Learning to identify fuzzy regions in magnetic resonance images

Author

Crane, Sarah E. ; Hall, Lawrence O.

Author_Institution

Dept. of Comput. Sci. & Eng., Univ. of South Florida, Tampa, FL, USA

fYear

1999

fDate

36342

Firstpage

352

Lastpage

356

Abstract

The paper presents an approach to automatic heuristic rule generation for tissue labeling in a magnetic resonance (MR) volumetric image of the human brain. The image is clustered with the semi-supervised fuzzy c-means (ssFCM) algorithm. The clusters are then labeled by analyzing the membership of pixels in the cluster and the corresponding ground truth data. Finally, production rules which are capable of labeling unseen data are learned. Production rule cluster type identification error rates decrease as the clusters become more homogeneous. After imposing a minimum of 70% cluster homogeneity on both the training and the testing data sets, this system was tested using 10-fold cross validation on 29 normal slices with an average cluster type identification error rate of 1.2%

Keywords

biomedical MRI; brain; fuzzy set theory; image recognition; learning (artificial intelligence); medical expert systems; pattern clustering; 10-fold cross validation; automatic heuristic rule generation; cluster homogeneity; fuzzy region identification; ground truth data; human brain; magnetic resonance images; magnetic resonance volumetric image; normal slices; production rule cluster type identification error rates; production rules; semi-supervised fuzzy c-means algorithm; ssFCM algorithm; testing data sets; tissue labeling; unseen data; Clustering algorithms; Cranes; Decision trees; Humans; Image segmentation; Labeling; Magnetic resonance; Production; Protons; System testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Information Processing Society, 1999. NAFIPS. 18th International Conference of the North American

Conference_Location

New York, NY

Print_ISBN

0-7803-5211-4

Type

conf

DOI

10.1109/NAFIPS.1999.781713

Filename

781713