MRI segmentation is critically important for clinical study and diagnosis. Existing methods based on soft clustering have several drawbacks, including low accuracy in the presence of image noise and artifacts, and high computational cost. In this paper, we introduce a new formulation of the MRI segmentation problem as a kernel-based intuitionistic fuzzy C-means (KIFCM) clustering problem and propose a new DNA-based genetic algorithm to obtain the optimal KIFCM clustering. While this algorithm searches the solution space for the optimal model parameters, it also obtains the optimal clustering, therefore the optimal MRI segmentation. We perform empirical study by comparing our method with six state-of-the-art soft clustering methods using a set of UCI (University of California, Irvine) datasets and a set of synthetic and clinic MRI datasets. The preliminary results show that our method outperforms other methods in both the clustering metrics and the computational efficiency.

As one of the evolutionary heuristics methods, genetic algorithms (GAs) have shown a promising ability to solve complex optimization problems. However, existing GAs still have difficulties in finding the global optimum and avoiding premature convergence. To further improve the search efficiency and convergence rate of evolution algorithms, inspired by the mechanism of biological DNA genetic information and evolution, we present a new genetic algorithm, called GA-TNE+DRO, which uses a novel triplet nucleotide coding scheme to encode potential solutions and a set of new genetic operators to search for globally optimal solutions. The coding scheme represents potential solutions as a sequence of triplet nucleotides and the DNA reproduction operations mimic the DNA reproduction process more vividly than existing DNA-GAs. We compared our algorithm with several existing GA and DNA-based GA algorithms using a benchmark of eight unconstrained optimization functions. Our experimental results show that the proposed algorithm can converge to solutions much closer to the global optimal solutions in a much lower number of iterations than the existing algorithms. A complexity analysis also shows that our algorithm is computationally more efficient than the existing algorithms.