arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.05946cs.CV
收藏

结合渐进生长GAN和SPADE合成脑肿瘤图像和注释

Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE

Linköping University(林雪平大学)

Mehdi Foroozandeh, Anders Eklund

摘要:

训练分割网络需要大量带注释的数据集,但手动注释既耗时又昂贵。我们在这里调查,如果一个噪声到图像的GAN和图像到图像的GAN的组合可以用来合成逼真的脑肿瘤图像以及相应的肿瘤注释(标签),以大幅增加训练图像的数量。噪声到图像GAN用于合成新的标记图像,而图像到图像GAN从标记图像生成相应的MR图像。我们的研究结果表明,这两个GANs可以合成看起来逼真的标签图像和MR图像,并且添加合成图像可以提高分割性能,尽管效果很小。

英文摘要:

Training segmentation networks requires large annotated datasets, but manual annotation is time consuming and costly. We here investigate if the combination of a noise-to-image GAN and an image-to-image GAN can be used to synthesize realistic brain tumor images as well as the corresponding tumor annotations (labels), to substantially increase the number of training images. The noise-to-image GAN is used to synthesize new label images, while the image-to-image GAN generates the corresponding MR image from the label image. Our results indicate that the two GANs can synthesize label images and MR images that look realistic, and that adding synthetic images improves the segmentation performance, although the effect is small.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑