Abstract
In this study, the tissues in the magnetic resonance (MR) images are classified. Feature vectors are formed by the discrete cosine transform of pixel intensities in the region of interest. In this study, discrete cosine, and Fourier transforms are comparatively investigated for the segmentation. An incremental self-organized map (ISOM) is proposed as the classifier for the segmentation process.
Original language | English |
---|---|
Pages (from-to) | 1101-1102 |
Number of pages | 2 |
Journal | Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings |
Volume | 2 |
Publication status | Published - 2002 |
Event | Proceedings of the 2002 IEEE Engineering in Medicine and Biology 24th Annual Conference and the 2002 Fall Meeting of the Biomedical Engineering Society (BMES / EMBS) - Houston, TX, United States Duration: 23 Oct 2002 → 26 Oct 2002 |
Keywords
- Image processing
- Incremental neural network
- Tissue classification