Author/Editor		Barhoumi, Walid; Zagrouba, Ezzeddine
Title		Semiautomatic detection of tumoral zones
Type		članek
Source		Image Anal Stereol
Vol. and No.		Letnik 20, št. Suppl 1
Publication year		2001
Volume		str. 578-83
Language		eng
Abstract		This paper describes a robust method based on the cooperation of fuzzy classification and regions segmentation algorithms, in order to detect the tumoral zones in the MRI brain images. On one hand, the classification in fuzzy sets is done by the FCM algorithm, where a study of its different parameters and its complexity has been previously done, which led us to improve it. On the other hand, the segmentation in regions is obtained by an hierarchical method through adaptive thresholding. Then, an operator expert selects a germ in the tumoral zones, and the class containing the sick zones is localised in return for the FCM algorithm. Finally, the superposition of the two partitions of the image will determine the sick zones. The originality of our approach is the parallel exploitation of different types of information in the image by the cooperation of two complementary approaches, which permits to carry out a robust approach for the detection of sick zones in MRI images.
Descriptors		BRAIN NEOPLASMS MAGNETIC RESONANCE IMAGING IMAGE PROCESSING, COMPUTER-ASSISTED