Deep learning has shown excellent performance in analysing medical images. However, datasets are difficult to obtain due privacy issues, standardization problems, and lack of annotations. We address these problems by producing realistic synthetic images using a combination of 3D technologies and generative adversarial networks. We use zero annotations from medical professionals in our pipeline. Our fully unsupervised method achieves promising results on five real polyp segmentation datasets. As a part of this study we release Synth-Colon, an entirely synthetic dataset that includes 20000 realistic colon images and additional details about depth and 3D geometry: https://enric1994.github.io/synth-colon

翻译：在分析医学图像方面,深层的学习显示在分析医学图像方面表现出色,然而,数据集很难获得适当的隐私问题、标准化问题和缺乏说明。我们通过结合3D技术和基因对抗网络,制作现实的合成图像来解决这些问题。我们在编审过程中使用医学专业人员的零说明。我们完全不受监督的方法在5个真实的聚合分块数据集上取得了有希望的结果。作为本研究的一部分,我们发行了Synth-Colon,这是一个完全合成的数据集,其中包括20000个现实的结肠图像和关于深度和3D几何学的更多细节:https://enric1994.github.io/synth-cron:https://enric1994.gthub.so/synth-cron。