Data augmentation (DA) has been widely leveraged in the realm of computer vision to alleviate the data shortage, whereas the DA in medical image analysis (MIA) faces multiple challenges. The prevalent DA approaches in MIA encompass conventional DA, synthetic DA, and automatic DA. However, the utilization of these approaches poses various challenges such as experience-driven design and intensive computation cost. Here, we propose an efficient and effective automatic DA method termed MedAugment. We propose the pixel augmentation space and spatial augmentation space and exclude the operations that can break the details and features within medical images. Besides, we propose a novel sampling strategy by sampling a limited number of operations from the two spaces. Moreover, we present a hyperparameter mapping relationship to produce a rational augmentation level and make the MedAugment fully controllable using a single hyperparameter. These revisions address the differences between natural and medical images. Extensive experimental results on four classification and three segmentation datasets demonstrate the superiority of MedAugment. We posit that the plug-and-use and training-free MedAugment holds the potential to make a valuable contribution to the medical field, particularly benefiting medical experts lacking foundational expertise in deep learning. Code is available at https://github.com/NUS-Tim/MedAugment.

翻译：数据增强已在计算机视觉领域被广泛用于缓解数据短缺问题，但在医学图像分析中面临多重挑战。当前的医学图像分析主流数据增强方法包括传统增强、合成增强和自动增强。然而，这些方法存在依赖经验设计和计算成本高昂等问题。本文提出一种高效且有效的自动数据增强方法MedAugment。我们构建了像素增强空间和空间增强空间，并排除了可能破坏医学图像细节与特征的操作。此外，我们提出一种新型采样策略，从这两个空间中采样有限数量的操作。同时，引入超参数映射关系以生成合理的增强强度，使得单个超参数即可完全控制MedAugment。这些改进针对自然图像与医学图像之间的差异进行了优化。在四个分类数据集和三个分割数据集上的广泛实验结果表明，MedAugment具有显著优越性。我们认为，这种即插即用且无需训练的MedAugment有望为医学领域做出重要贡献，尤其惠及缺乏深度学习基础知识储备的医疗从业者。代码已开源至https://github.com/NUS-Tim/MedAugment。