In this paper, we present a rule-based fuzzy segmentation system that is capable of segmenting magnetic resonance (MR) images of diseased human brains into physiologically and pathologically meaningful regions for measurement. We have developed a novel technique to automatically generate the membership functions for the fuzzy sets in the antecedent of the IF-THEN fuzzy rules in our system. Using this fuzzy system, we have performed the segmentation of brain images with periventricular lesions into four classes (grey matter, white matter, cerebrospinal fluid and periventricular lesions). The brain images were processed by our rule-based system as well as by the standard fuzzy c-means (FCM) algorithm used for performance comparison. The results, confirmed by the medical experts, showed that the rule-based fuzzy system significantly outperformed the standard FCM in the segmentation of the abnormal brain images.
Soft Computing in Intelligent Systems and Information Processing. Proceedings of the 1996 Asian Fuzzy Systems Symposium
SOFT COMPUTING IN INTELLIGENT SYSTEMS AND INFORMATION PROCESSING
- 4602 Artificial Intelligence
- 4605 Data Management And Data Science
- 46 Information And Computing Sciences
- Neurosciences
- Biomedical Imaging
0