Display options
Cite
Azmi R, Norozi N. A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images. J Med Signals Sens. 2011;1(3):156-64
Azmi, R., & Norozi, N. (2011). A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images. Journal of medical signals and sensors, 1(3), 156-64.
Azmi, Reza, and Norozi, Narges. "A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images." Journal of medical signals and sensors vol. 1,3 (2011): 156-64.
Azmi R, Norozi N. A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images. J Med Signals Sens. 2011 Jul;1(3):156-64. PMID: 22606671; PMCID: PMC3347230.
Copy Download .nbib Format: NLM
Share it on

J Med Signals Sens. 2011 Jul;1(3):156-64.

A New Markov Random Field Segmentation Method for Breast Lesion Segmentation in MR images.

Journal of medical signals and sensors

Reza Azmi, Narges Norozi

Affiliations

  1. Faculty of Engineering and Technology Alzahra University Tehran, Iran.

PMID: 22606671 PMCID: PMC3347230

Abstract

Breast cancer is a major public health problem for women in the Iran and many other parts of the world. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a pivotal role in breast cancer care, including detection, diagnosis, and treatment monitoring. But segmentation of these images which is seriously affected by intensity inhomogeneities created by radio-frequency coils is a challenging task. Markov Random Field (MRF) is used widely in medical image segmentation especially in MR images. It is because this method can model intensity inhomogeneities occurring in these images. But this method has two critical weaknesses: Computational complexity and sensitivity of the results to the models parameters. To overcome these problems, in this paper, we present Improved-Markov Random Field (I-MRF) method for breast lesion segmentation in MR images. Unlike the conventional MRF, in the proposed approach, we don't use the Iterative Conditional Mode (ICM) method or Simulated Annealing (SA) for class membership estimation of each pixel (lesion and non-lesion). The prior distribution of the class membership is modeled as a ratio of two conditional probability distributions in a neighborhood which is defined for each pixel: probability distribution of similar pixels and non-similar ones. Since our proposed approach don't use an iterative method for maximizing the posterior probability, above mentioned problems are solved. Experimental results show that performance of segmentation in this approach is higher than conventional MRF in terms of accuracy, precision, and Computational complexity.

Keywords: Breast Lesions segmentation; MR imaging; Markov Random Fields; Textural Features

References

  1. AJR Am J Roentgenol. 1992 Mar;158(3):521-6 - PubMed
  2. J Clin Oncol. 1999 Jan;17(1):110-9 - PubMed
  3. Med Phys. 2008 Jan;35(1):280-90 - PubMed
  4. IEEE Trans Med Imaging. 2007 Jun;26(6):880-9 - PubMed
  5. Comput Med Imaging Graph. 2009 Sep;33(6):431-41 - PubMed
  6. IEEE Trans Med Imaging. 2001 Jan;20(1):45-57 - PubMed
  7. Med Phys. 2004 May;31(5):1076-82 - PubMed
  8. Radiology. 1995 Dec;197(3):743-7 - PubMed
  9. CA Cancer J Clin. 2007 Mar-Apr;57(2):75-89 - PubMed
  10. Breast Cancer Res. 2001;3(1):55-60 - PubMed
  11. J Comput Assist Tomogr. 1998 Sep-Oct;22(5):827-37 - PubMed
  12. Radiology. 1999 Nov;213(2):317-20 - PubMed
  13. Comput Biol Med. 2008 Jan;38(1):116-26 - PubMed
  14. IEEE Trans Pattern Anal Mach Intell. 1984 Jun;6(6):721-41 - PubMed
  15. IEEE Trans Med Imaging. 1997 Dec;16(6):878-86 - PubMed
  16. Med Image Anal. 2010 Apr;14(2):87-110 - PubMed
  17. IEEE Trans Med Imaging. 2005 Dec;24(12):1548-65 - PubMed
  18. IEEE Trans Med Imaging. 1997 Apr;16(2):176-86 - PubMed
  19. Magn Reson Imaging. 2002 Feb;20(2):147-54 - PubMed
  20. Med Phys. 2009 Oct;36(10):4359-69 - PubMed
  21. Comput Med Imaging Graph. 2007 Jun-Jul;31(4-5):236-47 - PubMed
  22. Magn Reson Med. 2003 Jul;50(1):92-8 - PubMed
  23. Acad Radiol. 2006 Jan;13(1):63-72 - PubMed

Publication Types