Classification of Brain Tumors Using Hybridized Convolutional Neural Network in Brain MRI images


Authors: Shwetha V, C. H. Renu Madhavi, Nagendra Kumar M.

Abstract: In this research article, we have proposed a novel technique to operate on the Magnetic Resonance Imaging (MRI) data images which can be classified as image classification, segmentation and image denoising. With the efficient utilization of MRI images the medical experts are able to identify the medical disorders such as tumors which are correspondent to the brain. The prime agenda of the study is to organize brain into healthy and brain with tumor in brain with the test MRI data as considered. The MRI based technique is an methodology to study brain tumor based information for the better detailing of the internal body images when compared to other technique such as Computed Tomography (CT).Initially the MRI image is denoised using Anisotropic diffusion filter, then MRI image is segmented using Morphological operations, to classify the images for the disorder CNN based hybrid technique is incorporated, which is associated with five different set of layers with the pairing of pooling and convolution layers for the comparatively improved performance than other existing technique. The considered data base for the designed model is a publicly available and tested KAGGLE database for the brain MRI images which has resulted in the accuracy of 88.1%.

Pages: 561-570

DOI: 10.46300/9106.2022.16.70

International Journal of Circuits, Systems and Signal Processing, E-ISSN: 1998-4464, Volume 16, 2022, Art. #70

PDF DOI XML

Certification