Brain MRI and CT Image Fusion Using Generative Adversarial Network

Abstract

AbstractThe generative adversarial networks (GAN), complete model, is used to fuse computed tomography (CT) and magnetic resonance imaging (MRI) brain images in this research paper. To create a resultant fused image with bone structures from CT images and soft tissues from MRI images, our method develops an adversarial game between a generator and a discriminator. To make a stable training process, we use GAN instead of conventional fusion methods, and our architecture can handle different resolutions of multi-source medical images. The efficacy of the proposed procedure is demonstrated using several evaluation metrics. The proposed algorithms provide the best fused images without distortion and false artefacts. Comparison of proposed methods is done with the conventional techniques. The images obtained by fusing both sources’ content with the help of the above algorithm gives the best with respect to visualization and diagnosis of the condition.KeywordsCTMRIDeep learningGANImage fusion