Segmentation of rat brain MR images using a hybrid fuzzy system Conference Paper uri icon

abstract

  • We have developed a magnetic resonance (MR) image segmentation system which consists of a fuzzy ruled-based system and a fuzzy c-means algorithm (FCM). The first stage of the system is the fuzzy ruled-based system which classifies most pixels of MR images into several known classes and one `unclassified' class. In the second stage, the classified result of the first stage is used to find the initial prototypes for FCM and the `unclassified' pixels are classified by FCM. The result of this combination is a very robust classification system. Rat brain MR images with stroke lesions are segmented. This system successfully identified the penumbra area of the rat brain.

name of conference

  • NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intelligent Systems Conference, and the NASA Joint Technology Wo

published proceedings

  • NAFIPS/IFIS/NASA '94. Proceedings of the First International Joint Conference of The North American Fuzzy Information Processing Society Biannual Conference. The Industrial Fuzzy Control and Intelligent Systems Conference, and the NASA Joint Technology Wo

author list (cited authors)

  • Chang, C., Hillman, G. R., Ying, H., Kent, T. A., & Yen, J.

citation count

  • 5

complete list of authors

  • Chang, Chih-Wei||Hillman, GR||Ying, Hao||Kent, TA||Yen, J

publication date

  • January 1994