2015 International Symposium of Computer Application and Information Technology (IsCait 2015)

257 / 1971-01-01 00:00:00

3d Mr Brain Image Segmentation Through Quantum Particle Swarm Optimization-based Algorithm

MRI,Segmentation,QPSO,HMRF,EM

In this paper, a novel segmentation methodol-
ogy for Magnetic Resonance Image (MRI) of brain tissues
is presented and validated. The method is inspired by
our previously developed quantum-behaved particle swarm
optimization (QPSO) algorithm, and combined with Hid-
den Markov Random Field model and the Expectation-
Maximization algorithm (HMRF-EM), which can be applied
to MRIs in real-time environments. The QPSO is a stochastic
optimization algorithm, which shows better performance
than the standard particle swarm optimization (PSO) algo-
rithm. This hybrid method shows less sensitivity to the initial
estimation of parameters in contrast with other traditional
stochastic optimization techniques for MRF. Experimental
results on both simulated and real MR images are presented
to verify the advantages of the proposed method over its
competitors.