under different virtual perspectives, and the two were superimposed to obtain a digital reconstruction image library under various angles of position and orientation for intraoperative X-ray images. Secondly, we proposed a deep neural network based on branch decoding structure. Using digital reconstruction image library training, the position and attitude parameters of intraoperative X-ray images could be estimated to obtain CT angiography and intraoperative X-ray images. The spatial positional relationship was obtained. Finally, according to the pose parameters of the X-ray image in the CT angiography coordinate system, the thoracic aorta image in the CT angiography was re-projected and superimposed into the intraoperative X-ray image to navigation assistance for the doctors.
RESULTS AND CONCLUSION: (1) The experimental results show that the root mean square error of the proposed algorithm is reduced by 17% compared with the traditional algorithms of gradient correlation and mode strength. (2) In the dual-branch code structure network, the parameter estimation error is reduced to 30% of the network without branching structure in the digital reconstruction image test set. (3) In the experimental X-image experiment, the root mean square error is also reduced by 2%.

Key words: thoracic endovascular aortic repair, registration, deep neural network, CT angiography, X-ray image, branch code

CLC Number:

Jia Ruiming, Li Haoxuan, Chen Yu, Huang Xiaoyong, Pu Xin, Shu Lixia. Preoperative CT angiography and intraoperative X-ray image registration algorithm for thoracic aortic endovascular repair [J]. Chinese Journal of Tissue Engineering Research, 2019, 23(35): 5658-5663.

Figures/Tables 8

References

[1]陈忠.主动脉血管疾病腔内治疗现状与展望[J].中华普通外科杂志,2015, 30(8):585-587.

[2]陈忠,杨耀国. 胸主动脉夹层腔内修复术中封堵左锁骨下动脉的考量[J]. 中国血管外科杂志(电子版), 2016, 8(1):6-9.

[3]陈纪言,罗淞元,刘媛. 急性主动脉夹层的腔内修复术治疗现状与展望[J]. 中国循环杂志, 2014, 29(1):1-3.

[4]景在平,张荣杰,周建. 主动脉疾病腔内治疗的现状与展望[J]. 中华普通外科杂志, 2016, 31(8):617-619.

[5]张龙江,祁吉. 对比剂肾病:一个值得关注的问题[J].中华放射学杂志, 2007,41(8):882-884.

[6]El-Gamal EZA, Elmogy M, Atwan A. Current trends in medical image registration and fusion. Egypt Inform J. 2016;17(1):99-124.

[7]Matl S,Brosig R,Baust M,et al. Vascular image registration techniques: a living review. Med Image Anal. 2017;35:1-17.

[8]Vernikouskaya I, Rottbauer W, Seeger J, et al. Patient-specific registration of 3D CT angiography (CTA) with X-ray fluoroscopy for image fusion during transcatheter aortic valve implantation (TAVI) increases performance of the procedure. Clin Res Cardiol.2018:1-10.

[9]Schulz CJ, Schmitt M, Böckler D, et al. Fusion imaging to support endovascular aneurysm repair using 3d-3d registration. J Endovasc Ther. 2016; 23(5):791-799.

[10]Khalil A, Faisal A, Lai KW, et al. 2D to 3D fusion of echocardiography and cardiac CT for TAVR and TAVI image guidance. Med Biol Eng Comput. 2016; 55(8):1-10.

[11]Ahmad W, Obeidi Y, Majd P, et al. The 2D-3D registration method in Image Fusion is accurate and helps to reduce the used contrast medium, radiation and procedural time in standard EVAR procedures. Ann Vasc Surg. 2018:177-186.

[12]Koutouzi G, Sandström C, Roos H, et al. Orthogonal rings, fiducial markers, and overlay accuracy when image fusion is used for evar guidance. J Vasc Surg. 2016;52(5):604-611.

[13]Izhar LI, Elamvazuthi I, Stathaki T, et al. Multimodal image registration for potential diagnosis and monitoring of morphoea using a hybrid NGC method// Int Conf Biomed Eng. 2017.

[14]Chelbi S, Mekhmoukh A. Features based image registration using cross correlation and Radon transform. Alexandria Engineering Journal, 2017:S1110016817302417.

[15]Gouveia AR, Metz C, Freire L, et al. Registration-by-regression of coronary CTA and X-ray angiography. Comp Methods Biomech Biomed Eng Imaging Vis. 2017; 5(3):208-220.

[16]Gouveia AR, Metz C, Freire L, et al. 3D-2D image registration by nonlinear regression. IEEE Int Sympos Biomed Imaging. 2012: 1343-1346.

[17]Miao S , Wang ZJ , Liao R . A CNN Regression Approach for Real-Time 2D/3D Registration. IEEE Trans Med Imaging. 2016; 35(5):1352-1363.

[18]Miao S, Wang ZJ, Zheng Y, et al. Real-time 2D/3D registration via CNN regression. IEEE, Int Sympos Biomed Imaging. 2016:636-648.

[19]Kendall A, Grimes M, Cipolla R. PoseNet: A Convolutional Network for Real-Time 6-DOF Camera Relocalization// IEEE Int Conf Comp Vis. 2015.

[20]Hwang J, Park S, Kwak N. Athlete Pose Estimation by a Global-Local Network//2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). IEEE, 2017.

[21]Anjam SM, Banaee N, Rahmani H, et al. Determination of geometric accuracy of radiotherapy fields by port film and DRR using Matlab graphical user interface. Med Biol Eng Comput. 2018;(4):1-11.

[22]Al-Qizwini M, Barjasteh I, Al-Qassab H, et al. Deep learning algorithm for autonomous driving using GoogLeNet// Intelligent Vehicles Symposium. 2017.

[23]Szegedy C, Liu W, Jia Y, et al. Going Deeper with Convolutions//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015.

[24]雒培磊,李国庆,曾怡. 一种改进的基于深度学习的遥感影像拼接方法[J]. 计算机工程与应用, 2017, 53(20):180-186.

[25]Drusvyatskiy D, Lee HL, Ottaviani G, et al. The euclidean distance degree of orthogonally invariant matrix varieties. Israel J Math. 2017; 221(1):1-26.

[26]Tong J, Zhao W, Lv H, et al. Transcriptomic profiling in human decidua of severe preeclampsia detected by RNA sequencing. J Cell Biochem. 2017;119(1):607-615.

[27]Caiti G, Dobbe JGG, Strijkers GJ, et al. Positioning error of custom 3D-printed surgical guides for the radius: influence of fitting location and guide design. Int J Comp Assist Radiol Surg. 2018;13(4):507-518.

[28]Ketcha MD, De ST, Han R, et al. Effects of Image Quality on the Fundamental Limits of Image Registration Accuracy. IEEE Trans Med Imaging. 2017;(99):1-1.

[29]Ouadah S, Jacobson M, Stayman JW, et al. WE-AB-BRA-08: Correction of Patient Motion in C-Arm Cone-Beam CT Using 3D-2D Registration. Med Phys. 2016;43(6):3792-3793.

[30]Hajirassouliha A, Taberner AJ, Nash MP, et al. Subpixel phase-based image registration using savitzky-golay differentiators in gradient-correlation. Comp Vis Image Understand. 2017.

[31]Abolaban F, Zaman S, Cashmore J, et al. Changes in patterns of intensity-modulated radiotherapy verification and quality assurance in the UK. Clin Oncol. 2016;28(8):e28-e34.