Genetic Algorithms for Finite Mixture Model Based Voxel Classification in Neuroimaging

• Published in: IEEE transactions on medical imaging Vol. 26; no. 5; pp. 696 - 711
• Main Authors: Tohka, Jussi, Krestyannikov, Evgeny, Dinov, Ivo D., Graham, Allan MacKenzie, Shattuck, David W., Ruotsalainen, Ulla, Toga, Arthur W.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2007; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Animals; Artificial Intelligence; Biological information theory; Brain - anatomy & histology; Brain - diagnostic imaging; Brain modeling; Computer Simulation; Constraint optimization; Convergence; Finite Element Analysis; Genetic algorithms; Global optimization; Humans; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; image segmentation; Imaging, Three-Dimensional - methods; Magnetic resonance imaging; magnetic resonance imaging (MRI); Magnetic Resonance Imaging - methods; Medical imaging; Mice; Models, Genetic; Models, Neurological; Multidimensional systems; Neuroanatomy - methods; Neuroimaging; Optimization algorithms; Optimization methods; Parameter estimation; Pattern Recognition, Automated - methods; positron emission tomography (PET); Positron-Emission Tomography - methods; Reproducibility of Results; Sensitivity and Specificity; Studies
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2007.895453

Finite mixture models (FMMs) are an indispensable tool for unsupervised classification in brain imaging. Fitting an FMM to the data leads to a complex optimization problem. This optimization problem is difficult to solve by standard local optimization methods, such as the expectation-maximization (EM) algorithm, if a principled initialization is not available. In this paper, we propose a new global optimization algorithm for the FMM parameter estimation problem, which is based on real coded genetic algorithms. Our specific contributions are two-fold: 1) we propose to use blended crossover in order to reduce the premature convergence problem to its minimum and 2) we introduce a completely new permutation operator specifically meant for the FMM parameter estimation. In addition to improving the optimization results, the permutation operator allows for imposing biologically meaningful constraints to the FMM parameter values. We also introduce a hybrid of the genetic algorithm and the EM algorithm for efficient solution of multidimensional FMM fitting problems. We compare our algorithm to the self-annealing EM-algorithm and a standard real coded genetic algorithm with the voxel classification tasks within the brain imaging. The algorithms are tested on synthetic data as well as real three-dimensional image data from human magnetic resonance imaging, positron emission tomography, and mouse brain MRI. The tissue classification results by our method are shown to be consistently more reliable and accurate than with the competing parameter estimation methods.