Fusion of contourlet transform and zernike moments using content based image retrieval for MRI brain tumor images

Abstract

Background: Content based Image Retrieval (CBIR) is employed to search and retrieve the expected image from the database. Magnetic Resonance Imaging (MRI) technique plays a crucial role in diagnosing many diseases in human brain. Methods: In this paper, we proposed a texture fusion technique for T1 and T2 weighted MRI scans. Our proposed technique has three parts. First, texture and shape features are extracted from a brain tumor images. Next, the feature selection techniques like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) are used to combine the texture and shape features. Finally, the popular supervised learning machine techniques like Deep Neural Network (DNN) and Extreme Learning Machine (ELM) are used to classify the brain tumor based on the selected features. Findings: The results of proposed MRI brain tumor diagnosis method are robust, efficient, effective, reduces the retrieval time and improves the retrieval accuracy significantly. Best overall classification accuracy results were obtained using the given DiCom Images. Application: The proposed MRI image based brain tumor retrieval would efficiently deal with a medical decision system based on the CT+ZM fusion method provides more accurate results, so this method can yield better result of brain tumor diagnosis in advance where this method using in medical fields.