Image-to-Image Translation for Data Augmentation on Multimodal Medical Images

Medical images play an important role in medical diagnosis. However, acquiring a large number of datasets with annotations is still difficult task the field. For this reason, research field image-to-image translation combined computer-aided diagnosis, and data augmentation methods based on generative adversarial networks are applied to images. In paper, we try perform unimodal data. The designed StarGAN V2 network has high performance augmenting dataset using small original images, augmented expanded from multimodal image can be segmentation some improvement results. Our experiments demonstrate that generated improve glioma segmentation.