The segmentation and classi fication of brain magnetic resonance (MR) images are the crucial and challenging task for radiologists. The conventional methods for analyzing brain images are time-consuming and ineffectiv...
详细信息
The segmentation and classi fication of brain magnetic resonance (MR) images are the crucial and challenging task for radiologists. The conventional methods for analyzing brain images are time-consuming and ineffective in decision-making. Thus, to overcome these limitations, this work proposes an automated and robust computer-aided diagnosis (CAD) system for accurate classi fication of normal and abnormal brain MR images. The proposed CAD system has the ability to assist the radiologists for diagnosis of brain MR images at an early stage of abnormality. Here, to improve the quality of images before their segmentation, contrast limited adaptive histogram equalization (CLAHE) is employed. The segmentation of the region of interest is obtained using the multilevel Otsu's thresholding algorithm. In addition, the proposed system selects the most signi ficant and relevant features from the texture and multiresolution features. The multiresolution features are extracted using discrete wavelet transform (DWT), stationary wavelet transform (SWT), and fast discrete curvelet transform (FDCT). Moreover, the Tamura and local binary pattern (LBP) are used to extract the texture features from the images. These features are used to classify the brain MR images using feedforward neural network (FNN) classi fier, where different meta-heuristic optimization algorithms, e.g., genetic algorithm (GA), particle swarm optimization (PSO), gravitationalsearchalgorithm (GSA), and gbest-guided gravitational search algorithm (GGGSA) are employed for optimizing the weights and biases of FNN. The extensive experimental results on DS-195, DS-180, and three standard datasets show that the classi fication accuracy of GG-GSA based FNN classi fier outperforms all mentioned meta-heuristic-based classi fiers and several state-of-the-art methods. (C) 2020 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.
This study deals with the implementation of highly accurate, stable, minimum phase, and wideband fractional-order digital differentiators (FODDs) in terms of infinite impulse response filters using an efficient evolut...
详细信息
This study deals with the implementation of highly accurate, stable, minimum phase, and wideband fractional-order digital differentiators (FODDs) in terms of infinite impulse response filters using an efficient evolutionary optimisation algorithm called adaptive gbest-guided gravitational search algorithm (GGSA). Performance evaluation of GGSA as compared with real coded genetic algorithm (RGA), particle swarm optimisation (PSO), and differential evolution (DE) based designs are carried out in terms of different magnitude and phase response error metrics, solution quality reliability, and convergence speed. Simulation results clearly demonstrate that GGSA significantly outperforms RGA, PSO, and DE in consistently achieving the most accurate FODDs in a computationally efficient manner. The proposed FODDs also significantly outperform all state-of-the-art designs in terms of magnitude responses.
暂无评论