A Novel Computational Intelligence-based Approach for Medical Image Artifacts Detection

In this research, a novel computational intelligencebased algorithm to detect artifacts, specifically arrows, in medical images is presented. Image analyses techniques are developed to find the symbols and text automatically. Features are computed from the shape of arrow for the discrimination of arrows from other artifacts. We investigate a biologically-inspired reinforcement learning (RL) approach in an adaptive critic design (ACD) framework to apply Action Dependent Heuristic Dynamic Programming (ADHDP) for arrow discrimination based on the computed features. Experimental results for ADHDP are compared with feed forward multi-layer perception (MLP) back-propagation artificial neural networks (BP-ANN), particle swarm optimization (PSO) for training of a MLP neural network, genetic algorithm (GA) for training of a MLP neural network, k-nearest neighbor (KNN), and support vector machine (SVM).