Fuzzy information fusion scheme used to segment brain tumor from MR images

Authors:
Weibei Dou;Su Ruan;Qingmin Liao;Daniel Bloyet;Jean-Marc Constans;Yanping Chen
Affiliations:
GREYC-CNRS UMR 6072, Caen, France;GREYC-CNRS UMR 6072, Caen, France;Department of Electronic Engineering, Tsinghua University, Beijing, China;GREYC-CNRS UMR 6072, Caen, France;Unité d'IRM, CHRU, Caen, France;Imaging Diagnostic Center, Nanfang Hospital, Guangzhou, China
Venue:
WILF'03 Proceedings of the 5th international conference on Fuzzy Logic and Applications
Year:
2003

Citing 2
Cited 1

Mathematical Techniques in Multisensor Data Fusion

Mathematical Techniques in Multisensor Data Fusion
Fuzzy Markovian segmentation in application of magnetic resonance images

Computer Vision and Image Understanding

Editorial: Information fusion in the realm of medical applications - A bibliographic glimpse at its growing appeal

Information Fusion

Quantified Score

Hi-index	0.00

Visualization

Abstract

A fuzzy information fusion scheme is proposed in this paper to automatically segment tumor areas of human brain from multispectral magnetic resonance images such as T1-weighted, T2-weighted and Proton Density (PD) feature images. The proposed scheme consists of four stages: data-level fusion, space creation of fuzzy features, fusion of fuzzy features and fuzzy decision. Several fuzzy operators are proposed to create the feature-level fusion. The fuzzy information models describing the characteristics of tumor areas in human brain are also established. A fuzzy region growing based on fuzzy connecting is presented to obtain the final segmentation result. The comparison between the result of our method and the hand-labeled segmentation of a radiology expert shows that this scheme is efficient. The experimental results (based on 4 patients studied) show an average probability of correct detection equal to 96% and an average probability of false detection equal to 5%.