Glioma Segmentation-Oriented Multi-Modal MR Image Fusion With Adversarial Learning

Dear Editor, In recent years, multi-modal medical image fusion has received widespread attention in the processing community. However, existing works on methods are mostly devoted to pursuing high performance visual perception and objective metrics, while ignoring specific purpose clinical applications. this letter, we propose a glioma segmentation-oriented magnetic resonance (MR) method using an adversarial learning framework, which adopts segmentation network as discriminator achieve more meaningful results from perspective of task. Experimental demonstrate advantage proposed over some state-of-the-art methods.