Accurate registration of chest radiographs plays an increasingly important role in medical applications.
However, most current intensity-based registration methods rely on the assumption of intensity conservation that
is not suitable for alignment of chest radiographs. In this study, we propose a novel algorithm to match chest
radiographs, for which the conventional residual complexity (RC) is modified as the similarity measure and the
cubic B-spline transformation is adopted for displacement estimation. The modified similarity measure is allowed
to incorporate the neighborhood influence into variation of intensity in a justified manner of the weight, while
the transformation is implemented with a registration framework of pyramid structure. The results show that
the proposed algorithm is more accurate in registration of chest radiographs, compared with some widely used
methods such as the sum-of-squared-differences (SSD), correlation coefficient (CC) and mutual information (MI)
algorithms, as well as the conventional RC approaches.
XIANG Zhikang (相志康), LI Min* (李敏), XIAO Liang (肖亮), LIAN Zhichao (练智超), WEI Zhihui (韦志辉)
. Deformable Registration of Chest Radiographs Using B-spline Based Method with Modified Residual Complexity[J]. Journal of Shanghai Jiaotong University(Science), 2019
, 24(2)
: 226
-232
.
DOI: 10.1007/s12204-019-2056-8
[1] ISHIDA T, KATSURAGAWA S, NAKAMURA K, etal. Iterative image warping technique for temporal subtractionof sequential chest radiographs to detect intervalchange [J]. Medical Physics, 1999, 26(7): 1320-1329.
[2] LI M, CASTILLO E, LUO H Y, et al. Deformable imageregistration for temporal subtraction of chest radiographs[J]. International Journal of Computer AssistedRadiology & Surgery, 2014, 9(4): 513-522.
[3] HILL D L G, BATCHELOR P G, HOLDEN M, etal. Medical image registration [J]. Physics in Medicineand Biology, 2001, 46(3): 1-45.
[4] ZITOVA B, FLUSSER J. Image registration methods:A survey [J]. Image and Vision Computing, 2003,21(11): 977-1000.
[5] HARRIS C G, STEPHENS M. A combined corner andedge detector [C]// Proceedings of the 4th Alvey VisionConference. Alvey, UK: [s.n.], 1988: 147-151.
[6] SMITH S M, BRADY J M. SUSAN: A new approachto low level image processing [J]. International Journalof Computer Vision, 1997, 23(1): 45-78.
[7] MORADI M, ABOLMAESUMI P. Medical image registration based on distinctive image features from scale-invariant (SIFT) key-points [J]. InternationalCongress Series, 2005, 1281: 1292.
[8] SANG Q, ZHANG J Z, YU Z Y. Robust non-rigidpoint registration based on feature-dependant finitemiture model [J]. Pattern Recognition Letters, 2013,34(13): 1557-1565.
[9] CRUM W R, HARTKENS T, HILL D L G. Nonrigidimage registration: Theory and practice [J]. TheBritish Journal of Radiology, 2004, 77(Sup 2): 140-153.
[10] BROIT C. Optimal registration of deformed images[J]. Acta Obstetrica Et Gynaecologica Japonica, 1981,39(4): 556-562.
[11] CHRISTENSEN G E, RABBITT R D, MILLER MI. Deformable templates using large deformation kinematics[J]. IEEE Transactions on Image Processing,1996, 5(10): 1435-1447.
[12] THIRION J P. Image matching as a diffusion process:An analogy with Maxwell’s demons [J]. Medical ImageAnalysis, 1998, 2(3): 243-260.
[13] YANG J, WANG Y T, TANG S Y, et al. Multiresolutionelastic registration of X-ray angiography imagesusing thin-plate spline [J]. IEEE Transactions on NuclearScience, 2007, 54(1): 152-166.
[14] MYRONENKO A, SONG X B. Intensity-based imageregistration by minimizing residual complexity [J].IEEE Transactions on Medical Imaging, 2010, 29(11):1882-1891.
[15] NOCEDAL J, WRIGHT S J. Numerical optimization[M]. Berlin, Germany: Springer Science & BusinessMedia, 2006.
[16] KLEIN S, STARING M, PLUIM J P W. Evaluation ofoptimization methods for nonrigid medical image registrationusing mutual information and B-splines [J].IEEE Transactions on Image Processing, 2007, 16(12):2879-2890.
[17] PENNEY G P, WEESE J, LITTLE J A, et al. Acomparison of similarity measures for use in 2D-3Dmedical image registration [C]//Proceedings of InternationalConference on Medical Image Computingand Computer-Assisted Intervention. Berlin, Germany:Springer, 1998: 1153-1161.
[18] STRANG G. The discrete cosine transform [J]. SIAMReview, 1999, 41(1): 135-147.
[19] BROWN L G. A survey of image registration techniques[J]. ACM Computing Surveys, 1992, 24(4): 325-376.
[20] MAES F, COLLIGNON A, VANDERMEULEN D, etal. Multimodality image registration by maximizationof mutual information [J]. IEEE Transactions on MedicalImaging, 1997, 16(2): 187-198.
[21] CHEN Z, HAYKIN S. On different facets of regularizationtheory [J]. Neural Computation, 2002, 14(12):2791-2846.
[22] RUECKERT D, SONODA L I, HAYES C, et al. Nonrigidregistration using free-form deformations: Applicationto breast MR images [J]. IEEE Transactions onMedical Imaging, 1999, 18(8): 712-721.
[23] HOLDEN M. A review of geometric transformationsfor nonrigid body registration [J]. IEEE Transactionson Medical Imaging, 2008, 27(1): 111-128.
