Automatic liver CT image clustering based on invasive weed optimization algorithm

In this paper, an automated liver CT image clustering approach based on evolutionary metaheuristic algorithm called invasive weed optimization is presented without any prior information about the number of naturally occurring groups in the images. The fitness function used in the genetic algorithm is k-means objective function for searching of the smoothed compact cluster. The experimental results suggest that invasive weed optimization holds immense promise to appear as an efficient metaheuristic for multi-objective optimization in computer aided diagnosis applications.