Data Augmentation (DA) technique has been widely implemented in the computer vision field to relieve the data shortage, while the DA in Medical Image Analysis (MIA) is still mostly experience-driven. Here, we develop a plug-and-use DA method, named MedAugment, to introduce the automatic DA argumentation to the MIA field. To settle the difference between natural images and medical images, we divide the augmentation space into pixel augmentation space and spatial augmentation space. A novel operation sampling strategy is also proposed when sampling DA operations from the spaces. To demonstrate the performance and universality of MedAugment, we implement extensive experiments on four classification datasets and three segmentation datasets. The results show that our MedAugment outperforms most state-of-the-art DA methods. This work shows that the plug-and-use MedAugment may benefit the MIA community. Code is available at https://github.com/NUS-Tim/MedAugment_Pytorch.

翻译：数据增强（DA）技术已在计算机视觉领域广泛用于缓解数据短缺问题，但在医学图像分析（MIA）中，数据增强仍主要依赖经验驱动。本文开发了一种名为MedAugment的即插即用式DA方法，将自动数据增强引入MIA领域。为处理自然图像与医学图像之间的差异，我们将增强空间划分为像素增强空间与空间增强空间，并提出了一种从这些空间中采样DA操作时的新型操作采样策略。为验证MedAugment的性能与通用性，我们在四个分类数据集和三个分割数据集上开展了大量实验。结果表明，MedAugment优于多数当前最优的DA方法。本研究表明，即插即用式MedAugment可为MIA领域带来助益。代码已开源至https://github.com/NUS-Tim/MedAugment_Pytorch。