Abstract
When cancerous masses are embedded in and camouflaged by varying densities of parenchymal tissue structures, they are difficult to visually detect on mammograms. We present a novel algorithm based on the discrete wavelet transform (DWT) and multiresolution markov random field (MMRF) that will single out the suspicious masses to assist the attending radiologist in making decisions.
Full Text
The Full Text of this article is available as a PDF (951.7 KB).
References
- 1.Brzakovic D, Neskovic M. Mammogram screening using multiresolution-based image segmentation. Int J Pattern Recog Artif Intell. 1993;7:1437–1460. doi: 10.1142/S0218001493000704. [DOI] [Google Scholar]
- 2.Petrick N, Chan HP, Wei D. An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection. IEEE Trans Med Imaging. 1996;15:59–67. doi: 10.1109/42.481441. [DOI] [PubMed] [Google Scholar]
- 3.Chui CK. Wavelets: A Tutorial in Theory and Applications. San Diego, CA: Academic Press; 1992. [Google Scholar]
- 4.Besag J. Spatial interaction and the statistical analysis of lattice systems. J R Stat Soc B. 1974;36:192–236. [Google Scholar]
- 5.McKenzie P, Alder M: Initializing the EM algorithm for use in gaussian mixture modeling, in Pattern Recognition in Practice IV. the Netherlands, Vlieland, 1994
- 6.Bouman C, Liu B. Multiple resolution segmentation of textured images. IEEE Trans Pattern Anal Machine Intel. 1991;13:99–113. doi: 10.1109/34.67641. [DOI] [Google Scholar]
- 7.Li HD, Kallergi M, Clarke LP, et al. Markov random field for tumor detection in digital mammography. IEEE Trans Med Imaging. 1995;14:565–576. doi: 10.1109/42.414622. [DOI] [PubMed] [Google Scholar]
- 8.Dubes RC, Jain AK, Nadabar SG, et al. MRF model based algorithms for image segmentation. Proceedings of the 10th Internation Conference on Pattern Recognition. 1990;1:808–814. doi: 10.1109/ICPR.1990.118221. [DOI] [Google Scholar]