MFGAN: A medical image fusion generative adversarial network Using attention mechanism

Fusion is a key step to improve the ability of cancer screening and detection in medical images. In this task, an unsupervised generation adversarial network is proposed to solve the multimodal medical image fusion problem. This method introduces the attention mechanism into the generation network, so that the feature extraction layers pay more attention to useful information. And the double condition discriminator is involved to determine whether the generated image is consistent with the input image. The experimental results show that our network is superior to other most advanced methods in quality analysis and quantitative measurement.