Fuzzy Modeling Of Knowledge For MRI Brain Structure Segmentation

Jing-Hao Xue (1, 2) , Su Ruan (3) , Bruno Moretti (1) , Marinette Revenu (3) , Daniel Bloyet (1) , Wilfried Philips (2)

1 GREYC - Groupe de Recherche en Informatique, Image et Instrumentation de Caen
2 TELIN/UGent - Department of Telecommunications and Information Processing
3 Equipe Image - Laboratoire GREYC - UMR6072

In this paper, we propose a novel automatic method based on fuzzy modeling of knowledge to segment brain structures in MRI (Magnetic Resonance Imaging) images. The segmentation is achieved by the region-wise classification using GAs (Genetic Algorithms), followed by the voxelwise refinement using parallel region growing. To improve the accuracy of the labeling, we introduce a fuzzy model of ROI (Regions Of Interest) by analogy with the electrostatic potential distribution, to represent more appropriately knowledge of shape, distance and reaction between structures, and to estimate more reliably the statistical moments. This modeling is also used in the design of the fitness function of GAs, and the criteria of the region growing. The performance of our proposed method has been quantitatively validated by 4 indexes with respect to manually segmented images.

Domaines: Traitement des images [eess.IV]

Jing-Hao Xue, Su Ruan, Bruno Moretti, Marinette Revenu, Daniel Bloyet, et al.. Fuzzy Modeling Of Knowledge For MRI Brain Structure Segmentation. International Conference on Image Processing ICIP, 2000, Vancouver, Canada. pp.617-620. ⟨hal-00960267⟩