Title: Analysing thalamus and its sub nuclei in MRI brain image to distinguish schizophrenia subjects using back propagation neural network
Authors: K. ArivuSelvan; E. Sathiya Moorthy
Addresses: School of Information Technology and Engineering, Vellore Institute of Technology (VIT), Vellore, India ' School of Information Technology and Engineering, Vellore Institute of Technology (VIT), Vellore, India
Abstract: In this paper, we presented precise and proficient techniques for measuring the human thalamus, medial dorsal and the pulvinar nucleus with magnetic resonance imaging (MRI). In spite of the fact that thalamic nuclei are not straightforwardly visible on traditional MRI image. We applied a novel and competent image pre-processing techniques to enhance the visual quality of MRI image. In addition to this we have used various segmentation algorithms to accurately extract entire thalamus from brain MRI images. Diffusion MRI is used to extract various nucleus of thalamus. Several optimal features such as textures, morphological are derived from thalamus and medial dorsal regions which are then used to train the artificial neural network model (ANN). Our artificial neural network model accurately classifies between schizophrenic and healthy subjects based on thalamic anatomy for larger sample sizes.
Keywords: thalamus; artificial neural networks; magnetic resonance imaging; MRI; schizophrenia; GLCM; sobel; level set; fast marching.
International Journal of Internet Technology and Secured Transactions, 2020 Vol.10 No.1/2, pp.196 - 210
Received: 21 Dec 2017
Accepted: 21 Jan 2018
Published online: 20 Jan 2020 *