Image Segmentation and Offset Correction Based on Minimal Relative Entropy Theoryand Level Set Method

doi:10.16182/j.issn1004731x.joss.201711019

Abstract

Abstract: The new variational level set method is achieved with the combination of the traditional level set method and the energy function which is established by means of statistical model according to the minimal relative entropy.The new method isappliedto object segmentation and offset correction in intensity heterogeneous image.Object segmentation and offset correction are unified according to the evolution of the level set function, anda deviation estimation function with intrinsic smooth feature is obtained.The results prove that the overlapping areas between different tissues are significantly decreased and more accurate results are achieved. In addition, this model is not sensitive to contour initialization, and can achieve the desired effect with fewer iterations and shorter calculation time, which issuitable for the process of various automation applications in practice with large amount of data.

Key words: relative entropy, image segmentation, offset correction, level set method

CLC Number:

TP391.41

Pan Xiuqiang, Shan Jinxiao, Yang Caifeng. Image Segmentation and Offset Correction Based on Minimal Relative Entropy Theoryand Level Set Method[J]. Journal of System Simulation, 2017, 29(11): 2731-2741.

References

[1] Vovk U, PernusF, LikarB."A Review of Methods for Correction of Intensity Inhomogeneity in MRI[J].IEEE Transactions on Medical Imaging(S0278-0062), 2007, 26(3): 405-421.
[2] RussJ. The Image Processing Handbook[M].CRC Press,2011.
[3] TomaževičD,LikarB, PernušF.Comparative evaluation of retrospective shading correction methods[J]. Journal of Microscopy(S0022-2720),2002,208(3):212-223.
[4] Zhu GY, UdupaJ K, LiuJ, et al.Scale-based method for correcting background intensity variation in acquired images[C]. Medical Imaging 2002:Image Processing, 2002, 4684:1 103-1111.
[5] SledJ G, ZijdenbosA P, EvansA C.A nonparametric method for automatic correction of intensity nonuniformity in MRI data[J]. IEEE Transactions on Medical Imaging (S0278-0062),1998, 17(1):87-97.
[6] GispertJ D, ReigS, PascauJ,et al. Garcia-Barreno, and M. Desco. Method for bias field correction of brain T1-weighted magnetic resonance images minimizing segmentation error[J]. Human Brain Mapping (S1065-9471), 2004, 22(2): 133-144.
[7] L X, L L, L H, et al.Partial volume segmentation of brain magnetic resonance images based on maximum a posteriori probability[J]. Medical Physics(S0094-2405), 2005, 32(7): 2337-2345.
[8] WellsW M, I I I, W E L. Grimson, R. Kikinis, and F. A. Jolesz.Adaptive segmentation of MRI data[J].IEEE Transactions on Medical Imaging(S0278-0062), 1996, 15(4): 429-442.
[9] Z Kaihua, Z Lei, Z Su.A variational multiphase level set approach to simultaneous segmentation and bias correction[C]//2010 17th IEEE International Conference on Image Processing(ICIP),2010:4105-4108.
[10] C Li, R. Huang, Z Ding, et al."A Level Set Method for Image Segmentation in the Presence of Intensity Inhomogeneities With Application to MRI[J]. IEEE Transactions on Image Processing (S1057-7149), 2011, 20(7): 2007-2016.
[11] Chunming L, K Chiu-Yen, J C Gore, et al.Implicit Active Contours Driven by Local Binary Fitting Energy [C]//IEEE Conference on Computer Vision & Pattern Recognition2007(CVPR '07), 2007(1): 1-7.
[12] LiC M, KaoC Y, GoreJ C, et al. Minimization of region-scalable fitting energy for image segmentation[J]. IEEE Transactions on Image Processing(S1057-7149), 2008, 17(10): 1940-1949.
[13] Chan T, VeseL.Active contours without edges[J]. IEEE Transactions on Image Processing (S1057-7149), 2001, 10(2): 266-277.
[14] LiC, HuangR, DingZ, et al.A Variational Level Set Approach to Segmentation and Bias Correction of Images with Intensity Inhomogeneity[C]//11th International Conference on Medical Image Computing and Computer- Assisted Intervention, 2008, 11(2): 1083-1091.
[15] PrimaS,AyacheN, BarrickT, et al. Maximumlikelihood estimation of the bias ﬁeld in MR brain images: Investigating different modelings of the imaging process[C].Med.Image Comput.Computer-Assist. Intervention (MICCAI 2001), 2001, 2208: 811-819.
[16] Brechbühler C, Gerig G, Székely G.Compensation of spatial inhomogeneity in MRI based on a multi-valued image model and a parametric bias estimate[C]. International Conference on Visualization in Biomedical Computing, 1996, 1131: 141-146.
[17] Styner M, Brechbuhler C, Szekely G, et al.Parametric estimate of intensity inhomogeneities applied to MRI[J]. IEEE Transactions on Medical Imaging(S0278-0062), 2000, 19(3): 153-165.
[18] Nowak R D.Wavelet-based Rician noise removal for magnetic resonance imaging[J]. IEEE Transactions on Medical Imaging(S0278-0062), 1999, 8(10): 1408-1419.
[19] Gudbjartsson H, Patz S.The Rician Distribution of Noisy MRI Data[J].Magnetic Resonance in Medicine (S0740-3194), 1995, 34(6): 910-914.
[20] GuillemaudR, BradyM. Estimating the bias ﬁeld of MR images[J].IEEE Transactions on Medical Imaging (S0278-0062), 1997, 16(3): 238-251.
[21] Van K, Leemput, Mae F, et al.Automated model-based bias ﬁeld correction of MR images of the brain[J]. IEEE Transactions on Medical Imaging(S0278-0062), 1999, 18(10): 885-896.
[22] WellsW M, III, W E L. Grimson, R. Kikinis, and F. A. Jolesz. Adaptive segmentation of MRI data[J]. IEEE Transactions on Medical Imaging (S0278-0062), 1996, 15(4): 429-442.
[23] Octavio, Augusto, Fontes, et al. Combined Minimum Relative Entropy and Maximum Likelihood estimation of dynamic models[C]//the 12th Annual Conference on Global Economic Analysis, 2009.
[24] LiChunming, XuChenyang, GuiChangfeng, et al. Distance Regularized Level Set Evolution and its Application to Image Segmentation[J]. IEEE Transactions on Image Processing (S1057-7149), 2010, 19(12): 3243-3254.
[25] GilboaG, SochenN, ZeeviY Y. Forward-and-backward diffusion processes for adaptive image enhancement and denoising[J]. IEEE Transactions on Image Processing (S1057-7149), 2002, 11(7): 689-703.
[26] Likar B, Viergever M A, Pernus F.Retrospective correction of MR intensity inhomogeneity by information minimization[J]. IEEE Transactions on Medical Imaging (S0278-0062), 2001, 20(12): 1398-1410.