论文标题
无监督的息肉细分的合成数据
Synthetic data for unsupervised polyp segmentation
论文作者
论文摘要
深度学习在分析医学图像方面表现出色。但是，数据集很难获得适当的隐私问题，标准化问题和缺乏注释。我们通过使用3D技术和生成对抗网络的组合生成逼真的合成图像来解决这些问题。我们使用管道中医疗专业人员的零注释。我们完全无监督的方法在五个实际的息肉分割数据集上取得了有希望的结果。作为这项研究的一部分，我们发布了合成的数据集，其中包括20000个现实的结肠图像以及有关深度和3D几何形状的其他详细信息：https：//enric19994.github.io/synth-colon
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
