Statistical coronary motion models for 2D+t/3D registration of X-ray coronary angiography and CTA

被引:40
作者
Baka, N. [1 ,2 ,5 ]
Metz, C. T. [1 ,2 ]
Schultz, C. [3 ]
Neefjes, L. [4 ]
van Geuns, R. J. [4 ]
Lelieveldt, B. P. F. [5 ,8 ]
Niessen, W. J. [1 ,2 ,7 ]
van Walsum, T. [1 ,2 ]
de Bruijne, M. [1 ,2 ,6 ]
机构
[1] Erasmus MC, Dept Radiol, Biomed Imaging Grp Rotterdam, Rotterdam, Netherlands
[2] Erasmus MC, Dept Med Informat, Biomed Imaging Grp Rotterdam, Rotterdam, Netherlands
[3] Erasmus MC, Dept Cardiol, Rotterdam, Netherlands
[4] Erasmus MC, Dept Radiol, Rotterdam, Netherlands
[5] Leiden Univ, Med Ctr, Dept Radiol, Div Image Proc, Leiden, Netherlands
[6] Univ Copenhagen, Dept Comp Sci, DK-1168 Copenhagen, Denmark
[7] Delft Univ Technol, Fac Sci Appl, NL-2600 AA Delft, Netherlands
[8] Delft Univ Technol, Dept Intelligent Syst, Delft, Netherlands
关键词
SSM; 2D+t/3D+t registration; Reconstruction; 2D/3D alignment; Respiratory alignment; RESPIRATORY MOTION; 2D-3D REGISTRATION; RECONSTRUCTION; ARTERIES; CONSTRUCTION; PREDICTION; HEART;
D O I
10.1016/j.media.2013.03.003
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
Accurate alignment of intra-operative X-ray coronary angiography (XA) and pre-operative cardiac CT angiography (CTA) may improve procedural success rates of minimally invasive coronary interventions for patients with chronic total occlusions. It was previously shown that incorporating patient specific coronary motion extracted from 4D CTA increases the robustness of the alignment. However, pre-operative CTA is often acquired with gating at end-diastole, in which case patient specific motion is not available. For such cases, we investigate the possibility of using population based coronary motion models to provide constraints for the 2D + t/3D registration. We propose a methodology for building statistical motion models of the coronary arteries from a training population of 4D CTA datasets. We compare the 2D + t/3D registration performance of the proposed statistical models with other motion estimates, including the patient specific motion extracted from 4D CTA, the mean motion of a population, the predicted motion based on the cardiac shape. The coronary motion models, constructed on a training set of 150 patients, had a generalization accuracy of 1 mm root mean square point-to-point distance. Their 2D + t/3D registration accuracy on one cardiac cycle of 12 monoplane XA sequences was similar to, if not better than, the 40 CTA based motion, irrespective of which respiratory model and which feature based 2D/3D distance metric was used. The resulting model based coronary motion estimate showed good applicability for registration of a subsequent cardiac cycle. (C) 2013 Elsevier B.V. All rights reserved.
引用
收藏
页码:698 / 709
页数:12
相关论文
共 37 条
[1]
2D-3D shape reconstruction of the distal femur from stereo X-ray imaging using statistical shape models [J].
Baka, N. ;
Kaptein, B. L. ;
de Bruijne, M. ;
van Walsum, T. ;
Giphart, J. E. ;
Niessen, W. J. ;
Lelieveldt, B. P. F. .
MEDICAL IMAGE ANALYSIS, 2011, 15 (06) :840-850
[2]
Baka N., 2012, MICCAI WORKSH COMP A, P64
[3]
Baka N, 2011, LECT NOTES COMPUT SC, V6892, P434, DOI 10.1007/978-3-642-23629-7_53
[4]
Blackall JaneM., 2001, MICCAI 01 P 4 INT C, P1338
[5]
Automatic segmentation of echocardiographic sequences by active appearance motion models [J].
Bosch, JG ;
Mitchell, SC ;
Lelieveldt, BPF ;
Nijland, F ;
Kamp, O ;
Sonka, M ;
Reiber, JHC .
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2002, 21 (11) :1374-1383
[6]
Bouattour S, 2005, LECT NOTES COMPUT SC, V3691, P724
[7]
Chandrashekara R, 2003, LECT NOTES COMPUT SC, V2732, P599
[8]
Di Mario Carlo, 2007, EuroIntervention, V3, P30
[9]
FELDMAR J, 1995, FIFTH INTERNATIONAL CONFERENCE ON COMPUTER VISION, PROCEEDINGS, P549, DOI 10.1109/ICCV.1995.466891
[10]
Frangi AF, 1998, LECT NOTES COMPUT SC, V1496, P130, DOI 10.1007/BFb0056195