Multi-organ segmentation is a widely applied clinical routine and automated organ segmentation tools dramatically improve the pipeline of the radiologists. Recently, deep learning (DL) based segmentation models have shown the capacity to accomplish such a task. However, the training of the segmentation networks requires large amount of data with manual annotations, which is a major concern due to the data scarcity from clinic. Working with limited data is still common for researches on novel imaging modalities. To enhance the effectiveness of DL models trained with limited data, data augmentation (DA) is a crucial regularization technique. Traditional DA (TDA) strategies focus on basic intra-image operations, i.e. generating images with different orientations and intensity distributions. In contrast, the interimage and object-level DA operations are able to create new images from separate individuals. However, such DA strategies are not well explored on the task of multi-organ segmentation. In this paper, we investigated four possible inter-image DA strategies: CutMix, CarveMix, ObjectAug and AnatoMix, on two organ segmentation datasets. The result shows that CutMix, CarveMix and AnatoMix can improve the average dice score by 4.9, 2.0 and 1.9, compared with the state-of-the-art nnUNet without DA strategies. These results can be further improved by adding TDA strategies. It is revealed in our experiments that Cut-Mix is a robust but simple DA strategy to drive up the segmentation performance for multi-organ segmentation, even when CutMix produces intuitively 'wrong' images. Our implementation is publicly available for future benchmarks.

翻译：多器官分割是一种广泛应用的临床常规流程，自动化器官分割工具极大地改善了放射科医生的工作流程。近年来，基于深度学习的分割模型已展现出完成此类任务的能力。然而，分割网络的训练需要大量带有手动标注的数据，由于临床数据稀缺，这成为一个主要问题。对于新型成像模态的研究而言，在有限数据条件下开展工作仍很常见。为提升在有限数据下训练的深度学习模型的有效性，数据增强是一种至关重要的正则化技术。传统数据增强策略侧重于基本的图像内操作，即生成具有不同方向和强度分布的图像。相比之下，图像间和对象级的数据增强操作能够从不同个体中创建新图像。然而，此类数据增强策略在多器官分割任务上尚未得到充分探索。本文在两种器官分割数据集上研究了四种可能的图像间数据增强策略：CutMix、CarveMix、ObjectAug和AnatoMix。结果表明，与未使用数据增强策略的最先进nnUNet相比，CutMix、CarveMix和AnatoMix可将平均Dice分数分别提高4.9、2.0和1.9。通过加入传统数据增强策略，这些结果可得到进一步改善。我们的实验揭示，CutMix是一种鲁棒且简单的数据增强策略，即使其生成的图像在直觉上看似“错误”，也能有效提升多器官分割的性能。我们的实现已公开，以供未来基准测试使用。