Cut to the Mix: Simple Data Augmentation Outperforms Elaborate Ones in Limited Organ Segmentation Datasets

TL;DR

This paper demonstrates that simple inter-image data augmentation methods like CutMix outperform more complex strategies in limited organ segmentation datasets, significantly improving model accuracy.

Contribution

The study systematically compares inter-image data augmentation techniques and shows that simple methods like CutMix outperform elaborate strategies for multi-organ segmentation.

Findings

CutMix improves dice score by 4.9 points over baseline.

Inter-image augmentation strategies enhance segmentation accuracy.

Simple augmentation methods can outperform complex ones in limited data scenarios.

Abstract

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.