Using PSO to improve dynamic programming based algorithm for breast mass segmentation

Accurate segmentation of breast masses plays a crucial role in computer-aided mammography screening systems. In this paper, an improved algorithm based on dynamic programming is proposed for breast mass segmentation. The key idea focuses on generating optimal weights of the components of local cost by particle swarm optimization algorithm, and searching the optimal path in a restricted region. The experimental results show the validity of the proposed algorithm compared to other methods.