Genetic algorithms for finite mixture model based voxel classification in neuroimaging
Genetic algorithms for finite mixture model based voxel classification in neuroimaging
复制标题
DOI：
10.1109/tmi.2007.895453
复制
发表时间：
2007-05-01
影响因子：
10.6
通讯作者：
Toga, Arthur W.
中科院分区：
文献类型：
--
作者：
Tohka, Jussi;Krestyannikov, Evgeny;Toga, Arthur W.
有限混合模型(FMM)是脑成像中非监督分类不可缺少的工具。对数据进行FMM拟合导致了一个复杂的优化问题。如果没有原则性的初始化，这个优化问题很难用标准的局部优化方法，如期望最大化(EM)算法来解决。针对FMM参数估计问题，提出了一种基于实数编码遗传算法的全局优化算法。我们的具体贡献有两个方面：1)我们提出使用混合交叉，以将早熟收敛问题减少到最小；2)我们引入了一个全新的置换算子，专门用于FMM参数估计。除了改进优化结果之外，置换运算符还允许对FMM参数值施加生物上有意义的约束。我们还介绍了一种遗传算法和EM算法的混合算法，用于有效地求解多维FMM拟合问题。我们将我们的算法与自退火EM算法和标准实数编码遗传算法进行了比较，并与脑成像中的体素分类任务进行了比较。这些算法在合成数据以及来自人类磁共振成像、正电子发射断层扫描和小鼠脑MRI的真实三维图像数据上进行了测试。与其他参数估计方法相比，我们的方法得到的组织分类结果具有更高的可靠性和准确性。
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.