Mri brain image classification system using super pixel color contrast and support vector neural network

Abstract

The automatic classification of glioma on MR images has been widely used in the diagnosis and treatments of cancer. However, due to the shape of prostate varies significantly and low contrast with adjacent structures, the classification of MR images faces great challenges. Using information from MR images, CAD systems have been developed to benefit doctors in rapid diagnosis. CAD systems can provide the diagnosis depending upon the specific attributes present in the medical images. The present study proposes a comprehensive method for the diagnosis of the cancerous region in the MRI images. Here, after image noise reduction, optimal image segmentation based on support vector neural network algorithm is utilized. Afterward, an optimized feature extraction and feature selection based on a modified region growing optimization algorithm are proposed for improving the classification accuracy of brain images. Further, it is also proposed that the input MR brain image be de-noised using a non-local Euclidean median in non-subsampled contour-led space. Experimental results show the effectiveness of adversarial learning and SVNN on the classification of prostate MR images. At the same time, the proposed method achieves advanced results and outperforms most of the other existing methods on various evaluation metrics.