Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks
复制标题
DOI：
10.1038/s41598-019-52737-x
复制
发表时间：
2019-11-15
影响因子：
4.6
通讯作者：
Summers, Ronald M.
中科院分区：
文献类型：
--
作者：
Sandfort, Veit;Yan, Ke;Summers, Ronald M.
标记的医学成像数据稀缺，生成成本也很高。为了实现可推广的深度学习模型，需要大量的数据。标准数据扩充是一种增加泛化能力的方法，并且是常规执行的。产生式对抗网络为数据扩充提供了一种新的方法。我们评估了在CT分割任务中使用CycleGAN进行数据增强的效果。利用一个大的图像库，我们训练了一个CycleGAN来将对比CT图像转换成非对比图像。然后，我们使用训练过的CycleGan来增强我们的训练，使用这些合成的非对比度图像。我们比较了在原始数据集上训练的U-网和在原始数据和合成非对比度图像的组合数据集上训练的U-网的分割性能。我们进一步评估了U-Net在两个独立数据集上的分割性能：在原始对比CT数据集上创建了分割，以及来自不同医院的第二个数据集仅包含非对比CT。我们将这两个单独的数据集分别称为分布内数据集和分布外数据集。我们发现，在几个CT分割任务中，性能都得到了显著的改善，特别是在分布不均匀(非对比度CT)的数据中。例如，当用标准增强技术训练模型时，分布外非对比度图像上肾脏分割的性能显著低于分布内数据(分布外数据与分布内数据的Dice分数分别为0.09vs.0.94，p<；0.001)。当用CycleGAN增强技术训练肾脏模型时，分布不均匀(非对比度)的表现显著增加(从0.09分增加到0.66分，p<；0.001)。肝脏和脾的改善较小，分别从0.86到0.89和0.65到0.69。我们相信，这种方法对于医学影像研究人员减少CT成像中的人工分割工作量和成本将是有价值的。
Labeled medical imaging data is scarce and expensive to generate. To achieve generalizable deep learning models large amounts of data are needed. Standard data augmentation is a method to increase generalizability and is routinely performed. Generative adversarial networks offer a novel method for data augmentation. We evaluate the use of CycleGAN for data augmentation in CT segmentation tasks. Using a large image database we trained a CycleGAN to transform contrast CT images into non-contrast images. We then used the trained CycleGAN to augment our training using these synthetic non-contrast images. We compared the segmentation performance of a U-Net trained on the original dataset compared to a U-Net trained on the combined dataset of original data and synthetic non-contrast images. We further evaluated the U-Net segmentation performance on two separate datasets: The original contrast CT dataset on which segmentations were created and a second dataset from a different hospital containing only non-contrast CTs. We refer to these 2 separate datasets as the in-distribution and out-of-distribution datasets, respectively. We show that in several CT segmentation tasks performance is improved significantly, especially in out-of-distribution (noncontrast CT) data. For example, when training the model with standard augmentation techniques, performance of segmentation of the kidneys on out-of-distribution non-contrast images was dramatically lower than for in-distribution data (Dice score of 0.09 vs. 0.94 for out-of-distribution vs. in-distribution data, respectively, p < 0.001). When the kidney model was trained with CycleGAN augmentation techniques, the out-of-distribution (non-contrast) performance increased dramatically (from a Dice score of 0.09 to 0.66, p < 0.001). Improvements for the liver and spleen were smaller, from 0.86 to 0.89 and 0.65 to 0.69, respectively. We believe this method will be valuable to medical imaging researchers to reduce manual segmentation effort and cost in CT imaging.