MR image segmentation and bias field estimation based on coherent local intensity clustering with total variation regularization.

Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE

Publication: New York, NY : Springer
Original Publication: Stevenage, Eng., Peregrinus.

Algorithms* ; Image Interpretation, Computer-Assisted*; Magnetic Resonance Imaging/*methods; Analysis of Variance ; Cluster Analysis ; Gray Matter/pathology ; Humans ; White Matter/pathology

Though numerous segmentation algorithms have been proposed to segment brain tissue from magnetic resonance (MR) images, few of them consider combining the tissue segmentation and bias field correction into a unified framework while simultaneously removing the noise. In this paper, we present a new unified MR image segmentation algorithm whereby tissue segmentation, bias correction and noise reduction are integrated within the same energy model. Our method is presented by a total variation term introduced to the coherent local intensity clustering criterion function. To solve the nonconvex problem with respect to membership functions, we add auxiliary variables in the energy function such as Chambolle's fast dual projection method can be used and the optimal segmentation and bias field estimation can be achieved simultaneously throughout the reciprocal iteration. Experimental results show that the proposed method has a salient advantage over the other three baseline methods on either tissue segmentation or bias correction, and the noise is significantly reduced via its applications on highly noise-corrupted images. Moreover, benefiting from the fast convergence of the proposed solution, our method is less time-consuming and robust to parameter setting.

Phys Med Biol. 2004 Sep 7;49(17):4119-33. (PMID: 15470927)
Med Biol Eng Comput. 2013 Sep;51(9):1021-30. (PMID: 23686392)
Magn Reson Imaging. 2014 Sep;32(7):913-23. (PMID: 24928302)
Med Biol Eng Comput. 2013 Oct;51(10):1091-104. (PMID: 23744446)
Neuroimage. 2006 Apr 1;30(2):388-99. (PMID: 16275137)
IEEE Trans Med Imaging. 1998 Feb;17(1):87-97. (PMID: 9617910)
AJR Am J Roentgenol. 1987 Feb;148(2):418-20. (PMID: 3492123)
Neuroimage. 2001 May;13(5):856-76. (PMID: 11304082)
Med Biol Eng Comput. 2015 Jan;53(1):23-35. (PMID: 25304717)
IEEE Trans Med Imaging. 2003 Sep;22(9):1063-75. (PMID: 12956262)
IEEE Trans Med Imaging. 1993;12(4):770-81. (PMID: 18218473)
IEEE Trans Med Imaging. 1999 Oct;18(10):885-96. (PMID: 10628948)
Med Image Anal. 2011 Aug;15(4):622-39. (PMID: 20688559)
Comput Med Imaging Graph. 2011 Jul;35(5):383-97. (PMID: 21256710)
IEEE Trans Med Imaging. 1999 Sep;18(9):737-52. (PMID: 10571379)
IEEE Trans Med Imaging. 1996;15(2):154-69. (PMID: 18215898)
Schizophr Res. 2007 Nov;96(1-3):1-13. (PMID: 17761401)
Neuroimage. 2006 Aug 1;32(1):54-61. (PMID: 16647862)
Magn Reson Imaging. 2014 Oct;32(8):1058-66. (PMID: 24948583)
Med Biol Eng Comput. 2001 Jan;39(1):8-14. (PMID: 11214277)
Magn Reson Med. 1994 Jul;32(1):121-8. (PMID: 8084227)
Neuroimage. 2005 Jul 1;26(3):839-51. (PMID: 15955494)
Magn Reson Imaging. 1993;11(2):183-96. (PMID: 8455430)
Inf Process Med Imaging. 2009;21:288-99. (PMID: 19694271)
IEEE Trans Med Imaging. 2007 Mar;26(3):405-21. (PMID: 17354645)

Keywords: Bias correction; Chambolle’s fast dual projection; Nonconvex term; Tissue classification

Date Created: 20160705 Date Completed: 20170417 Latest Revision: 20181113

20231215

10.1007/s11517-016-1540-7

27376641