Constrained 최적화 기법을 이용한 Non-rigid 영상 등록

Non-rigid Image Registration using Constrained Optimization

  • 김정태 (이화여자대학교 정보통신학과 멀티미디어신호처리연구실)
  • 발행 : 2004.10.01

초록

비강체 (non-rigid) 영상 등록에서 추정되는 좌표변환은 가역이어야 함으로 그 변환의 Jacobian 행렬식은 항상 양수 값을 가져야 한다. 본 논문에서는 이러한 가역 조건을 만족하는 좌표변환의 조건을 gradient 크기 제한의 조건으로 구한다. 또한 cubic B-spline을 이용한 변환 모델의 경우, 이 gradient 크기 제한 조건을 만족시키는 인수 집합을 이웃한 두 계수들의 차이가 제한된 인수들의 집합으로 구하였다. 이러한 인수들의 집합은 half space들의 교집합으로 이루어진 convex 집합이다. 본 논문에서는 이 convex 집합에 속하는 인수로 구성되는 좌표변환들 중에서 유사지수 (similarity measure) 를 최대로 만드는 변환을 gradient projection 최적화 기법을 통해 발견하였다. 이론적 분석, 폐 CT (Computed Tomography) 영상을 이용한 시뮬레이션 및 실험을 통하여, 제안된 알고리즘의 성능이 벌칙 함수 penalty function) 를 이용하는 기존의 방법보다 우수함을 증명하였다.

In non-rigid image registration, the Jacobian determinant of the estimated deformation should be positive everywhere since physical deformations are always invertible. We propose a constrained optimization technique at ensures the positiveness of Jacobian determinant for cubic B-spline based deformation. We derived sufficient conditions for positive Jacobian determinant by bounding the differences of consecutive coefficients. The parameter set that satisfies the conditions is convex; it is the intersection of simple half spaces. We solve the optimization problem using a gradient projection method with Dykstra's cyclic projection algorithm. Analytical results, simulations and experimental results with inhale/exhale CT images with comparison to other methods are presented.

키워드

참고문헌

  1. J M Fitzpatrick, D L G Hill, and C R Maurer,'Image Registration,' in Handbook ofMedical Imaging, Volume 2. Medical Image Processing and Analysis, M. Sonka, J. Michael Fitzpatrick, Ed., pp. 477-513. SPICE, Bellingham, 2000
  2. M J Murphy, 'An automatic six -degree -offreedom image registration algorithm for image-guided frameless s t e r e o t act i c radiosurgery,' Med Phys., vol. 24, on. 6, pp. 857, June 1997 https://doi.org/10.1118/1.598005
  3. J Kim, J A Fessler, K L Lam, J M Balter, and R K Ten Haken, 'A feasibility study of mutual information based set-up error estimator for radiotherapy,' Med. Phys., vol.28, no. 12, pp. 2391-2593,2001 https://doi.org/10.1118/1.1421374
  4. K K Brock, D L McShan, R K Ten Haken,S J Hollister, L A Dawson, and J M Balter, 'Inclusion of organ deformation in dose calculation,' Med. Phys., vol. 30, no.3, pp. 290-95,2003 https://doi.org/10.1118/1.1539039
  5. J Weese, G P Penny, P Desmedt, T M Buzug, D L G Hill, and D J Hawkes, 'Voxel-based 2-D/3-D registration of fluoroscopy images and CT scans for image-guided surgery,' IEEE trans. On Info. Tech. in Biomedicine, vol. 1no.4, pp. 284-293, 1997 https://doi.org/10.1109/4233.681173
  6. C R Meyer, J L Boes, B Kim, P H Bland, et aI., 'Demonstration of accuracy and clinical versatility of mutual information for automatic multimodality image fusion using affme and thin plate spline warped geometric deformations,' Med Im. Anal., vol. 1, no. 3, pp. 195-206, 1997 https://doi.org/10.1016/S1361-8415(97)85010-4
  7. J Kim and J.A. Fessler, 'Image registration using robust correlation,' in Proc. IEEE IntI. Symp. Biomedical Imaging, 2002, pp. 353-6
  8. T Rohfling, C R Maurer Jr., D A Bluemke and M A Jacobs ,'Volume-preserving nonrigid registration of MR breast images using free-form deformation with an inompressibility constraint,' IEEE Tr .Med. Im., vol. 22, no. 6, pp.730-741, June 2003 https://doi.org/10.1109/TMI.2003.814791
  9. D Rueckert, L I Sonoda, C Hayes, D L G Hill, M 0 Leach, and D J Hawkes, :Nonrigid registration using free-form deformations: Applications to breast NR images,' IEEE Tr. Med Im., vol. 18, no. 8, pp.712-20, Aug.1999 https://doi.org/10.1109/42.796284
  10. J Kybic, P Thvenaz, A Nirkko, and M Unser, 'Unwarping of unidirectionally distorted EPI mages,' IEEE Tr. Med 1M., vol 19, no. 2, Feb.2000
  11. G K Rhode, A Aldroubi, and B M Dewant, 'The adaptive bases algorithm for intensity-based nonrigid image registration, 'IEEE Tr. Med IM., vol 22, no. 11, pp.1470-79 Nov. 2003 https://doi.org/10.1109/TMI.2003.819299
  12. A W Naylor and G R Sell, Linear operator theory in engineering and science, Springer, New York, 2000
  13. M Unser, 'Splines a perfect fit for signal and image processing.' IEEE Signal processing magazine, pp. 22-38. Nov 1999
  14. F L Bookstein, 'Principal warps: thin-plate splines and the decomposition of deformations,' IEEE Tr. Patt. Anal. Mach. Int., vol. 11, no. 6, pp. 567-87, June 1989 https://doi.org/10.1109/34.24792
  15. G E Christensen and H J Johnson, 'Consistent image registration, ' IEEE Tr. Med IM., vol 20, no. 7, pp.568-82 July. 2001 https://doi.org/10.1109/42.932742
  16. D G Luenberger, Optimization by vector space methods, Wiley, New York,1969
  17. F Deutch and H Hundal, 'The rate of convergence of Dykstra's cyclic projections algorithm: the polyhedral case,' Numer. Funct. Anal. and Optimiz., vol. 15, pp.537-65 1994 https://doi.org/10.1080/01630569408816580
  18. A Booker, J E Dennis, P Frank, D Serafini, V Torczon, and M Trosset, 'A rigorous framework for optimization of expensive f unctions by surrogates,' Structural Optimization, vol. 17, bo.l, pp.1-13, Feb.1999 https://doi.org/10.1007/BF01197708