The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

EM Algorithm-based Segmentation of Magnetic Resonance Image Corrupted by Bias Field

바이어스필드에 의해 왜곡된 MRI 영상자료분할을 위한 EM 알고리즘 기반 접근법

  • 김승구 (상지대학교 응용통계학과)
  • Published : 2003.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper provides a non-Bayesian method based on the expanded EM algorithm for segmenting the magnetic resonance images degraded by bias field. For the images with the intensity as a pixel value, many segmentation methods often fail to segment it because of the bias field(with low frequency) as well as noise(with high frequency). Our contextual approach is appropriately designed by using normal mixture model incorporated with Markov random field for noise-corrective segmentation and by using the penalized likelihood to estimate bias field for efficient bias filed-correction.

본 연구에서는 바이어스 필드에 의해 왜곡된 MRI 영상에 대한 분할을 위해 확장된 EM 알고리즘을 기반으로 한 통계적 접근법을 제시한다. 영상의 명암값을 자료로 하는 분할기법들은 고주파 성분의 잡음 뿐만 아니라 영상을 불균질하게 만드는 바이어스 필드라는 저주파 성분의 왜곡에 특히 취약하다. 이 문제를 해결하기 위해 본 논문에서는 잡음을 효과적으로 제어하기 위해 마코프랜덤필드가 적용된 정규혼합모형을 고려하며, 효과적인 바이어스 필드의 보정을 위해 페널티-우도를 도입하여 추정하는 방법으로 고안되었다.

Keywords

References

  1. Journal of the Royal Statistical Society B v.48 On Statistical analysis of dirty picture(discusion) Besag,J.
  2. IEEE Transaction on Medical Imaging v.16 no.3 Estimating the Bias Field of MR Images Guillemaud,R.;M.Brady https://doi.org/10.1109/42.585758
  3. Journal of the Royal Statistical Society B v.48 Contribution to the discussion of paper by J. Besang Kay,J.
  4. Proceedings of the Second International Conference on Image Processing and Applications Image labelling and the statistical analysis of incomplete data Kay,J;D.M.Titterington
  5. IEEE Transaction on Medical Imaging v.18 no.10 Automated Model-Based Bias Field Correction of MR Images of the Brain Lemmput,K.V.;F.M.Dirk;P.Stuetens https://doi.org/10.1109/42.811268
  6. IEEE Transaction on Medical Imaging v.18 no.10 Automated Model-Based Tissue Classification of MR Images of the Brain Lemmput,K.V.;F.M.Dirk;P.Stuetens https://doi.org/10.1109/42.811270
  7. ISIS Information, Statistics and Induction in Science An Algorithm for unsupervised learning via normal mixture model McLachlan,G.J.;D.Peel;D.L.Dowe(ed.);K.B.Korb(ed.);J.J.Oliver(ed.)
  8. The EM Algorithm and Extentions McLachlan,G.J.;T.Krishnan
  9. Biomerika v.80 Maximum Likelihood estimation via the ECM algorithm: a general framework Meng,X.L.;D.B.Rubin
  10. Proceeding of DICTA 95, 3rd Conference of Digital Image Computing: Techniques and Applications A mixture model approach to segmentation of magnetic resonance images Ng,S.K.;G.J.McLachlan;G.Galloway;S.E.Rose
  11. Philosophical Transaction of the Royal Society of London A v.337 Estimation of parameters in hidden Markov models Qian,W.;D.M.Titterington https://doi.org/10.1098/rsta.1991.0132
  12. Journal of Statistical Computation and Simulation v.40 Stochastic relaxations and EM algorithms for Markov random fields Qian,W.;D.M.Titterington https://doi.org/10.1080/00949659208811365
  13. IEEE Transaction on Medical Imaging v.15 no.4 Adaptive Segmentaion of MRI Data Wells,W.M.Ⅲ;W.E.Grimson;R.Kikinis;F.A.Jolesz https://doi.org/10.1109/42.511747
  14. IEEE Transaction on Medical Imaging v.20 no.1 Segmentation of Brain MR Images Through a Hidden Markov Random Field Model and the Expectation-Maximization Algorithm Zhang,Y.;M.Brady;S.Smith https://doi.org/10.1109/42.906424