Background and Objective:
In order to reduce time complexity and to improve the
computational efficiency in diagnosing process, automated brain tissue segmentation for magnetic
resonance brain images is proposed in this paper.
Methods:
This method incorporates two processes, the first one is preprocessing and the second
one is segmentation of brain tissue using Histogram based Swarm Optimization techniques. The
proposed method was investigated with images obtained from twenty volumes and eighteen volumes
of T1-Weighted images obtained from Internet Brain Segmentation Repository (IBSR), Alzheimer
disease images from Minimum Interval Resonance Imaging in Alzheimer's Disease (MIRIAD)
and T2-Weighted real-time images collected from SBC Scan Center Dindigul.
Results:
The proposed technique was tested with three brain image datasets. Quantitative evaluation
was done with Jaccard (JC) and Dice (DC) and also it was compared with existing swarm optimization
techniques and other methods like Adaptive Maximum a posteriori probability (AMAP),
Biased Maximum a posteriori Probability (BMAP), Maximum a posteriori Probability (MAP),
Maximum Likelihood (ML) and Tree structure K-Means (TK-Means).
Conclusion:
The performance comparative analysis shows that our proposed method Histogram
based Darwinian Particle Swarm Optimization (HDPSO) gives better results than other proposed
techniques such as Histogram based Particle Swarm Optimization (HPSO), Histogram based Fractional
Order Darwinian Particle Swarm Optimization (HFODPSO) and with existing swarm optimization
techniques and other techniques like Adaptive Maximum a posteriori Probability
(AMAP), Biased Maximum a posteriori Probability (BMAP), Maximum a posteriori Probability
(MAP), Maximum Likelihood (ML) and Tree structure K-Means (TK-Means).