Evaluation of advanced Lukas–Kanade optical flow on thoracic 4D-CT
- 322 Downloads
Extensive use of high frequency imaging in medical applications permit the estimation of velocity fields which corresponds to motion of landmarks in the imaging field. The focus of this work is on the development of a robust local optical flow algorithm for velocity field estimation in medical applications. Local polynomial fits to the medical image intensity-maps are used to generate convolution operators to estimate the spatial gradients. A novel polynomial window function with a compact support is used to differentially weight the optical flow gradient constraints in the region of interest. Tikhonov regularization is exploited to synthesize a well posed optimization problem and to penalize large displacements. The proposed algorithm is tested and validated on benchmark datasets for deformable image registration. The ten datasets include large and small deformations, and illustrate that the proposed algorithm outperforms or is competitive with other algorithms tested on this dataset, when using mean and variance of the displacement error as performance metrics.
KeywordsOptical flow Acute illness Deformable image registration Radiotherapy planning
The authors would like to acknowledge the help of Richard Castillo, MS who processed the result of our algorithm and assessed its performance. The authors would like to thank the National Science Foundation, which funded this project under grant CMMI-#0928630. C. Hoog Antink also would like to thank Fulbright and the German National Academic Foundation for partial funding. The authors have no financial relationship with the National Science Foundation which funded the research, the results of which are presented in this paper.
Conflict of interest
The authors declare that they have no conflict of interest.
- 1.Bouguet JY. Pyramidal implementation of the Lucas Kanade feature tracker: description of the algorithm. Intel Corporation 2001.Google Scholar
- 3.Castillo E, Castillo R, Zhang Y, Guerrero T. Compressible image registration for thoracic computed tomography images. J Med Biol Eng. 2009;29(5):222–233.Google Scholar
- 7.Delaunay BN. Sur la sphère vide. Bull Acad Sci USSR. 1934;6:793–800.Google Scholar
- 8.Duan Q, Herz S, Ingrassia C, Costa K, Holmes J, Laine A, Angelini E, Gerard O, Homma S. Dynamic cardiac information from optical flow using four dimensional ultrasound. In: 27th annual international conference of the engineering in medicine and biology society. IEEE-EMBS, vol 4. 2005. p. 4465–4468.Google Scholar
- 9.Gessat M, Frauenfelder T, Altwegg L, Grünenfelder J, Falk V. Transcatheter aortic valve implantation. Role of imaging. Aswan Heart Centre Sci Pract Ser. 2011;1:3.Google Scholar
- 12.Lucas BD, Kanade T. An iterative image registration technique with an application to stereo vision. In: Proceedings of the 7th international joint conference on artificial intelligence, vol 3. 1981. p. 674–679.Google Scholar
- 13.Murphy K, van Ginneken B, Reinhardt JM, Kabus S, Ding K, Deng X, Cao K, Du K, Christensen GE, Garcia V, Vercauteren T, Ayache N, Commowick O, Malandain G, Glocker B, Paragios N, Navab N, Gorbunova V, Sporring J, de Bruijne M, Han X, Heinrich MP, Schnabel Ja, Jenkinson M, Lorenz C, Modat M, McClelland JR, Ourselin S, Muenzing SEa, Viergever Ma, De Nigris D, Collins DL, Arbel T, Peroni M, Li R, Sharp GC, Schmidt-Richberg A, Ehrhardt J, Werner R, Smeets D, Loeckx D, Song G, Tustison N, Avants B, Gee JC, Staring M, Klein S, Stoel BC, Urschler M, Werlberger M, Vandemeulebroucke J, Rit S, Sarrut D, Pluim JPW. Evaluation of registration methods on thoracic ct: the empire10 challenge. IEEE Trans Med Imaging. 2011;30(11):1901–1920.PubMedCrossRefGoogle Scholar